discernment-nudge
claudeAppends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
19 skills
General-purpose reasoning and controlled execution with silent per-request depth triage, progressive references and a strong Deep Research path
Ships a Codex manifest but no marketplace file, so Codex can't add it by name yet. Add it to a local marketplace (.agents/plugins/marketplace.json).
Plugin reasoning-workflow in zy839971925-zyy/Agent--deep-research-Workflow-Skills. Commands read from the repo's manifest — 24 days ago.
reasoning-workflowDefault silent entry for questions, research, artifacts, code, coordination and persistent projects. When available to the host, infer the relevant evidence path from each direct request, including real-world, pre-build engineering, or linked hybrid research; choose proportionate Light-to-Ultra work
audit-verificationUse when a material result needs contract verification, independent or orthogonal review, evaluator-validity checks, effectiveness review, or defensible closure.
decision-analysisUse when the deliverable is a choice, recommendation, prioritization, trade-off, resource allocation, or robustness-sensitive decision.
deep-researchUse when a scenario calls for real-world evidence, pre-build engineering/architecture research, or a linked hybrid; infer the route without requiring the user to label it. Keep the host-selected default model; infer proportionate workflow depth, honoring explicit depth requests such as Ultra.
execution-controlUse when work creates durable artifacts or external side effects, delegates execution, needs authorization, or must preserve state/checkpoint/recovery semantics.
reasoning-coreUse when a task needs problem framing, representation choice, decomposition, relationships, causal chains, hypotheses, or careful interpretation.
workflow-learningMaintenance-plane only. Use after completed runs or evaluations to derive CAPA/experience candidates, challenge transferability, and gate learning promotion or rollback.
Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context
19 skills
Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP
5 skills · 1 command · 4 agents
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Turn a tangled working tree into a clean, reviewable commit series. Three deterministic stdlib scripts over git: a series planner that groups changes into commits in build-safe order (manifest with lockfile, pure moves, formatting, each module's change with its tests, docs, CI), holds back .env and key files, and flags mixed formatting and moves whose callers would break; a secret gate that scans staged or pushed lines for provider tokens, high-entropy secrets, sensitive files and conflict markers and blocks before the commit exists, with redacted output and reasoned waivers; and a message linter that blocks vague subjects, missing why on large changes and pending fixup commits, matching the repo's own convention. Ships pre-commit, commit-msg and pre-push hooks, cs-commit-craft agent, /cs-commit-craft and /cs-commit-check commands and 3 cited references.
1 skill · 2 commands · 1 agent
Skills for building apps with the AG-UI .NET SDK: streaming chat (stateless vs hosted agents), server tools, client tools, human-in-the-loop (approvals & interrupts), shared state, multimodal messages, reasoning traces, protobuf transport, and troubleshooting.
9 skills
把本地文件夹建成 Agent 可稳定查找、收录和维护的知识库,并支持导航、版本判断、健康检查及 SOT 分层治理。用户要求搭建、查询、更新、整理或瘦身知识库时使用。
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.