Self-Improving Agent (CEO Edition)

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's files and runtime instructions are consistent with its stated purpose: it implements a local, file-based self-improving memory in ~/self-improving and does not request external credentials, installs, or network endpoints.

Purpose & Capability

Name/description (self-reflection, learning, memory) match the asked-for artifacts: creating/reading/writing a ~/self-improving directory, tiered memory files, and correction/promotion rules. The skill does not request unrelated credentials or binaries and the metadata lists ~/self-improving/ as its config path, which is coherent.

Instruction Scope

All instructions are limited to creating, reading, and maintaining files under ~/self-improving and to internal maintenance (compaction, promotions, weekly maintenance). The instructions also ask integrators to add lines to workspace files like AGENTS.md and SOUL.md (workspace config), which is outside the skill's own directory — this is reasonable for integration but you should expect the agent to suggest or make edits to those workspace config files. There are no instructions to call external network endpoints or to read arbitrary system files.

Install Mechanism

Instruction-only skill with no install spec and no code files. Risk from install mechanism is minimal because nothing is downloaded or extracted by the skill itself.

Credentials

The skill requires no environment variables, no credentials, and no third-party service tokens. Boundaries.md explicitly forbids storing credentials or sensitive categories; that is appropriate and proportional. Enforcement, however, depends on the agent following the instructions.

Persistence & Privilege

The skill creates and maintains persistent local files under ~/self-improving (HOT/WARM/COLD tiers), supports exports (ZIP) and wipes (kill switch). It is not always:true and does not request elevated system privileges, but it does give the agent ongoing local storage — users should be aware this persists across sessions and may be exported if requested.

Assessment

This skill is internally coherent and appears to do what it says: keep and use a local, tiered memory under ~/self-improving to learn from corrections. Before installing or enabling it: 1) Accept that the agent will create and read files in your home directory (~/self-improving) and persist preferences across sessions; inspect those files after first run. 2) Ensure you will not accidentally store sensitive secrets in those files — the docs say 'never store credentials', but that depends on correct agent behavior. 3) Review any proposed edits to workspace files (AGENTS.md, SOUL.md) before applying them. 4) If you need strict privacy, run in Passive/Strict mode (requires confirmation before promoting lessons) or keep memory on a separate/local-only environment. 5) The skill has no network endpoints or required credentials; if you later see it trying to send data externally, treat that as a serious red flag. Overall: coherent and expected behavior, but verify created files and modes to match your privacy preferences.

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