nyx-skills

The official skillset consisting of core agent manuals to operate ChronoAI official services.

12 skills

Turn an ambiguous request into scoped testable acceptance criteria with risks and edge cases.

1 skill

只读体检验收 canary 数据是否漂移、fixture 是否完好。用户提到“验收 fixture 漂移体检”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Subject a claim to two independent skeptical reviews pass only if neither refutes.

1 skill

testing skill for aevatar bot

1 skill

Use when a user wants to create, edit, validate, publish, or explain an Aevatar Agent Profile; set purpose or instructions; bind exact Ornn skills and activation modes; restrict tool authority; or diagnose ETag, validation, publication, deployment exposure, or runtime binding. Agent Profile is a separate resource, not a workflow, member, team, service, or schedule. Use the opaque profileId, exact `{skillGuid, literalVersion, expectedName, expectedPublisherId}` references, strong ETags, accepted-vs-committed semantics, and capability detection before mutation.

1 skill

Boundary test for inbound Lark attachments — the user sends an image or file alongside this command and the bot reports exactly what it can observe on the chat path (text only, attachment refs, or nothing), without guessing. Detects when the platform wires chat-path attachment visibility so dependent skills can be upgraded.

1 skill

Aevatar scheduling & workflow automation: scheduled_agent_creator (cron/one-shot) for independent scheduled Ornn skill agents and reminders — NOT an alias for Studio Team member automation — the long-running task automation playbook, workflow creation semantics (Scope Workflow vs Ornn publish), agent_builder lifecycle, the typed required_nyx_services contract (exact user_service_id is the authorization; a slug snapshot never substitutes), dedicated Agent Key semantics (vault-held raw material, borrowed durable reference late-resolved per use, exact non-wildcard grants, ~90-day projected expiry, reauthorize-then-revoke, independent NyxID and Vault revocation tracks), accepted-is-admission-only receipts, and a token_expired triage protocol that reads credentialSourceKind before assuming any TTL.

1 skill

Aevatar channel & delivery how-to: capability tools (code_execute, nyxid_proxy, GitHub PAT fallback, channel bots), token_expired/401 credential triage that identifies the typed credential source before interpreting the failure (a dedicated scheduled-invocation Agent Key is vault-held and late-resolved per use — never diagnose it with the 300-second broker TTL), LLM route selection slash commands, channel_registrations (staged Lark provisioning), agent_delivery_targets binding, and a strict never-emit-secret-material policy.

1 skill

Configure and prove Aevatar codex_exec for one NyxID account, choosing operator-managed chrono-sandbox/gVisor for bounded empty-workspace work or private NyxID node-backed SSH for a fixed host workspace. Use for managed eligibility and UserService readiness, private node/SSH hardening, mandatory public-sample verification, or diagnosing typed managed and private-route failures.

1 skill

Mount and run harmless Aevatar workflows that prove codex_exec works through either the operator-managed chrono-sandbox/gVisor target or a private NyxID node-backed SSH target. Use after managed eligibility and required NyxID UserServices are ready, or after configuring a personal SSH node; also use when diagnosing typed managed or private-route failures before real tasks.

1 skill

Use Aevatar connected services through NyxID fixed operation invocation.

1 skill

Use before building when a user asks whether Aevatar can achieve a goal, what prerequisites it has, or why it is unavailable. Triggers include bots and third-party APIs, inbound channels, external HTTP triggers, schedules, service exposure, Agent Profiles and tool ceilings, and bounded managed or private-host codex_exec work. It distinguishes outbound connectors from inbound channels and separates not connected, host-gated, not deployed, and genuinely unsupported outcomes. It chooses managed_sandbox versus private_ssh without promising repository, model, credential, runtime, or deployment capabilities the caller does not control, then routes feasible work to the owning Aevatar skill.

1 skill

Verify the read-file path end to end — the user sends a PDF/DOCX/txt/json/md/csv plus the trigger, a workflow document_extract step pulls its text, and the run output proves the file was read. Run it before any file-dependent workflow (invoice, resume screening, reimbursement intake). As of 2026-06-12 this probe is expected to surface a known gap; the result tells you whether read-file is wired yet.

1 skill

Lark resource provisioning for Aevatar agents: after creating any private doc/Base/sheet/folder for a user, grant the requester full access BEFORE returning the link, with an org-wide (tenant) share fallback when no personal id resolves. Always-on correctness rule.

1 skill

Entry point, panorama, and router for the Aevatar skill family. Use before building, running, publishing, scheduling, externally triggering, or operating Aevatar resources; configuring an Agent Profile; assessing managed/private codex_exec feasibility and setup; running the canonical Codex readiness proof; authoring a workflow with codex_exec; diagnosing a Codex failure; or deciding which companion skill owns a request. It teaches resource and identity boundaries, NyxID-brokered auth, client REST versus in-session tools, deployment gates, and exact handoffs without treating member, workflow, service, profile, schedule, or Codex capabilities as one lifecycle.

1 skill

Use when an authenticated Aevatar user asks whether scheduled Studio Team member workflows can run with a dedicated NyxID Agent Key, especially for production checks involving cron origin, credential use, or cleanup readiness.

1 skill

Create and manage recurring Aevatar runs and route to the correct scheduling resource. Use for cron, recurring Team member workflows, scheduled skill agents, typed service invocations, pause/resume, run-now, reauthorization, deletion, or credential triage. Team member automation uses its dedicated route and Agent Key; generic schedules accept typed service invocation only. External raw actor/envelope schedules are retired and must fail closed.

1 skill

Verify the code_execute sandbox is fully working from chat — runs a tiny deterministic snippet in each supported language (python / javascript / typescript / bash) and checks the output equals the known answer, reporting a per-language pass/fail matrix. Run it before any workflow that relies on code_execute (deterministic amount math, payload building).

