skill-feedback

name	skill-feedback
description	Capture and aggregate real-world usage feedback for Agent Skills so the Skill Quality Gate loop can keep improving them over time. Use it whenever a skill misfires or underperforms: a skill triggered wrongly (wrong trigger), failed to auto-load on a relevant request (near-miss / description gap), produced a wrong, broken, or low-quality output (output issue), or the user manually corrected its result (manual correction). Also use it to review accumulated skill feedback before running skill-forge, or to close the feedback loop that raises skill quality. Writes one structured JSON object per line to feedback/<skill>/YYYY-MM-DD.jsonl and can summarize them into a report/export that feeds skill-forge's Optimize-description step. Trigger phrases: 'skill feedback', 'log skill feedback', 'skill triggered wrongly', 'near-miss trigger', 'wrong trigger', 'output issue', 'manual correction', 'improve skill', 'skill quality', 'feedback loop'.
when_to_use	Use when: a skill fired but was wrong; a request should have triggered a skill but did not (near-miss); the user edited or corrected a skill's output; you want to review accumulated skill feedback. Examples: 'запомни: запрос X должен был вызвать скилл Y', 'добавь фидбек по skill-forge', 'покажи накопленный фидбек по скиллам', 'этот вывод скилла неверный — запиши'.
license	MIT
metadata	{"author":"bestdeejay-design","version":"1.0.0","compatibility":"Requires Python 3 stdlib only; no third-party packages"}

Skill Feedback — capture the fuel for skill improvement

This skill closes the loop opened by docs/SKILL_QUALITY_GATE.md. The Quality Gate tells you whether a skill is good; this skill tells you how to make it better next time by recording what happened in real usage and turning it into a feed for skill-forge.

Without a feedback capture, improvement is guesswork. With it, every near-miss trigger and every manual correction becomes a concrete edit to a skill's description / when_to_use / body.

When to use

• A skill should have triggered but did not (near-miss): the user's request was in-scope but the auto-load missed it.
• A skill triggered wrongly: the wrong skill loaded for the request.
• A skill produced a wrong / broken / low-quality output (output issue).
• The user manually corrected the skill's output (edited the result, or told you "no, do it differently").
• You want to review what has piled up before running skill-forge.

DO NOT USE FOR

• General chat feedback, venting, or notes unrelated to a specific skill — those belong in memory or the session log, not the skill feedback store.
• Capturing secrets or personal data — never log credentials or PII in entries.

Auto-capture (make it automatic)

For the loop to run without manual nudging, capture feedback proactively. Append the rule from AGENTS_FRAGMENT.md (repo root) to your opencode AGENTS.md. Then any near-miss / manual correction is logged automatically — no explicit "remember this" needed. Each consumer grows their own skills locally; see docs/SKILL_QUALITY_GATE.md Layer C.

How feedback is stored

Each entry is one JSON object on its own line in:

feedback/<skill-name>/YYYY-MM-DD.jsonl

Entry schema:

{
  "ts": "2026-08-26T14:03:00",
  "skill": "api-contract-testing",
  "type":