메뉴
기본적으로 소스를 먼저 확인하는 Prompt가 선택됩니다. 직접 명령으로 전환하거나 로컬 사본을 다운로드할 수도 있습니다.
설치 여부를 결정하기 전에 SKILL.md와 SkillsMP에 표시된 보조 파일을 읽어 보세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/thiagofernandes1987-create/APEX --skill self-improving-agent명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
SOC 직업 분류 기준
| name | self-improving-agent |
| description | Use this skill when the task requires self improving agent capabilities. |
| executor | LLM_BEHAVIOR |
| skill_id | engineering.cs-engineering-team.self-improving-agent |
| status | ADOPTED |
| security | {"level":"standard","pii":false,"approval_required":false} |
| anchors | ["engineering","llm","agent"] |
| tier | 2 |
| input_schema | [{"name":"code_or_task","type":"string","description":"Code snippet, script, or task description to process","required":true},{"name":"context","type":"string","description":"Additional context or background information","required":false}] |
| output_schema | [{"name":"result","type":"string","description":"Generated or refactored code output"},{"name":"explanation","type":"string","description":"Explanation of changes or implementation decisions"}] |
Auto-memory captures. This plugin curates.
Claude Code's auto-memory (v2.1.32+) automatically records project patterns, debugging insights, and your preferences in MEMORY.md. This plugin adds the intelligence layer: it analyzes what Claude has learned, promotes proven patterns into project rules, and extracts recurring solutions into reusable skills.
| Command | What it does |
|---|---|
/si:review | Analyze MEMORY.md — find promotion candidates, stale entries, consolidation opportunities |
/si:promote | Graduate a pattern from MEMORY.md → CLAUDE.md or .claude/rules/ |
/si:extract | Turn a proven pattern into a standalone skill |
/si:status | Memory health dashboard — line counts, topic files, recommendations |
/si:remember | Explicitly save important knowledge to auto-memory |
┌─────────────────────────────────────────────────────────┐
│ Claude Code Memory Stack │
├─────────────┬──────────────────┬────────────────────────┤
│ CLAUDE.md │ Auto Memory │ Session Memory │
│ (you write)│ (Claude writes)│ (Claude writes) │
│ Rules & │ MEMORY.md │ Conversation logs │
│ standards │ + topic files │ + continuity │
│ Full load │ First 200 lines│ Contextual load │
├─────────────┴──────────────────┴────────────────────────┤
│ ↑ /si:promote ↑ /si:review │
│ Self-Improving Agent (this plugin) │
│ ↓ /si:extract ↓ /si:remember │
├─────────────────────────────────────────────────────────┤
│ .claude/rules/ │ New Skills │ Error Logs │
│ (scoped rules) │ (extracted) │ (auto-captured)│
└─────────────────────────────────────────────────────────┘
/plugin marketplace add alirezarezvani/claude-skills
/plugin install self-improving-agent@claude-code-skills
clawhub install self-improving-agent
./scripts/codex-install.sh --skill self-improving-agent
| File | Who writes | Scope | Loaded |
|---|---|---|---|
./CLAUDE.md | You (+ /si:promote) | Project rules | Full file, every session |
~/.claude/CLAUDE.md | You | Global preferences | Full file, every session |
~/.claude/projects/<path>/memory/MEMORY.md | Claude (auto) | Project learnings | First 200 lines |
~/.claude/projects/<path>/memory/*.md | Claude (overflow) | Topic-specific notes | On demand |
.claude/rules/*.md | You (+ /si:promote) | Scoped rules | When matching files open |
1. Claude discovers pattern → auto-memory (MEMORY.md)
2. Pattern recurs 2-3x → /si:review flags it as promotion candidate
3. You approve → /si:promote graduates it to CLAUDE.md or rules/
4. Pattern becomes an enforced rule, not just a note
5. MEMORY.md entry removed → frees space for new learnings
Auto-memory is excellent at recording what Claude learns. But it has no judgment about:
That's what this plugin does.
When you promote a learning, it moves from Claude's scratchpad (MEMORY.md) to your project's rule system (CLAUDE.md or .claude/rules/). The difference matters:
Promoted rules have higher priority and load in full (not truncated at 200 lines).
Not everything belongs in CLAUDE.md. Use .claude/rules/ for patterns that only apply to specific file types:
# .claude/rules/api-testing.md
---
paths:
- "src/api/**/*.test.ts"
- "tests/api/**/*"
---
- Use supertest for API endpoint testing
- Mock external services with msw
- Always test error responses, not just happy paths
This loads only when Claude works with API test files — zero overhead otherwise.
Analyzes MEMORY.md and topic files to identify:
Takes a proven pattern and generates a complete skill:
/plugin install or clawhub publishMonitors command output for errors. When detected, appends a structured entry to auto-memory with:
Token overhead: Zero on success. ~30 tokens only when an error is detected.
| Platform | Memory System | Plugin Works? |
|---|---|---|
| Claude Code | Auto-memory (MEMORY.md) | ✅ Full support |
| OpenClaw | workspace/MEMORY.md | ✅ Adapted (reads workspace memory) |
| Codex CLI | AGENTS.md | ✅ Adapted (reads AGENTS.md patterns) |
| GitHub Copilot | .github/copilot-instructions.md | ⚠️ Manual promotion only |
Implement — Curate Claude Code
Use this skill when the task requires self improving agent capabilities.
If this skill fails to produce the expected output: (1) verify input completeness, (2) retry with more specific context, (3) fall back to the parent workflow without this skill.