1 skill

Publish an Aevatar member, team, or workflow as an invocable service and (host permitting) register it with NyxID, then verify, invoke, or wire external HTTP triggers such as Lark Base automation — all over the REST API. Use when a user wants to "publish/bind a service", "expose my workflow/team as a service", "register it with NyxID", "make it callable", "get the service slug/URL", "invoke my service", "let Lark Base call my workflow", "trigger this workflow from an external webhook", or "version/deploy/roll out a service". It covers the simple scope binding, reading back a member's published service, the full account-level service lifecycle (revision → publish → deploy → rollout), how to confirm the NyxID registration (slug + status), how to invoke an endpoint, and how to distinguish direct NyxID proxy triggering from host-gated externalExposure. Build the team/member first with the team-builder skill.

1 skill

Load authoritative NyxID/Ornn manuals and domain skills via use_skill before platform-specific work, and proactively discover skills (ornn_search_skills) when the user names a skill or a task needs specialized capability.

1 skill

Build an Aevatar agent team and its members over the REST API. Use when a user wants to "create a team", "add a member", "make a workflow member / script member / gagent member", "set the team's entry point", or "assemble agents into a team". It creates the team, creates members whose implementation is a workflow (most common), a script, or a hosted gagent, binds each member's concrete implementation (the workflow YAML is attached here), waits for the async binding to succeed, and sets the team entry member. Author the workflow YAML first with the workflow-authoring skill; publish the result as a service with the service-publisher skill.

1 skill

Use after an Aevatar workflow, codex_exec call, schedule, channel, connector, skill, Agent Profile, or control-plane request fails or behaves unexpectedly. It applies when the agent must attribute the first broken boundary across Aevatar, NyxID, Ornn, chrono-sandbox/gVisor, the managed runner, or private SSH; distinguish credential sources and deployment gaps; preserve sanitized evidence; determine defect versus usage; or draft an issue for explicit user confirmation. Never use it to guess a root cause from one error string or auto-file.

1 skill

Verify the read-image (vision) path end to end — the user sends an image plus the trigger, a workflow vision step describes it, and the run output proves the model actually saw the image (a real description, not "no image received"). Run it before any image-dependent workflow (petty-cash receipt, invoice OCR).

1 skill

Author, preview, validate, and persist an executable aevatar workflow from a natural-language request. Use it when the user wants to create, build, set up, automate, or feature-probe a multi-step task as a runnable Aevatar workflow. It covers exact NyxID operation and authored-request admission, bounded YAML, file inputs, terminal run verification, feature-equivalent evidence boundaries, and reusable publication. Not for blindly rerunning an existing failed workflow.

1 skill

Verify the workflow engine can actually start a run and return its output to chat — uses aevatar_start_workflow with an inline self-contained workflow (no pre-registration needed), waits for completion, and checks the run output echoes a unique token. Run it before relying on any workflow; it isolates "is the engine alive" from "is my workflow correct".

1 skill

Use Google Workspace connected services through NyxID fixed operation invocation.

1 skill

Use the user's Twitter / X API connected service through NyxID fixed operation invocation.

1 skill

审计审批查询时间窗口是否过期、历史窗口陷阱或窗口重基线。用户提到“审批窗口完整性审计”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

预览或明确提交 IT 资产盘点记录。用户提到“资产盘点确认”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

八字原局与流日分析。基于确定性排盘事实（干支/十神/节气/刑冲合害）生成解释文本；从不自行计算历法，计算一律调用已装载的排盘工具。

1 skill

Builds deterministic Lark budget variance payloads and, when asked, runs the full budget monitoring flow through a NyxID service instead of direct Lark credentials.

1 skill

Runs the weekly budget-monitor flow end to end — reads the four Lark Bitable budget/actual tables, computes budget-vs-actual variance with the bundled deterministic builder, builds the weekly Lark variance card, and posts it to the current Lark chat.

1 skill

蛋糕店 甜品店 订单 报价 订金 制作 取货 送货 取消 改期 巡查 报告 待处理 cake shop bakery order desk patrol report. Owner-side order management for a cake or dessert shop set up by cake-shop-onboarding. Use only on owner turns (NyxID app, channel messages marked (owner), or scheduled runs) when the owner quotes a custom order, confirms or cancels an order, records a deposit, marks an order in production, ready, picked up or delivered, reschedules, asks about orders or deliveries for a date, or when a schedule asks for an order patrol, a morning report or an evening report; then reads the order sheet and sends a structured report of new orders, orders needing the owner, upcoming deliveries and capacity. Reads and updates the shop's order Google Sheet; never deletes rows; never used on customer turns.

1 skill

Cake shop, bakery, dessert shop order desk: orders, quote, deposit, production, pickup, delivery, cancel, reschedule, patrol, morning report, evening report, needs you. Owner-side order management for a cake or dessert shop set up by cake-shop-onboarding-en. Use only on owner turns (NyxID app, channel messages marked (owner), or scheduled runs) when the owner quotes a custom order, confirms or cancels an order, records a deposit, marks an order in production, ready, picked up or delivered, reschedules, asks about orders or deliveries for a date, or when a schedule asks for an order patrol, a morning report or an evening report; then reads the Order Book and sends a structured report of new orders, orders needing the owner, upcoming deliveries and capacity. Reads and updates the shop's order Google Sheet; never deletes rows; never used on customer turns.

