aevatar-codex-exec-workflow-sample

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

CLI edition: NyxID skills for agents that drive the nyxid CLI or the authenticated Web API, plus the synchronized Aevatar platform skill family. For the hosted MCP connection, install the `nyxid` plugin.

17 skills

Iterative multi-agent code review. Four cross-agent skills: review-anvil (engine — requested rounds of parallel codex-exec/claude-exec reviewers, adaptive continuation up to max_rounds, synthesized findings, default-on batched reproduction, and optional fix commits), review-anvil-readonly (engine with commit_mode=none), review-anvil-pr (read-only PR review with hybrid posting — inline review comments for file-anchored findings + top-level summary for the rest), review-anvil-improve-pr (productive PR loop — posts a 'starting' PR comment cc'ing the author, applies fix commits across requested/adaptive rounds, pushes back to the PR, then edits the starting comment in-place with the synthesized report or failure summary). Reviewers get distinct lenses, validate PR-author replies against current code, and suppress explained findings; the PR helper resolves only verified obsolete review-anvil threads. Uncertain material findings are reproduced against code before being applied or posted; a per-round build/test gate keeps fix commits green; Bash-dispatched reviewers run under a run-reviewer.sh watchdog (hard timeout, empty-output detection). PR posting and verification delegated to `set -euo pipefail` shell helpers.

4 skills

Schedule and loop Codex prompts locally — cron, fixed intervals, and one-shot runs executed through `codex exec`, guarded by a single-runner lock.

2 skills

Opinionated orchestration of work through two delegation surfaces: dispatched workers (Codex CLI (GPT-6) and Claude subagents) via a task-strategy workflow with model and reasoning-effort routing, fenced write scopes, and independent two-worker verification; and sibling Claude Code sessions via a distribution workflow with session enumeration, mandatory dispatch-message blocks, and explicit stand-down closure. Ships 11 duty agent definitions that pin no model or effort; the routing table sets model and reasoning effort per checkpoint type at spawn time. Both skills are extendable at five workflow positions and via recognized named configuration values; the plugin ships hooks that deliver a project's per-skill extension files (.claude/extensions/work-orchestrator/) wrapped in a structural envelope.

2 skills · 11 agents · hooks