Self Improving 1.2.16

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

Security Scan

The skill is internally consistent: it implements a local, file-backed self-learning memory (~/self-improving/), requires no credentials or external installs by default, and its instructions align with the described purpose.

Purpose & Capability

The name/description (self-reflection, persistent memory, learning) matches what the SKILL.md asks the agent to do: create and maintain a local ~/self-improving/ directory, load a small HOT memory on startup, log corrections, and run conservative maintenance. Required resources (filesystem access, workspace edits) are appropriate for this purpose and there are no unrelated env vars or binaries requested.

Instruction Scope

Runtime instructions direct the agent to read and write multiple local files (memory.md, corrections.md, heartbeat-state.md, AGENTS.md, SOUL.md, HEARTBEAT.md) and to scan the ~/self-improving/ tree for changes. It also describes periodic maintenance (heartbeat, weekly compaction) and an optional flow to install a companion 'Proactivity' skill. These behaviors are coherent with a persistent memory feature, but they do grant the agent persistent local state and recurring file I/O — the user should be aware that the agent will automatically load HOT memory on session start and will modify some workspace files non-destructively.

Install Mechanism

Instruction-only skill with no install spec and no code files. Nothing is downloaded or executed by default. The only install-like action mentioned is an optional, explicit user-approved command to install a separate 'Proactivity' skill (clawhub install proactivity); that step is conditional and requires user consent.

Credentials

The skill requests no environment variables, no credentials, and no external services by default. Metadata points to configPaths (~/self-improving/ and optional workspace files) which is appropriate for a local memory feature. The main proportionality note is that it asks for filesystem access in the user's home and workspace — not unusual here, but a privacy consideration.

Persistence & Privilege

The skill persists state on disk (creates ~/self-improving/ and many .md files) and instructs the agent to load HOT memory each session. The registry flags do not force 'always: true' and autonomous invocation is the platform default (disable-model-invocation: false). This persistence is expected for the feature, but it does increase the blast radius if the agent or environment is compromised (stored memories are loaded automatically).

Assessment

This skill is coherent and implements a local, file-based memory system. Before installing or enabling it: 1) Understand it will create and write files to ~/self-improving/ and read small workspace files (AGENTS.md, SOUL.md, HEARTBEAT.md) — back those up if you care about them. 2) Do not put secrets, credentials, or sensitive personal data into memory files; the skill's own 'Never Store' guidance is helpful but not enforced by the platform. 3) Review and set filesystem permissions on ~/self-improving/ (consider an isolated account or encrypted directory on shared machines). 4) The optional 'Proactivity' companion requires an explicit network install — decline if you don't want network installs. 5) To remove the skill's persistence later: delete ~/self-improving/ and undo the non-destructive edits to AGENTS.md/SOUL.md/HEARTBEAT.md. If you want greater assurance, ask for a walkthrough of exactly which files will be created and for sample contents before enabling automatic loading of HOT memory.

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. Workspace setup should add the standard self-improving steering to the workspace AGENTS, SOUL, and HEARTBEAT.md files, with recurring maintenance routed through heartbeat-rules.md.

~/self-improving/
├── memory.md          # HOT: ≤100 lines, always loaded
├── index.md           # Topic index with line counts
├── heartbeat-state.md # Heartbeat state: last run, reviewed change, action notes
├── 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
Heartbeat state template	heartbeat-state.md
Memory template	memory-template.md
Workspace heartbeat snippet	HEARTBEAT.md
Heartbeat rules	heartbeat-rules.md
Learning mechanics	learning.md
Security boundaries	boundaries.md
Scaling rules	scaling.md
Memory operations	operations.md
Self-reflection log	reflections.md
OpenClaw HEARTBEAT seed	openclaw-heartbeat.md

Requirements

• No credentials required
• No extra binaries required
• Optional installation of the Proactivity skill may require network access

Learning Signals

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

Common Traps

Trap	Why It Fails	Better Move
Learning from silence	Creates false rules	Wait for explicit correction or repeated evidence
Promoting too fast	Pollutes HOT memory	Keep new lessons tentative until repeated
Reading every namespace	Wastes context	Load only HOT plus the smallest matching files
Compaction by deletion	Loses trust and history	Merge, summarize, or demote instead

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/)
• Maintains heartbeat state in ~/self-improving/heartbeat-state.md when the workspace integrates heartbeat
• 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
• Deletes or blindly rewrites self-improving memory during heartbeat cleanup
• Modifies its own SKILL.md

Data Storage

Local state lives in ~/self-improving/:

• memory.md for HOT rules and confirmed preferences
• corrections.md for explicit corrections and reusable lessons
• projects/ and domains/ for scoped patterns
• archive/ for decayed or inactive patterns
• heartbeat-state.md for recurring maintenance markers

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