con un clic
skill-feedback
Capture ad-hoc feedback about any skill for the decision trace system.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Capture ad-hoc feedback about any skill for the decision trace system.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
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-feedback |
| description | Capture ad-hoc feedback about any skill for the decision trace system. |
| disable-model-invocation | true |
| allowed-tools | Read, Write, Bash |
| argument-hint | <skill-name> "<feedback text>" |
Record feedback about any skill's behavior as a decision trace. This feeds the short loop (skill reads its own traces on future runs) and the long loop (/skill-improve analyzes accumulated traces to propose skill mutations).
Use this when you have feedback that doesn't correspond to a specific gate interaction — general impressions, workflow complaints, meta-observations, or suggestions.
Template paths are resolved from ${AGENTS_SKILLS_ROOT}/skill-feedback/.
Follow the Harnessy policy in .jarvis/context/docs/standards/skill-feedback-protocol.md when deciding whether feedback must be captured and which skill should receive the trace. The short rule is: capture reusable skill lessons, not empty retrospectives.
skill-name — the skill to attach feedback tofeedback text — free-text description of the issue, suggestion, or observation$ARGUMENTS.${AGENTS_SKILLS_ROOT}/<skill-name>/ or ~/.agents/skills/<skill-name>/ exists. If not, report the error and list similar skill names.
skill-feedback unless the recorder itself failed.python3 "${AGENTS_SKILLS_ROOT}/_shared/trace_capture.py" capture \
--skill "<skill-name>" \
--gate "ad_hoc" \
--gate-type "retrospective" \
--outcome "approved" \
--feedback "<feedback text>"
/skill-improve <skill-name>.