Claw Self Improving Pro

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use befo...

Security Scan

The skill is an instruction-only local memory/self-improvement system that reads and writes files under ~/self-improving/ and its declared behavior is consistent with its description.

Purpose & Capability

The name/description (self-reflection, learning, memory) matches the requested artifacts and operations: it only requires local file read/write under ~/self-improving/, manages corrections/memory/promotions, and documents expected behaviors. There are no unrelated environment variables, binaries, or external services demanded.

Instruction Scope

SKILL.md and supporting docs instruct the agent to create and maintain files in ~/self-improving/, log corrections, promote/demote patterns, export ZIPs, and optionally run weekly maintenance. These actions are coherent with the purpose. Two caveats: (1) some setup guidance suggests adding lines to AGENTS.md and SOUL.md (workspace config files) — this is advisory but would modify files outside ~/self-improving/ if applied; (2) the 'project detected → preload relevant namespace' behavior is underspecified and could imply scanning workspace context to find the active project. Recommend confirming exactly which files the agent will read/write and whether you want it to edit workspace config files before enabling automatic operations.

Install Mechanism

No install spec and no code files — instruction-only skill. This is lowest-risk from an install perspective: nothing is downloaded or executed from remote sources by the skill itself.

Credentials

The skill requests no environment variables, credentials, or external config paths. It explicitly documents a security boundary forbidding storage of credentials, financial, health, biometric, third-party, or location data. The requested local filesystem access (~/self-improving/) is proportionate to a persistent local-memory feature.

Persistence & Privilege

always:false (not force-included) and autonomous invocation is default but expected. The skill persists data in its own directory only; it does not request elevated/system-wide privileges. The only potential persistence beyond its own scope is the optional advice to edit AGENTS.md/SOUL.md in the workspace — review those edits before applying.

Assessment

This skill appears to do exactly what it says: create and maintain a local self-improvement memory under ~/self-improving/, log corrections, and use that memory to inform future responses. Before installing, consider: (1) Confirm that you are comfortable with the agent creating and editing files in your home directory at ~/self-improving/ (it will create memory.md, corrections.md, index.md, projects/, domains/, archive/, and can export ZIPs). (2) The skill explicitly says never to store credentials/sensitive data, but you should avoid telling it secrets or pasting API keys into its memory files. (3) The setup docs suggest adding lines to AGENTS.md and SOUL.md — verify those target files/paths in your environment before applying edits. (4) If you want to restrict the agent from scanning other workspace files for 'project detection', test the skill in a controlled workspace or review how your agent determines project context. (5) Because this is instruction-only, there is no remote install risk, but if your agent has network privileges, be mindful of where exports/backups are sent; the skill does not itself declare any external endpoints. If you need stricter guarantees, run the skill in a sandboxed account or inspect the created files periodically and keep backups you control.

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. 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

Quick Reference

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

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 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

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

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

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