borghei/Claude-Skills / engineering/self-improving-agent
self-improving-agent
VerifiedCurates agent memory and turns repeated lessons into reviewed rules: memory health checks, pattern extraction, feedback and regression analysis. Use when managing auto-memory or building agents that learn from their own sessions.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.0 KB |
| assets/memory_index/MEMORY.md | markdown | 316 B |
| assets/memory_index/feedback_migrations.md | markdown | 203 B |
| assets/memory_index/feedback_pnpm.md | markdown | 255 B |
| assets/sample_feedback.jsonl | other | 2.2 KB |
| assets/sample_metrics.json | config | 3.6 KB |
| references/feedback-loop-patterns.md | markdown | 9.2 KB |
| references/memory-curation-guide.md | markdown | 4.6 KB |
| references/meta-learning-architectures.md | markdown | 2.4 KB |
| references/self-improvement-methodology.md | markdown | 4.3 KB |
| scripts/feedback_analyzer.pyexecutable | script | 18.5 KB |
| scripts/memory_health_checker.py | script | 13.1 KB |
| scripts/pattern_extractor.py | script | 10.8 KB |
| scripts/regression_detector.pyexecutable | script | 17.0 KB |
| scripts/rule_manager.pyexecutable | script | 12.0 KB |
| scripts/rule_promoter.py | script | 12.0 KB |
| skills/extract.md | markdown | 2.1 KB |
| skills/promote.md | markdown | 2.8 KB |
| skills/remember.md | markdown | 2.1 KB |
| skills/review.md | markdown | 2.3 KB |
| skills/status.md | markdown | 2.5 KB |
skills/remember.md
View on GitHub# Sub-Skill: Remember
**Parent:** self-improving-agent
**Trigger:** "remember this", "capture learning", "log what happened", "save this error"
## Purpose
Capture errors, corrections, and learnings from the current session into the memory system. This is the entry point for the self-improvement loop -- nothing can be improved if it is not first recorded.
## Workflow
### Step 1: Classify the Event
Determine what type of learning to capture:
| Type | Signal | Example |
|------|--------|---------|
| Error resolution | A tool error was fixed | "Bash command failed because path had spaces" |
| User correction | User edited agent output | "User changed import path from relative to absolute" |
| Pattern discovery | A reusable approach worked | "Using `test.beforeEach` eliminated shared state bugs" |
| Anti-pattern | An approach repeatedly fails | "Never use `cy.wait()` -- always use assertions" |
| Preference | User stated a preference | "Use pnpm, not npm" |
### Step 2: Record the Learning
Format the entry using the feedback capture template:
```markdown
## Learning: [Short description]
**Context:** [What task was being performed]
**What happened:** [Outcome description]
**Root cause:** [Why the outcome occurred]
**Correct approach:** [What should have been done]
**Confidence:** [High/Medium/Low]
**Recurrence:** [First time / Seen N times]
**Action:** [KEEP / PROMOTE / EXTRACT]
```
### Step 3: Check for Duplicates
Before adding, search existing memory for related entries:
- If a matching entry exists, increment its recurrence count
- If recurrence crosses the promotion threshold (3+), flag for promotion
### Step 4: Store
Add the entry to the appropriate location:
- MEMORY.md for general learnings
- `memory/<topic>.md` for topic-specific learnings
- Verify MEMORY.md stays under 200 lines
## Inputs
| Input | Required | Description |
|-------|----------|-------------|
| Description | Yes | What was learned |
| Context | Yes | What task triggered the learning |
| Type | No | Auto-classified from description |
## Outputs
- New memory entry with confidence score
- Duplicate detection result (new vs incremented)
- Promotion flag if recurrence threshold met
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |