agentleFS
ai-workspace-labai-workspace-lab/xworkspace-core-skills/skills/marketplace/self-improving-1.1.3/SKILL.md

Self-Improving Agent (With Self-Reflection)

Skill8 starsChanged 5 months agoMITView on GitHub

Self-reflection + Self-criticism + learning from corrections. Agent evaluates its own work, catches mistakes, and improves permanently.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. About 0 are common, 13 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈13

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All data stored in ~/self-improving/.

    line 42
  2. Distinctive:

    After completing significant work, pause and evaluate:

    line 80
  3. Distinctive:

    After completing a multi-step task

    line 87
  4. Distinctive:

    After receiving feedback (positive or negative)

    line 88
  5. Distinctive:

    After fixing a bug or mistake

    line 89
  6. Distinctive:

    When you notice your output could be better

    line 90
  7. Distinctive:

    Never infer from silence alone

    line 149
  8. Distinctive:

    After 3 identical lessons → ask to confirm as rule

    line 150
  9. Distinctive:

    Never delete without asking

    line 163
  10. Distinctive:

    If ambiguous → ask user

    line 175
  11. Distinctive:

    When file exceeds limit:

    line 178
  12. Distinctive:

    Never lose confirmed preferences

    line 182
  13. Very specific:

    Every action from memory → cite source: "Using X (from projects/foo.md:12)"

    line 185
  14. Distinctive:

    If context limit hit:

    line 193
  15. Distinctive:

    Never fail silently — tell user what's not loaded

    line 196

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

When to Use

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.

Architecture

Memory lives in ~/self-improving/ with tiered structure. See memory-template.md for setup.

~/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

Quick Reference

TopicFile
Setup guidesetup.md
Learning mechanicslearning.md
Security boundariesboundaries.md
Scaling rulesscaling.md
Memory operationsoperations.md
Self-reflection logreflections.md

Data Storage

All data stored in ~/self-improving/. Create on first use:

mkdir -p ~/self-improving/{projects,domains,archive}

Detection Triggers

Log automatically when you notice these patterns:

Corrections → add to corrections.md, evaluate for memory.md:

  • "No, that's not right..."
  • "Actually, it should be..."
  • "You're wrong about..."
  • "I prefer X, not Y"
  • "Remember that I always..."
  • "I told you before..."
  • "Stop doing X"
  • "Why do you keep..."

Preference signals → add to memory.md if explicit:

  • "I like when you..."
  • "Always do X for me"
  • "Never do Y"
  • "My style is..."
  • "For [project], use..."

Pattern candidates → track, promote after 3x:

  • Same instruction repeated 3+ times
  • Workflow that works well repeatedly
  • User praises specific approach

Ignore (don't log):

  • One-time instructions ("do X now")
  • Context-specific ("in this file...")
  • Hypotheticals ("what if...")

Self-Reflection

After completing significant work, pause and evaluate:

  1. Did it meet expectations? — Compare outcome vs intent
  2. What could be better? — Identify improvements for next time
  3. Is this a pattern? — If yes, log to corrections.md

When to self-reflect:

  • After completing a multi-step task
  • After receiving feedback (positive or negative)
  • After fixing a bug or mistake
  • When you notice your output could be better

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.

Quick Queries

User saysAction
"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

Memory Stats

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

Core Rules

1. Learn from Corrections and Self-Reflection

  • Log when user explicitly corrects you
  • Log when you identify improvements in your own work
  • Never infer from silence alone
  • After 3 identical lessons → ask to confirm as rule

2. Tiered Storage

TierLocationSize LimitBehavior
HOTmemory.md≤100 linesAlways loaded
WARMprojects/, domains/≤200 lines eachLoad on context match
COLDarchive/UnlimitedLoad on explicit query

3. Automatic Promotion/Demotion

  • Pattern used 3x in 7 days → promote to HOT
  • Pattern unused 30 days → demote to WARM
  • Pattern unused 90 days → archive to COLD
  • Never delete without asking

4. Namespace Isolation

  • Project patterns stay in projects/{name}.md
  • Global preferences in HOT tier (memory.md)
  • Domain patterns (code, writing) in domains/
  • Cross-namespace inheritance: global → domain → project

5. Conflict Resolution

When patterns contradict:

  1. Most specific wins (project > domain > global)
  2. Most recent wins (same level)
  3. If ambiguous → ask user

6. Compaction

When file exceeds limit:

  1. Merge similar corrections into single rule
  2. Archive unused patterns
  3. Summarize verbose entries
  4. Never lose confirmed preferences

7. Transparency

  • Every action from memory → cite source: "Using X (from projects/foo.md:12)"
  • Weekly digest available: patterns learned, demoted, archived
  • Full export on demand: all files as ZIP

8. Security Boundaries

See boundaries.md — never store credentials, health data, third-party info.

9. Graceful Degradation

If context limit hit:

  1. Load only memory.md (HOT)
  2. Load relevant namespace on demand
  3. Never fail silently — tell user what's not loaded

Scope

This skill ONLY:

  • Learns from user corrections and self-reflection
  • Stores preferences in local files (~/self-improving/)
  • Reads its own memory files on activation

This skill NEVER:

  • Accesses calendar, email, or contacts
  • Makes network requests
  • Reads files outside ~/self-improving/
  • Infers preferences from silence or observation
  • Modifies its own SKILL.md

Related Skills

Install with clawhub install <slug> if user confirms:

  • memory — Long-term memory patterns for agents
  • learning — Adaptive teaching and explanation
  • decide — Auto-learn decision patterns
  • escalate — Know when to ask vs act autonomously

Feedback

  • If useful: clawhub star self-improving
  • Stay updated: clawhub sync

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.