1 skill

蛋糕店 甜品店 烘焙 蛋糕定制 蛋糕预订 订蛋糕 生日蛋糕 订单 询价 前台 客服 接单 订单管理 巡查 开店 接入 cake shop bakery dessert custom cake order inquiry onboarding. Use on owner turns when a cake, dessert or bakery shop owner wants a NyxBot agent that answers customer questions and takes cake orders or custom-cake inquiries (蛋糕店助手、订单助手、接单助手、定制询价), even if the owner already has another specialist; ask whether it is the same shop or a new one. Bind this skill to NyxBot with set_agent_skills before running it. Collects the shop profile (website or social page, address, pickup hours), the product catalog (photo, PDF, text or website) and order rules (lead time, daily capacity, custom-quote flow, deposit, delivery zones and fees, allergen note, change and cancel policy, report times); builds a Drive folder, shop-info doc and an order sheet with a settings tab, product tab and per-day capacity tab in the owner's Google Workspace; creates a customer-facing specialist with a fixed Role that answers product and shop questions from the sheet (recommends items, logs unanswered questions for the owner) and takes orders, and an owner-only order manager bound to a private copy of cake-order-desk with scheduled order patrol reports; reminds the owner to link the Telegram bot. Never used on customer turns; never deletes or overwrites the owner's existing files.

1 skill

Cake shop, bakery, dessert shop, custom cake, birthday cake, cake order, inquiry, quote, order management, onboarding. Use on owner turns when a cake, dessert or bakery shop owner wants a NyxBot agent that answers customer questions and takes cake orders or custom-cake inquiries, even if the owner already has another specialist; ask whether it is the same shop or a new one. Bind this skill to NyxBot with set_agent_skills before running it. Collects the shop profile, product catalog (photo, PDF, text or website) and order rules (lead time, daily limit, custom quotes, deposit, delivery, allergen note, report times); builds a Drive folder, shop-info doc and order sheet in the owner's Google Workspace; creates a customer-facing specialist with a fixed Role that answers from the sheet and takes orders, and an owner-only order manager bound to a private copy of cake-order-desk-en with scheduled patrol reports. Never used on customer turns; never deletes or overwrites owner files.

1 skill

检查候选人附件、材料完整性或隐私约束。用户提到“候选人材料完整性预览”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Method for producing short vertical videos from ChatGPT image generation through a fixed browser tab, local TTS narration, timed subtitle burn-in, cover exports, and a manifest. Use when an operator needs a reproducible image-to-short workflow with pinned session consistency, per-beat visual prompts, 1080x1920 safe-area rules, local ffmpeg/PIL assembly, and private access kept outside the skill.

1 skill

Runs the CHO weekly goal audit / weekend review flow end to end — parses the employee's Lark goal message, audits or reviews it with your own model, writes the Base record, and posts the employee reply plus the CHO diagnosis to Lark.

1 skill

Pulls a GitHub account's issues and pull requests for the week, analyzes what shipped, what is in progress, and what is blocked with real workload metrics, then renders a Lark interactive card with hyperlinked rows and a metrics table, or a markdown report. The agent runs the whole flow itself using its own NyxID-brokered tools.

1 skill

Deploy a user's application to the ChronoAI cluster with chrono-cd through NyxID, either with the CLI (`nyxid proxy request chrono-cd ...`) or, for agents without a shell such as the NyxID Assistant and NyxBot on Telegram or Lark, with their NyxID proxy request tool (service `chrono-cd`, method, path, body). Covers the whole flow an agent runs for the user - check the account and quota, pick a personal or organization scope, write the app spec (one or more ghcr.io images with ports, routes, env, config files, volumes and an optional MongoDB add-on), create or update the app, set its secrets, watch status and logs, query stored metrics and logs for any window up to 31 days (presets or PromQL and LogsQL), restart, roll back by re-deploying a tag, delete, and ask for more quota. Use whenever the user wants to deploy, update, inspect or remove an app on the ChronoAI platform (hostnames under apps.nyxid.ai, older apps under apps.chrono-ai.fun), or asks what chrono-cd needs from them. Every request body and response shape is given, so the agent never guesses.

1 skill

Chrono AI 非技术团队 onboarding — 安装 NyxID CLI, 配置 AI 工具 MCP, 克隆战略仓库, 运行每日更新

1 skill

Use the user's Chrono Sandbox connected service through NyxID fixed operation invocation.

1 skill

Run a real GitHub-based team health / performance audit for the Chrono AI engineering team. Triggers on "team health", "团队健康", "全员审计", "全员绩效", "绩效审计", "check the team". Runs a fixed self-contained script via code_execute and returns a red/yellow/green report; posts it to Lark.

1 skill

Operate ChronoAI Managed Agent (CMA) through its public API or NyxID proxy. Use for creating and using hosted agents, managing user environments and profiles, sharing resources, publishing Triggers, and configuring Telegram Bots and Event Worker Profiles.

1 skill

Runs the CN reimbursement intake end to end and posts a structured summary; full approval state machine requires a bundled workflow.

1 skill

Use when answering mathematical, conceptual, philosophical, or metaphysical questions through repository-first scientific reasoning, a clause-complete formal bridge, retained exact Lean specializations, reusable library growth, and an ordinary conversational answer; the formal work stays internal and is shown only when the user asks for it.

1 skill

Use when asked to formalize and close an open digestion atom in this repository.

1 skill

Runs the community-radar flow end to end and posts a digest to the chat.

1 skill

验证 managed sandbox、固定输出和多分支 receipt。用户提到“复杂 codex_exec 验证”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

检查外包人员附件、历史去重并预览或创建审批。用户提到“外包人员访问资料审批”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

每天汇总全球科技新闻，中文输出，覆盖 AI、芯片、互联网、创业、开源。

1 skill

每天汇总全球科技新闻，中文输出，覆盖 AI、芯片、互联网、创业、开源。

1 skill

Runs the deadline-monitor flow end to end — reads GitHub repo or org milestones/issues, ranks deadline risk, builds the exact Lark digest with the bundled deterministic builder, and posts it to the current Lark chat.

1 skill

Given any topic, returns three surprising true facts plus one catchy title for them. Runs a tiny two-step aevatar workflow (facts then title) and is watchable in the observatory. A minimal demo of a workflow-carrying ornn skill.

1 skill

Deployment gate with human approval — runs preflight checks, sends an interactive Lark approval card, then simulates deployment on approval. Usable from Lark bot via natural language or /deploy command.

1 skill

验证 deterministic parallel 三路 worker、receipt 与 dispatch index 合并。用户提到“确定性并行证据审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

验证 deterministic race 的首成功 winner 与后续完成忽略语义。用户提到“确定性竞速政策审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

只读检查邮箱访问审批列表和实例详情。用户提到“邮箱访问审批审计”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Runs the SG employee reimbursement intake end to end and posts a structured summary; full approval state machine requires a bundled workflow.

1 skill

Universal try-catch fallback for the aevatar model. Use whenever, after a genuine attempt, you cannot complete the user's request with available server-side capabilities — no matching skill/workflow/connector/tool, a terminal failure, or a task that inherently needs the caller's local environment (files, shell, local context). Instead of failing opaquely or fabricating, return the original request verbatim to the calling agent so it can finish with its own local tools. Generic by design — addresses "the calling agent" with no hardcoded client or skill names.

1 skill

Lark FIN-02 预算差异 workflow 路由。用户说‘帮我查看 2026 年第 32 周的预算差异’、‘预算差异’、‘预算对比’、‘预算执行’、‘超支情况’、‘第 N 周预算’、‘budget variance’或 fin-budget-variance-monitor 时，优先加载并执行这个精确 skill/workflow；不要只生成泛化周报或分析发票。

1 skill

Lark FIN-01 发票预检 workflow 路由。用户说‘帮我预检刚上传的发票’、‘发票预检’、‘检查发票’、‘检查刚上传的发票’、‘发票审批’、‘付款审批’、‘发起付款’、‘invoice precheck’或 fin-invoice-precheck-approval 时，优先加载这个精确 skill；附件和申请日期齐备后执行 workflow，缺项时先索取；不要走通用 OCR。

1 skill

Teach an aevatar agent to run Firecrawl web-research/agent jobs through NyxID (submit, poll, then read the result).

1 skill

Operator manual for the fkst-hosted control plane — how to start, drive, monitor, and stop autonomous fkst-substrate coding sessions through GitHub issues (the source of truth; the dashboard/REST API reads and writes those same issues). Use whenever you need to: (a) launch a session by opening an `fkst-substrate-trigger` issue with the exact `### Session Name` / `### Packages` / `### Manifest` / `### Work Label` / optional `### Environment` / `### Auto-merge` / `### FKST Contributors` (alias: `### Log Access Allowlist`) / `### Session Collaborators` / `### Output Language` / `### Engine Config` body; (b) queue tasks by opening issues that carry the session's work labels; (c) interpret the session's status comments and labels (registered / picked-up / degraded / retired / invalid / config-rejected / unauthorized) and the dashboard's typed recovery states; (d) download a session's redacted logs (whole-session or per-run) from the identity-gated `/api/v1/logs/{session_id}` endpoint; or (e) stop or idle a session by closing issues. Covers the package-reference grammar `owner/repo@ref:path`, manifest expansion, work-label auto-discovery, config immutability, the idle-vs-permanent lifecycle, the one-work-label-per-trigger rule, and control-plane availability (`/ready`, restart/failover 503 windows).

1 skill

Runs the GitHub candidate sourcing flow end to end and posts a digest to the chat.

1 skill

Given an owner repo rank recent GitHub activity into an actionable digest.

1 skill

On-demand GitHub intelligence for any repo the team's credential can see — weekly activity digest, issue and PR triage table, milestone progress, release-notes draft, and "what changed since X" answers, fetched live through NyxID-brokered GitHub access and delivered in chat. Complements deadline-monitor (deadline risk) and github-candidate-sourcing (hiring).

1 skill

Operate a user's GitHub account through NyxID's credential-brokering proxy (service slug api-github) — read and write repositories, files, issues, pull requests, commits, branches, Actions, gists and anything else the GitHub REST API exposes, all on the user's behalf and without ever handling a raw token. NyxID injects the user's GitHub credential server-side. Use when an agent needs to read from or act on GitHub for a user who has connected their GitHub account in NyxID.

1 skill

Runs the Lark HR approval bot flow end to end yourself — read the Lark leave request, look up the employee contact record, analyze the request, then SUBMIT the Lark leave approval and send the reply.

1 skill

考勤填写提醒。当用户说：考勤提醒、催填考勤、考勤填写、月底提醒、提醒大家填考勤、attendance reminder 时使用。生成月底考勤核对清单卡片预览；确认后可正式发送提醒。

1 skill

月度考勤审批。当用户说：月度考勤、考勤审批、考勤汇总、提交考勤、预览某月考勤、monthly attendance 时使用。读取考勤表并汇总人数/应出勤/离职/事假/病假，生成审批预览；确认后可正式创建审批并通知。

1 skill

入职邮箱开通审批。当用户说入职邮箱、新员工邮箱、邮箱申请、开通邮箱、邮箱审批、onboarding email，或 Employee Master 新员工入职状态触发邮箱审批时使用。支持自然语言预览/提交和 Base record 自动化；默认只预览，用户无需知道 workflow、skill、工具或 JSON。

1 skill

Runs the NyxID ICP Hunter scoring flow end to end — searches ICP evidence, enriches and scores candidates with your own model, writes the new candidates to the ICP Hunter Lark Base, and posts the run report card.

1 skill

Runs the interview-minutes analysis flow end to end — scans the ATS Bitable, reads the Lark Minutes transcript, analyzes the interview with your own model, writes the AI notes back to the ATS record, and posts the HR card.

1 skill

验证当前发票附件、审批历史去重和 contact 路由的 no-submit 集成契约。用户提到“发票审批路由预览”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Runs the invoice OCR approval flow end to end yourself — collect invoice files and review fields, OCR them, upload attachments, resolve Lark contacts and related approvals, then SUBMIT the Lark approval instance.

1 skill

从发票图片或 PDF 提取字段、归一化并检查历史重复。用户提到“发票 OCR 与策略审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Translate Japanese text into Chinese with support for tone, context, and output style preferences.

