메뉴
Publish a skill after validation and approvals; updates the catalog and logs the publish event.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Autonomous code refactoring agent that rewrites messy functions, splits large files, removes duplication, improves naming, enforces structure, and preserves behavior.
Interact with Anytype's local REST API to manage spaces, objects, types, properties, tags, lists, and search.
Generate API integration test suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters.
Generate browser integration suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters for fixtures, routes, and helper imports.
End-to-end product development orchestrator with human-in-the-loop reviews.
Safe repo pull/push workflow that targets the repository integration branch, uses deterministic planning, and keeps PRs moving with a bounded autonomous resolution loop.
| name | skill-publish |
| description | Publish a skill after validation and approvals; updates the catalog and logs the publish event. |
| disable-model-invocation | true |
| allowed-tools | Read, Grep, Glob, ApplyPatch, Write |
| argument-hint | [skill-name] |
Publish a validated skill with proper approvals, then update catalog metadata and log the publish event.
Skill name
Evidence of test gates
Explicit approver (required for high blast radius)
Template paths are resolved from ${AGENTS_SKILLS_ROOT}/skill-publish/.
/skill-validate <skill-name> and confirm PASS.blast_radius: high, require explicit approval from an authorized maintainer. If missing, STOP.updated date.jarvis/context/skills/publish-log.md with:
This skill participates in the skill evolution system by capturing decision traces at gate resolutions and consulting accumulated feedback.
Before executing any step with a quality or human gate, query accumulated decision traces:
python3 "${AGENTS_SKILLS_ROOT}/_shared/trace_query.py" recent \
--skill "skill-publish" --gate "<gate_name>" --limit 5 --min-loops 1
If patterns or recent feedback exist, incorporate them as additional constraints. Do not cite traces to the user unless asked.
After every gate resolves, capture a decision trace:
python3 "${AGENTS_SKILLS_ROOT}/_shared/trace_capture.py" capture \
--skill "skill-publish" \
--gate "<gate_name>" --gate-type "<human|quality>" \
--outcome "<approved|rejected|passed|failed>" \
--refinement-loops <N> \
[--feedback "<user's feedback text>"] \
[--category <CATEGORY>]
After completion, ask: "Any feedback on this skill-publish run? (skip to finish)" If provided, capture via trace_capture.py with gate "run_retrospective" and gate-type "retrospective".