meta
14
总安装量
3
周安装量
#24178
全站排名
安装命令
npx skills add https://github.com/atrislabs/atris --skill meta
Agent 安装分布
opencode
3
codex
3
claude-code
3
gemini-cli
3
antigravity
2
Skill 文档
Meta Skill
How to be an effective agent. Load this when you need to check yourself.
When to activate
- Starting a new session (orientation)
- Feeling stuck or uncertain
- Output feels sloppy or generic
- Complex task ahead
- After a mistake
Context awareness
- MAP first – Read
atris/MAP.mdbefore any search. It’s the index. - Journal context – Check today’s log for recent work, patterns, blockers.
- LESSONS.md – What failed before? Don’t repeat.
- Skill routing – Frontend? Load
design. Backend? Loadbackend. Writing? Loadwriting.
Pace control
| Signal | Action |
|---|---|
| Simple task, clear path | Execute fast |
| Complex task, multiple approaches | Slow down, plan first |
| Uncertain about intent | Ask ONE question |
| Output feels off | Pause, re-read context |
| Stuck > 2 attempts | Escalate, don’t spiral |
Self-correction triggers
Stop and reassess when:
- You’re about to search without checking MAP
- You’re writing code during PLAN phase
- You’re adding features not requested
- You’re explaining instead of doing
- You’ve used words like “robust”, “comprehensive”, “streamlined”
Memory leverage
Before acting:
- Check
atris/policies/LESSONS.md– short lessons from past mistakes - Check
atris/features/– prior art for similar work - Check journal history –
grep -i "<keyword>" atris/logs/**/*.md
Skill composition
You can stack skills:
meta+design= thoughtful frontend workmeta+backend= careful API designmeta+writing= deliberate prose
Meta is the foundation. Domain skills are the specialization.
The loop
Orient (read context)
â
Decide (which skill? what pace?)
â
Act (execute with focus)
â
Check (output match intent?)
â
Learn (add to LESSONS if miss)
Anti-patterns
- Grepping before MAP check
- Coding during planning
- Adding unrequested features
- Verbose explanations
- Guessing instead of asking
- Repeating past mistakes
- Creating skill without symlinking to .claude/skills/ (won’t load mid-session)
Skill evolution
Skills improve from your mistakes:
- After REVIEW, log learnings to
LESSONS.md(format:date | skill | lesson) - Repeated lessons (2-3x) get promoted into the relevant skill
- Next agent loads the improved skill
You’re training future agents. Leave the codebase smarter than you found it.
One-liner
Think before you act. Check yourself. Use the system.