1 skill

Check one Lark approval instance or list approval tasks with the typed lark_approvals_get / lark_approvals_list tools and report the normalized status (approved / rejected / running, is_terminal, pending task and approver). Doubles as the end-to-end test for approval status tracking and as a daily "查审批" helper.

1 skill

Create and operate Lark Base (多维表格 / Bitable) tables through the bot's NyxID-brokered bitable/v1 + drive/v1 APIs — create a new Base and grant the requester access, list a Base's tables and a table's fields, read and filter records, create or update single rows, and batch-write many rows. Handles the app_token + table_id extraction from a Base share URL, writes by field NAME with the right typed value shapes (date = ms timestamp, person = open_id, single/multi-select = existing option names), grants the requester full_access on any Base it creates, and doubles as the bitable-scope probe — on a scope 403 it reports the exact missing permission. Lark Base here is the Bitable database product, distinct from Lark Sheets — use the Sheets skill for plain grid spreadsheets.

1 skill

验证通过 Lark Bot 上传的文件、附件引用或 document_extract 主链。用户提到“Lark Bot 文件上传验证”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Calendar assistant over the bot's NyxID-brokered Lark calendar/v4 APIs — list calendars, check free/busy across people, find a common slot, read your agenda for a window, and create or update events with attendees. Knows the event-time shape (a timestamp + timezone object, not RFC3339) and that attendees are added in a separate call, and doubles as the calendar-scope probe — on a scope 403 it reports the exact missing permission instead of failing.

1 skill

Recall and summarize Lark conversations — pull a chat's history over a time window through the real im/v1 history API, reconstruct discussions, and answer "who said what" with quoted evidence. Use for "总结这个群今天聊了什么 / 上周谁提过X / 找一下关于Y的讨论". Requires the bot tenant scope im:message.group_msg; reports the exact missing scope verbatim when absent.

1 skill

通过 contact batch_get_id 解析入职邮箱身份。用户提到“Lark 联系人批量解析”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Create and edit Lark cloud documents (Docx) through the bot's NyxID-brokered docx/v1 + drive/v1 APIs — create a document and grant the requester access, append headings and text paragraphs, read a document's plain-text content, and share it with other people or make it tenant-readable. Handles the Docx block model (block_type + text_run elements) and the document-root block_id, grants the requester full_access on any doc it creates, and doubles as the docx-scope probe — on a scope 403 it reports the exact missing permission.

1 skill

Send, reply to, react to, read, and find Lark messages and chats through the bot's NyxID-brokered im/v1 APIs — proactively post to a chat or DM, thread-reply, add or remove emoji reactions, read a single message or pull a chat's history over a time window, search or list the chats the bot is in, and download an image/file from a message. Handles the "content must be a JSON string" footgun and receive_id_type selection, and doubles as the im-scope probe — on a scope 403 it reports the exact missing permission instead of failing silently.

1 skill

Runs the Lark Meeting v2 flow end to end — extracts tasks from meeting notes (or reads the Base task records), analyzes them with your own model, writes the task records to Lark Bitable, and posts the task list / reminder to the Lark group.

1 skill

Builds the connector-ready Lark approval instance payload for the onboarding email approval flow. Use after Aevatar has received a Lark/Base onboarding event and before calling the NyxID Lark approval connector.

1 skill

验证 POST 搜索的 typed tool approval pending、resume 或 issue 3184 回归。用户提到“Lark POST 搜索批准恢复探针”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Read and write Lark Sheets (电子表格) through the bot's NyxID-brokered sheets APIs — find a spreadsheet and its sheet ids, read a cell range, append rows to the bottom, and overwrite a range. Handles the range format (sheetId!A1:D10) and the valueRange wrapper, extracts the spreadsheet_token from a share URL, and doubles as the sheets-scope probe — on a scope 403 it reports the exact missing permission. Lark Sheets here is the spreadsheet product, distinct from Lark Base / Bitable — use the Base skill for Bitable tables.

1 skill

Index, router, and dependency map for the aevatar Lark/Feishu skill family on ornn — load this FIRST when someone wants the bot to do anything in Lark (send a message, recall a chat, write a doc / sheet / Base record, manage a calendar event, run an approval). It names the six core operation primitives (im / docx / sheets / bitable / calendar / approval), states the one shared premise (every call goes through nyxid_proxy slug api-lark-bot, scope-probe-first), routes intent to exactly one primitive, lists which business workflows consume them, and flags the current cleanup items. It does not call Lark itself — it routes to the right ops skill.

1 skill

Builds Lark team-health command parsing, progress-message payloads, and report-message payloads from collected GitHub and AI analysis results.

1 skill

李诞做自媒体/内容工作的思维框架与表达方式。基于《李诞工作手册（全新修订版）》 第一部分（自媒体内容工作，8 个「心」章节 + 问答）的精读提炼，含 6 个核心心智模型、 10 条决策启发式和完整表达 DNA。 用途：作为思维顾问，用李诞的视角审内容、做内容决策、面对数据焦虑与网络争议时给反馈。 当用户提到「用李诞的视角」「李诞会怎么看」「李诞模式」「李诞自媒体心法」时使用。 即使用户只是说「帮我用李诞的角度想想这条内容」「如果是李诞会怎么做这个号」「切换到李诞」也应触发。

1 skill

六爻解卦。基于确定性排卦事实（本变卦/世应/六亲/六神/动爻）解读所占之事；从不自行排卦，排卦一律来自排卦工具。

1 skill

Use OpenAI API connected services through NyxID fixed operation invocation.

1 skill

Write polished long-form content with structure credibility and an optional supplied voice.

1 skill

为商户自动处理订餐咨询与预订请求，遵守每个订餐时段至少间隔1小时、单次最多4人及总座位数40人的规则，并准确回复可订状态。

1 skill

执行月末访问认证、提醒预览或明确发送提醒。用户提到“月度访问认证”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Builds Lark monthly attendance approval/reminder payloads and, when asked, runs the full attendance flow through a NyxID service instead of direct Lark credentials.

