القائمة
Automated feedback collection and learning documentation. Captures learnings from issues, generates ADRs for architecture decisions, and prompts for retrospective insights.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Orchestrates a dual-AI engineering loop where Claude CLI runs with `--dangerously-skip-permissions` for planning/implementation and Codex validates/reviews outputs. Use when users ask for Claude+Codex collaboration, cross-review, dual AI loop, or explicit Claude CLI execution with skip-permission mode ("claude", "dangerously-skip-permission", "dangerously-skip-permissions", "codex claude", "dual AI", "교차 검증", "claude 협업").
Codex Agent 작성 전문가. Frontmatter 검증, 트리거 키워드 제안, 구조 템플릿 제공, 테스트 시나리오 작성을 지원합니다.
Synchronize all agile development artifacts in one command. Updates CHANGELOG, README stats, progress tracking, and validates documentation completeness.
Agent/Skill 사용 통계 및 성과 리포트 생성 전문가. CLI 차트로 시각화하고 인사이트를 제공합니다. "통계", "사용량", "analytics", "성과", "리포트", "메트릭", "분석", "usage", "metrics", "statistics", "report" 키워드에 반응.
Tool/Agent 사용 통계를 CLI 차트로 시각화. "통계", "사용량", "analytics", "metrics", "리포트" 키워드에 반응.
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
| name | feedback-loop |
| description | Automated feedback collection and learning documentation. Captures learnings from issues, generates ADRs for architecture decisions, and prompts for retrospective insights. |
Automates collection of learnings, architectural decisions, and retrospective insights.
/feedback <command> [options]
| Command | Description | Output Location |
|---|---|---|
learning | Record learning from issue/bug | docs/feedback/LEARNINGS.md |
adr | Create Architecture Decision Record | docs/adr/ADR-{N}-{slug}.md |
retro | Generate retrospective template | docs/retros/sprint-N-retro.md |
review | Review recent learnings/decisions | Console output |
/feedback learning "Database connection pooling prevents timeout errors"
/feedback learning --from-issue ISS-042
Prompts: What was the problem? → Root cause? → What learned? → Future prevention?
## LRN-{N}: {Title}
**Date**: {date} | **Category**: {category} | **Related**: {issue_id}
### Context / Problem / Root Cause / Learning / Application
### Tags: `{tag1}` `{tag2}`
/feedback adr "Use PostgreSQL over MySQL"
/feedback adr --title "Authentication Strategy" --status proposed
| Option | Values |
|---|---|
--title | ADR title |
--status | proposed, accepted, deprecated, superseded |
--supersedes | ADR number this replaces |
Prompts: Context/problem? → Options considered? → Decision? → Consequences?
# ADR-{N}: {Title}
**Status**: {status} | **Date**: {date} | **Deciders**: {names}
## Context → Decision Drivers → Considered Options → Decision → Consequences
/feedback retro # Current sprint
/feedback retro --milestone "v1.0" # For milestone
/feedback retro --quick # Quick 3-question
| Mode | Sections |
|---|---|
| Quick | What went well? / What could improve? / What to try? |
| Full | Keep / Problem / Try / Action items / Velocity analysis |
/feedback review # Last 10 items
/feedback review --category bugs # Filter by category
/feedback review --last 30d # Last 30 days
| Trigger | When | Action |
|---|---|---|
| Issue Resolution | fix: or closes # commit | Prompt for learning |
| Architecture Change | Core infrastructure modified | Prompt for ADR |
| Category | Keywords | Example |
|---|---|---|
bugs | fix, error, crash | Memory leak patterns |
performance | slow, optimize, cache | Query optimization |
security | auth, vulnerability | Input validation |
architecture | design, pattern | Event sourcing |
tooling | build, deploy, ci | Docker multi-stage |
process | workflow, team | Code review practices |
| Category | When to Use |
|---|---|
infrastructure | Database, hosting, scaling |
architecture | Patterns, structure, modules |
security | Auth, encryption, compliance |
integration | APIs, third-party, protocols |
process | Development workflow, tools |
docs/
├── feedback/LEARNINGS.md, INDEX.md
├── adr/INDEX.md, ADR-{N}-{slug}.md, template.md
└── retros/sprint-N-retro.md, milestone-{name}-retro.md
{
"feedback": {
"auto_prompt_on_fix": true,
"auto_prompt_on_arch_change": true,
"learning_categories": ["bugs", "performance", "security", "architecture"],
"adr_auto_number": true,
"retro_template": "full",
"review_default_count": 10
}
}
| Type | DO | DON'T |
|---|---|---|
| Learning | Record immediately, include examples, tag for search | Skip "obvious" learnings, be too brief |
| ADR | Create before implementation, include rejected options | Create for trivial decisions, forget consequences |
| Retro | Hold within 24h, assign owners to actions | Blame individuals, skip action items |
| Skill | Purpose |
|---|---|
/sprint | Sprint management with retro |
/agile-sync | Include feedback in sync |
/doc | General documentation |