root

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's behavior (creating and managing a local ~/self-improving memory, editing workspace AGENTS/SOUL files, and optionally installing another skill) is coherent with a self-improvement purpose, but there are important inconsistencies in metadata and some operational behaviors that merit caution before installing.

Purpose & Capability

The SKILL.md content implements a 'self-improving' memory system that reads and writes files under ~/self-improving and updates workspace AGENTS.md / SOUL.md. Those capabilities align with the stated purpose. However, registry/top-level metadata is inconsistent with internal files: the provided skill name/slug is 'root' in the registry header while the SKILL.md and file tree use 'self-improving' (slug self-improving); ownerId values also differ between registry metadata and _meta.json. This mismatch could indicate packaging or provenance issues.

Instruction Scope

The runtime instructions explicitly instruct the agent to read and write files in the user's home directory (~/self-improving/) and to modify workspace files (AGENTS.md, SOUL.md, HEARTBEAT.md). Those actions are within the declared purpose (local memory and steering). The SKILL.md also directs optional installation of a 'Proactivity' skill (network action) but requires explicit user consent. No instructions request unrelated system credentials or secret exfiltration; boundaries.md explicitly forbids storing credentials, which is consistent but should be audited in practice.

Install Mechanism

This is an instruction-only skill with no install spec or code-archive downloads, which is low risk. One caveat: setup.md instructs to run `clawhub install proactivity` if the user agrees — that would perform a network package install from an external source. Installation of that companion skill is explicit/optional, but the user should verify the source of 'proactivity' before consenting.

Credentials

The skill requests no environment variables, binaries, or credentials, and its documented storage rules explicitly forbid saving secrets or third-party personal data. That is proportionate to its self-improvement purpose. Still, the skill will persist user-provided corrections and preferences to disk locally, which could include sensitive user content if the user writes it as a correction — users should ensure sensitive material is not stored.

Persistence & Privilege

The skill creates and manages a persistent local datastore under ~/self-improving/ and will update workspace files. always:false, so it is not force-included globally. This level of persistence is expected for a memory/learning skill, but any skill that writes persistent local state should be reviewed for what it stores and for transparency controls (export/wipe).

What to consider before installing

Key things to check before installing: - Metadata mismatch: The registry header lists this skill as 'root' while the SKILL.md and files call it 'self-improving' (slug self-improving). Owner IDs also differ between top-level metadata and _meta.json. Confirm the skill's provenance with the publisher before trusting it. - Local file writes: The skill will create and manage ~/self-improving/ and modify workspace AGENTS.md / SOUL.md / HEARTBEAT.md. Back up those files first and review diffs after any automated edits. - Data stored locally: The skill is designed to persist corrections, preferences, and patterns. Although its boundaries.md forbids storing credentials and sensitive categories, you should avoid putting secrets or private content into corrections or prompts that will be logged. - Optional network install: setup.md may run `clawhub install proactivity` if you explicitly consent. Review the Proactivity skill's source before allowing that network install. - Autonomy: The skill can be invoked autonomously by the agent (platform default). Because it writes persistent state, consider running it in passive mode initially and review every change it proposes. - If you want to proceed: (1) verify publisher and version (resolve the metadata mismatch), (2) back up workspace config and your home ~/self-improving if present, (3) run in passive mode or review changes interactively, and (4) audit the first few entries the skill writes to ensure it obeys the stated boundaries.

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