1 skill

Runs the monthly China-region attendance approval flow end to end yourself — fetch the month's Lark attendance records, compute出勤/离职/事假/病假 stats, build the exact approval body, SUBMIT the Lark attendance approval instance, then DM the confirmation card.

1 skill

Placeholder built-in skill for NyxBot and its specialists. How NyxBot works inside NyxID - who does what, how to delegate to specialists, grant services, set up chat channels and schedules, and hand the owner setup pages instead of asking for secrets. Read it when unsure which NyxID tool fits a request or how NyxBot and specialists cooperate. Guidance only; it grants no permissions.

1 skill

Placeholder built-in skill for NyxBot and specialists - how to use ChronoAI Managed Agent (CMA) through the owner's connected cma service in NyxID, for hosted agents, sandboxes and running a command line when one is truly needed. Read it when work needs a hosted agent, a sandbox or a CLI. Guidance only; it grants no permissions.

1 skill

Placeholder built-in skill for NyxBot and specialists - how to find, attach, read and draft Ornn skills with NyxID's native skill tools (search, preview, pin, request, read, draft) instead of the Ornn CLI or raw Ornn APIs. Read it when the owner asks to find, add, improve or create a skill, or when you need a skill you do not have. Guidance only; it grants no permissions.

1 skill

为 ChronoAI / NyxBot 的中小企业客户（餐馆、招牌店等）做 45–65 秒、抓人的中文宣传视频：读客户人物志和方案页，产出逐帧可控的 HTML 动画影片、按配音时段压低的原创配乐、配音稿与字幕（SRT），并渲染 MP4；配音由用户在第三方平台生成。当用户要给某个客户做 NyxBot 宣传片、按人物志和方案做视频、出配音稿或按中文配音调整画面节奏时使用。

1 skill

Brokers credentials for downstream services (OpenAI, Anthropic, GitHub, Lark, custom APIs, SSH, MCP) so the agent never sees raw API keys or OAuth tokens. Use whenever the user asks to call, proxy, or authenticate against a third-party API/service, mentions NyxID, asks to "connect", "add a service", "set up an API key", manage credentials/nodes/MCP, send messages through bot platforms, or wire up SSH access. Operate exclusively through the `nyxid` CLI.

1 skill

当用户要在 NyxID 配置消息机器人并接入 Aevatar，例如“给我弄个 Telegram bot，连上 Aevatar”“把飞书接到 Aevatar”，或创建、复用、检查 Aevatar Channel 时使用。通过 NyxID 的 Aevatar Service 完成 Channel 接入、服务授权、可选的运行技能绑定及核验；使用 CLI/API，无需用户了解服务入口、Channel 等技术术语。

1 skill

Owner and scheduled operations for a NyxBot business front-desk specialist built by nyxid-business-starter. Use in owner chats and schedule runs to show the queue, call the next customer with an SMS, mark served or no-show, send batched queue confirmations, list pending reservations and confirm or decline them. Customer (guest) turns never see this skill; their rules live in the agent description.

1 skill

CMA worker procedure for nyxid-business-starter. Use when a task block starts with TASK notion-hub or TASK faq-research. Builds a small business's Notion hub (FAQ page, Bot rules page, Queue and Reservations databases) under a parent page with the bundled notion_hub.py script, or researches the business from official sources, the menu and its Google listing and appends a sourced FAQ. Ends with a SETUP_RESULT JSON line. Never contacts customers.

1 skill

Owner onboarding for small businesses on NyxBot. Use when the owner asks to set up a queue manager, a business FAQ, or reservations (alone or combined), or names this skill. Interviews the owner, connects Notion, Telnyx and CMA, has a CMA worker build the Notion hub and research the FAQ, creates one customer-facing front-desk specialist, sets guest access and approvals, links a Telegram bot, and runs a test. Guidance only; it grants no permissions.

1 skill

验证 managed workflow 的 NyxID provider receipt、首步输出或 issue 3161 回归。用户提到“NyxID 只读回执探针”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Invoke an operation on a connected and authorized NyxID service through Aevatar's dynamically typed connected-service tools or the credential-injecting nyxid_proxy fallback. Use when a user asks to read, search, create, update, send, run, download, or otherwise call a NyxID service while keeping upstream credentials inside NyxID and respecting provider scopes, approvals, and service routing. 中文触发包括“调用我的 NyxID 服务”“使用服务”“让服务执行”。

1 skill

Connect, add, reconnect, or repair a NyxID service through NyxID's secure credential and provider OAuth surfaces, then grant the current Aevatar developer app incremental access to that connected service. Use when a user wants a new NyxID service, sees a missing-connection or missing-credential error, needs provider OAuth, or must authorize an already connected service for NyxID Chat without exposing secrets to the model. 中文触发包括“连接新的 NyxID 服务”“新增服务”“授权服务”。

1 skill

Inventory and inspect NyxID services available to the current authenticated user across connected instances, the service catalog, proxy availability, and LLM routes. Use when a user asks what services they have, what can be added, whether a service is connected, active, healthy, or callable, which personal or organization source owns it, or needs exact service details before connecting, invoking, or maintaining it. 中文触发包括“我有哪些 NyxID 服务”“查看服务列表”“服务状态”。

1 skill

Diagnose NyxID service and credential problems from chat — "工具 403 / Provider not connected / 服务没绑 / 找不到搜索服务" — using the typed nyxid_* tools to inspect what is actually connected, who owns the credential, and which grant the current run is using, then prescribe the exact fix (connect, org-share, or rebind).

