From agi-super-team
Evaluates its own work, catches mistakes, and improves permanently through self-reflection, self-criticism, and self-organizing memory. Use before starting work and after responding to the user.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agi-super-team:self-improvingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
User corrects you or points out mistakes. You complete significant work and want to evaluate the outcome. You notice something in your own output that could be better. Knowledge should compound over time without manual maintenance.
User corrects you or points out mistakes. You complete significant work and want to evaluate the outcome. You notice something in your own output that could be better. Knowledge should compound over time without manual maintenance.
Memory lives in ~/self-improving/ with tiered structure. If ~/self-improving/ does not exist, run setup.md.
~/self-improving/
├── memory.md # HOT: ≤100 lines, always loaded
├── index.md # Topic index with line counts
├── projects/ # Per-project learnings
├── domains/ # Domain-specific (code, writing, comms)
├── archive/ # COLD: decayed patterns
└── corrections.md # Last 50 corrections log
| Topic | File |
|---|---|
| Setup guide | setup.md |
| Memory template | memory-template.md |
| Learning mechanics | learning.md |
| Security boundaries | boundaries.md |
| Scaling rules | scaling.md |
| Memory operations | operations.md |
| Self-reflection log | reflections.md |
Log automatically when you notice these patterns:
Corrections → add to corrections.md, evaluate for memory.md:
Preference signals → add to memory.md if explicit:
Pattern candidates → track, promote after 3x:
Ignore (don't log):
After completing significant work, pause and evaluate:
corrections.mdWhen to self-reflect:
Log format:
CONTEXT: [type of task]
REFLECTION: [what I noticed]
LESSON: [what to do differently]
Example:
CONTEXT: Building Flutter UI
REFLECTION: Spacing looked off, had to redo
LESSON: Check visual spacing before showing user
Self-reflection entries follow the same promotion rules: 3x applied successfully → promote to HOT.
| User says | Action |
|---|---|
| "What do you know about X?" | Search all tiers for X |
| "What have you learned?" | Show last 10 from corrections.md |
| "Show my patterns" | List memory.md (HOT) |
| "Show [project] patterns" | Load projects/{name}.md |
| "What's in warm storage?" | List files in projects/ + domains/ |
| "Memory stats" | Show counts per tier |
| "Forget X" | Remove from all tiers (confirm first) |
| "Export memory" | ZIP all files |
On "memory stats" request, report:
📊 Self-Improving Memory
HOT (always loaded):
memory.md: X entries
WARM (load on demand):
projects/: X files
domains/: X files
COLD (archived):
archive/: X files
Recent activity (7 days):
Corrections logged: X
Promotions to HOT: X
Demotions to WARM: X
| Tier | Location | Size Limit | Behavior |
|---|---|---|---|
| HOT | memory.md | ≤100 lines | Always loaded |
| WARM | projects/, domains/ | ≤200 lines each | Load on context match |
| COLD | archive/ | Unlimited | Load on explicit query |
projects/{name}.mddomains/When patterns contradict:
When file exceeds limit:
See boundaries.md — never store credentials, health data, third-party info.
If context limit hit:
This skill ONLY:
~/self-improving/)This skill NEVER:
~/self-improving/Install with clawhub install <slug> if user confirms:
memory — Long-term memory patterns for agentslearning — Adaptive teaching and explanationdecide — Auto-learn decision patternsescalate — Know when to ask vs act autonomouslyclawhub star self-improvingclawhub syncnpx claudepluginhub aaaaqwq/agi-super-team --plugin agi-super-teamLogs errors, user corrections, missing features, API failures, knowledge gaps, and best practices to .learnings/ markdown files. Promotes key insights to CLAUDE.md and AGENTS.md for AI agent self-improvement.
Captures high/medium/low confidence patterns from conversations to prevent repeating mistakes and preserve successes. Invoke proactively after corrections, praise, edge cases, or skill-heavy sessions.
Captures high/medium/low confidence learnings from conversations via triggers like corrections, praise, edge cases. Improves skills by preventing mistakes and preserving successes. Invoke proactively after 'no/wrong', 'perfect', or session ends.