1 skill

Maintain an existing NyxID service by inspecting and updating labels, endpoints, active state, direct or node routing, health, external-key metadata, and deletion, while sending all credential rotation or repair through NyxID's secure UI. Use when a user asks to edit, reroute, enable, disable, repair, rotate credentials for, diagnose, or remove a connected NyxID service. 中文触发包括“修改 NyxID 服务路由”“更新服务”“轮换凭据”“删除服务”。

1 skill

Find or author an agent skill for a NyxID proxy service that has no OpenAPI spec or typed operations. Use when a NyxID service only exposes the generic proxy tool, `nyxid catalog endpoints` returns nothing for the slug, or you would otherwise have to guess endpoint paths. Searches Ornn for an existing skill bound to the service; if none exists, creates one — researching the official OpenAPI spec on the web for public services, or collecting the contract from the user for private/custom services (never fabricate endpoints) — then uploads it to Ornn, binds it to the service, and records it locally.

1 skill

Lark/Feishu integration via NyxID proxy. Replaces lark-cli — call Lark OpenAPI directly through nyxid proxy request with automatic credential injection.

1 skill

Turn the office wall lights on or off via two pre-registered aevatar scope workflows (office_lights_on / office_lights_off). Each asserts the on/off state of the 10 office wall-switch lights (Corridor, Front/Mid Reception, Coworking ceiling; Dubai Room excluded) through the NyxID-brokered home-assistant service. Use whenever the user wants to switch the office lights on or off.

1 skill

Runs the new-hire onboarding email-account approval flow end to end yourself — resolve the new hire's info, build the exact Lark approval body with the bundled deterministic builder, then SUBMIT the onboarding email approval instance.

1 skill

The manual an AI agent loads to operate Ornn — the model-agnostic skill-lifecycle API (an npm-style registry + CLI for agent skills) — via the NyxID CLI (`nyxid proxy request ornn-api …`). Load and follow this skill WHENEVER the user asks to do anything with Ornn skills or skillsets. Skills: search Ornn or find a skill, pull or install a skill (or a specific version), run a skill, build and upload a skill, publish a new version, make a skill public / private / shared, run or read a security audit, deprecate or delete a version, diff two versions, check usage analytics, bind a skill to a NyxID service, link a skill to GitHub or sync from source, manage npm-style dist-tags, or transfer skill ownership. Skillsets — curated multi-skill bundles with a required master prompt: bundle skills into a set, create or publish a skillset, resolve its closure in one call, export a skillset as a Claude Code marketplace plugin, transfer skillset ownership, or diagnose why a shared skillset isn't visible (visibility derives from its member skills). Also load it to check your quota or pick an LLM model before an SSE call, and on phrases like 'share my skill', 'bundle these skills', or 'export as a Claude Code plugin'. Once loaded, the agent runs the whole search → pull → execute → build → upload → share lifecycle with no further setup — this is the authoritative Ornn↔agent contract, paired with references/api-reference.md (full per-endpoint catalogue + error legend).

1 skill

Runs the petty-cash approval flow end to end yourself — collect Lark DM/sheet/image context, extract receipt details, build the exact approval body, then SUBMIT the Lark approval instance.

1 skill

从 Base 申请创建并回读共享邮箱审批。用户提到“项目共享邮箱审批”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Verify-first promotion intelligence for ANY repo or org. Pulls live GitHub state, runs sshx multi-perspective consensus over it, and returns an evidence-backed board of what is genuinely promotable, how items connect, and what is unverifiable. Use when an agent or operator asks "what's worth promoting / what connects / what's real" for a target repo or org.

1 skill

Take a rough prompt and its goal and return an optimized prompt with clarified intent, structure, constraints, and output spec.

1 skill

Portable checklist for gating public-facing copy before release. Use when captions, posts, manifests, topics, titles, or launch copy must be checked for generic AI wording, leaked internal labels, forbidden experiment or tool names, platform topic allowlists, CTA spam, and unsupported overclaims.

1 skill

预览或明确发送季度访问审查私信。用户提到“季度访问审查提醒”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

验证声明 read_only 风险的语义只读 POST 免运行时审批执行。用户提到“只读声明 POST 探针”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

检查上线准备、备份、监控或回滚控制。用户提到“发布准备度审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Severity-weighted BLOCK, WARN, OK reviewer method for technical and research posts. Use when reviewing X threads, announcements, captions, or launch copy for hook strength, thread arc, generic AI vocabulary, source fidelity, claim support, numeric-claim verification, and thread format before recommending publish.

1 skill

Draft, revise, or review focused research manuscripts with complete arguments, verified literature, and direct prose. Remove defensive wording and repeated summaries while preserving exact claims, attribution, authors' voice, and reproducibility. Especially useful for mathematical, theoretical-CS, and computer-assisted papers, short notes, and coauthor revisions; adaptable to empirical papers. Use for manuscript work, not outreach campaigns or standalone theorem proving.

1 skill

餐厅 订位 入座 离店 翻台 换桌 散客 排位 改期 取消 待确认 特殊要求 场合 桌况 余量 包间日历 restaurant table check-in check-out walk-in reservation desk settings. Owner-side daily operations for a restaurant reservation specialist set up by restaurant-reservation-onboarding. Use only on owner turns (NyxID app, or channel messages marked (owner)) when the owner or staff says a table was seated or left (for example B3 入座, B3 离店), a walk-in party sat down, a booking moved table, a guest did not show, a booking was rescheduled or cancelled, a pending booking is approved or declined, asks bookings, live table status or remaining tables for a date, or changes a house rule in the 餐厅设置 tab. Reads and updates the reservation Google Sheet and keeps the private-room calendar in step; never deletes rows; never used on customer turns.

1 skill

Restaurant reservation desk: seated, left, table turnover, move table, walk-in, seating, reschedule, cancel, pending, special requests, occasion, table status, free tables, room calendar, check-in, check-out, settings. Owner-side daily operations for a restaurant reservation specialist set up by restaurant-reservation-onboarding-en. Use only on owner turns (NyxID app, or channel messages marked (owner)) when the owner or staff says a table was seated or left (for example B3 seated, B3 left), a walk-in party sat down, a booking moved table, a guest did not show, a booking was rescheduled or cancelled, a pending booking is approved or declined, asks for bookings, live table status or free tables for a date, or changes a house rule in the Settings tab. Reads and updates the reservation Google Sheet and keeps the room calendar in step; never deletes rows; never used on customer turns.

1 skill

餐厅 订位 订座 预定 预订 订餐 订台 订桌 包间 排位 菜单 前台 接待 客服 咨询 开店 接入 restaurant reservation booking table front-desk onboarding. Use on owner turns when a restaurant owner says they run a restaurant (餐厅、饭店、餐馆、饭馆) and want a NyxBot agent that handles customer enquiries and table bookings (订位助手、预订助手、预定助手、前台助手、接待客人询问和预订就餐), even if the owner already has another reservation specialist — ask whether it is the same restaurant or a new one. Bind this skill to NyxBot with set_agent_skills before running it. Collects the restaurant profile, menu (photo, PDF or text), table and private-room inventory and booking rules; builds a Drive folder, menu sheet, restaurant-info doc, reservation sheet with live table board, a 餐厅设置 settings tab holding the house rules and a 订位速查 per-day free-table tab, and a private-room calendar in the owner's Google Workspace; then creates the reservation specialist with the fixed Role template (only store name and sheet ID filled in), grants Google Workspace, copies restaurant-reservation-desk into a private per-store skill on Ornn (house rules go there; public template updates are merged only with the owner's consent) and binds it so the owner can say which table checked in or left, and links the customer channel. Never used on customer turns; never deletes or overwrites the owner's existing files.

1 skill

Restaurant reservation, booking, table and front desk onboarding. Use on owner turns when a restaurant owner says they run a restaurant and want a NyxBot agent that answers guest questions and takes table bookings (reservation assistant, booking assistant, front desk assistant), even if the owner already has a reservation specialist; ask whether it is the same restaurant or a new one. Bind this skill to NyxBot with set_agent_skills first. Collects the restaurant profile, menu (photo, PDF or text), table and private-room inventory and booking rules; builds a Drive folder, menu sheet, restaurant info doc, reservation sheet with live table board, a Settings tab for house rules and a Lookup tab of free tables per day, and a private-room calendar in the owner's Google Workspace; creates the specialist from the fixed Role template (only store name and sheet ID filled in), grants Google Workspace, copies restaurant-reservation-desk-en into a private per-store Ornn skill and binds it, and links the guest channel. Never used on guest turns; never deletes or overwrites owner files.

1 skill

Runs the HR resume screening flow end to end — collects the candidate's form/chat fields and resume PDF, screens the resume with your own model, uploads the passing resume to Lark Drive, writes the Bitable record, and posts a summary to the chat.

1 skill

验证未声明风险 POST 的运行时 tool approval 挂起、恢复与真实写入回执。用户提到“运行时工具审批写入探针”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

汇总多路 Base 数据并预览或发送许可证优化卡片。用户提到“SaaS 许可证优化摘要”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

复核软件席位、许可证利用率或订阅成本。用户提到“SaaS 许可证利用率审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

验证通用 JavaScript 执行和结构化结算 receipt。用户提到“安全 code_execute 验证”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Audit, debug, trigger, and repair scheduled (cron) agents from chat — list what exists, verify cron and timezone really mean what the user intended, manually run one to test, disable or delete-and-recreate broken ones. Encodes the known failure modes (timezone double-conversion, zombie agents from older runtimes, cron-mode credential 403, DM-vs-group visibility) so users can self-serve.

1 skill

Collect items from a connected source score and summarize them against a brief and emit a ranked digest.

1 skill

验证一次运行内连续两次写入的 tool approval 挂起与恢复组合。用户提到“顺序工具审批写入探针”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Read-only X Twitter search producing a ranked summarized digest of recent posts.

1 skill

Method for drafting and reviewing source-anchored research or technical announcements, especially X threads or short posts. Use when public copy must distinguish claimed from not claimed, attach every technical claim to an artifact anchor, avoid overclaiming, remove generic AI phrasing, and require dry-run plus human approval before live publishing.

1 skill

验证 guard、conditional 与 while 三个确定性工作流原语的真实运行行为。用户提到“供应商控制项自证审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

验证 map_reduce 与 cache 两个确定性工作流原语的真实运行行为。用户提到“供应商风险分档汇总”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Runs the team-health report flow end to end and posts a digest to the chat.

1 skill

Runs the tech-digest aggregator flow end to end and posts a digest to the chat.

1 skill

Runs the tweet-draft approval flow end to end yourself — collect the Lark tweet draft or approval-card action, audit it with your own model, build the exact Lark post/card, and post it to the source chat.

1 skill

验证 workflow_call 的 inline 子定义绑定、子运行与结果回传。用户提到“供应商政策 inline 委派审查”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Use when a user asks whether managed codex_exec is available for their current account, requests a codex_exec readiness check, or wants to run the canonical managed Codex smoke test.

1 skill

Derive a structured reusable writing-voice profile from supplied sample texts.

1 skill

Structured web research from chat — multi-source search, fetch and cross-check, then a compact cited brief (背景 / 关键发现 / 分歧与不确定性 / 来源列表). Uses discovery-first search service resolution plus web_fetch; long reports land as a Lark doc. Use for "帮我调研X / 对比A和B / 这个说法靠谱吗 / 最近关于Y有什么新进展".

1 skill

生成预算周报、月度投影或配置 recurring schedule。用户提到“周度预算差异摘要”、对应英文名称或要求运行该验收 workflow 时使用。

1 skill

Read selected Zoho Mail messages or an email supplied in chat, show the original in a private Lark review conversation, draft employee announcements and useful reminders or a reply to the sender, and deliver only after the owner explicitly approves the exact content, recipients and time.

1 skill