← Back to Skills Marketplace
amitpnyc

Self-Improving Agent

by AmitPNYC · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
74
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install amitpnyc-self-improving-agent
Description
Log high-signal corrections, tool failures, feature requests, and recurring workflow lessons to a lightweight .learnings/ directory, then promote only repeat...
README (SKILL.md)

Self-Improving Agent

Capture useful lessons while context is fresh. Keep the default behavior lightweight, private, and append-only.

Core rules

  • Prefer signal over volume.
  • Default to logging, not self-modifying instructions.
  • Log only meaningful corrections, failures, recurring issues, durable conventions, or explicit “remember this” requests.
  • Never log secrets, tokens, private keys, environment variables, raw customer data, or full sensitive transcripts unless the user explicitly asks.
  • Prefer short summaries and redacted excerpts over raw output.
  • In OpenClaw, treat edits to AGENTS.md, SOUL.md, TOOLS.md, and MEMORY.md as high-authority changes. Do not make them automatically unless the user asked or the workspace explicitly authorizes it.
  • In OpenClaw, update MEMORY.md only in trusted direct or main-session contexts, not by default from shared/group contexts or routine subagent work.

Initialize once

Store the skill in \x3Cworkspace>/skills/self-improving-agent/ for workspace-local use or ~/.openclaw/skills/self-improving-agent/ for shared use.

Create .learnings/ in the active workspace root or project root and ensure these files exist:

  • .learnings/LEARNINGS.md
  • .learnings/ERRORS.md
  • .learnings/FEATURE_REQUESTS.md

Never overwrite an existing log file.

Where to log

  • ERRORS.md — command failures, tool crashes, API/integration issues, reproducible environment problems
  • LEARNINGS.md — user corrections, outdated assumptions, best practices, non-obvious debugging conclusions, recurring workflow hardening
  • FEATURE_REQUESTS.md — capabilities the user wanted but the system or workflow did not support

Use these learning categories when relevant:

  • correction
  • insight
  • knowledge_gap
  • best_practice

Default operating mode

Use append-only capture by default:

  • append a short structured entry to the right file
  • link related prior entries when issues recur
  • suggest promotion when warranted
  • do not automatically edit long-lived instruction or memory files unless authorized

Promotion rules

Promote a learning only when it is repeated, durable, broad, costly to forget, or explicitly marked permanent by the user.

Do not promote one-off incidents, transient outages, machine-specific glitches, speculative opinions, or unclear temporary preferences.

Promote to the smallest durable home:

  • AGENTS.md — workflow rules and execution guidance
  • TOOLS.md — tool gotchas and environment notes
  • SOUL.md — behavioral principles and communication style
  • MEMORY.md — durable user/project facts
  • project instruction files such as CLAUDE.md or .github/copilot-instructions.md — only when the learning is project-wide

When promoting, distill the lesson into a short rule. Do not copy the full log entry.

Dedupe

Before adding a new entry:

  • scan for a related item
  • use See Also for related entries
  • prefer updating recurrence metadata over creating near-duplicates

Use a stable Pattern-Key for repeated workflow issues when helpful.

Minimal entry shapes

## [LRN-YYYYMMDD-XXX] category
**Logged**: ISO-8601 timestamp
**Priority**: low | medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config | workflow

### Summary
One-line lesson

### Details
What happened and what is correct now

### Metadata
- Source: conversation | error | user_feedback | investigation
- Related Files: path/to/file.ext
- See Also: LRN-YYYYMMDD-XXX
- Pattern-Key: optional-key
- Recurrence-Count: 1
## [ERR-YYYYMMDD-XXX] system_or_command
**Logged**: ISO-8601 timestamp
**Priority**: medium | high | critical
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config | workflow

### Summary
What failed

### Error
Short error text or redacted excerpt

### Context
- Operation attempted
- Relevant inputs or parameters

### Metadata
- Reproducible: yes | no | unknown
- Related Files: path/to/file.ext
- See Also: ERR-YYYYMMDD-XXX
## [FEAT-YYYYMMDD-XXX] capability-name
**Logged**: ISO-8601 timestamp
**Priority**: low | medium | high
**Status**: pending
**Area**: frontend | backend | infra | tests | docs | config | workflow

### Requested Capability
What the user wanted

### User Context
Why it mattered

### Metadata
- Frequency: first_time | recurring
- Related Features: feature-or-workflow

Cross-session sharing

Share learnings across sessions only when the user wants that behavior or the environment explicitly supports it.

When sharing:

  • send a short sanitized summary
  • include only needed IDs and file paths
  • do not send raw transcripts or secret-bearing output by default
  • in OpenClaw, prefer sessions_send summaries over transcript forwarding

OpenClaw notes

  • Prefer openclaw skills install \x3Cslug> for installation guidance.
  • Do not include Claude/Codex-style hook examples unless you are shipping a real OpenClaw hook.
  • If you add hook automation, ship HOOK.md + handler.ts and enable it with openclaw hooks enable \x3Cname>.
  • If the skill later references bundled files, use {baseDir}.
  • Keep setup instructions cross-platform.

Default behavior

When something notable happens:

  1. Decide whether it clears the logging threshold.
  2. Append a concise entry.
  3. Link related prior entries if applicable.
  4. Suggest promotion only if the lesson is repeated or durable.
  5. Promote sparingly and in distilled form.

If unsure whether something deserves promotion, keep it in .learnings/ and move on.

Usage Guidance
Install this if you want the agent to keep local, persistent notes about corrections and workflow lessons. Keep the .learnings/ directory out of shared repos if it may contain private context, and review any proposed promotion into AGENTS.md, MEMORY.md, or similar instruction files before allowing it.
Capability Analysis
Type: OpenClaw Skill Name: amitpnyc-self-improving-agent Version: 1.0.0 The 'self-improving-agent' skill is designed to log workflow corrections, errors, and feature requests to a local `.learnings/` directory to improve agent performance over time. The instructions in `SKILL.md` include explicit security safeguards, such as forbidding the logging of secrets or tokens and requiring user authorization before modifying high-authority configuration files like `AGENTS.md` or `SOUL.md`. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found.
Capability Assessment
Purpose & Capability
The stated purpose is persistent self-improvement through local learning logs; this is coherent with the instructions, but users should understand it creates durable workspace memory.
Instruction Scope
The skill limits logging to high-signal corrections, failures, feature requests, and durable lessons, and it explicitly discourages automatic promotion into long-lived instruction files.
Install Mechanism
There is no install script, dependency, binary requirement, or code file; this is an instruction-only skill.
Credentials
The skill writes to a local .learnings/ directory in the active workspace or project root, which is proportional to its purpose but may matter in shared repositories.
Persistence & Privilege
The skill can create persistent learning records and may suggest promotion into AGENTS.md, MEMORY.md, or project instruction files, but it includes user-authorization safeguards for those high-authority changes.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install amitpnyc-self-improving-agent
  3. After installation, invoke the skill by name or use /amitpnyc-self-improving-agent
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial OpenClaw-native release. Adds append-only .learnings capture for corrections, failures, feature requests, and recurring lessons, with guarded promotion into durable memory/instruction files and no fake hook or non-OpenClaw workflow assumptions.
Metadata
Slug amitpnyc-self-improving-agent
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Self-Improving Agent?

Log high-signal corrections, tool failures, feature requests, and recurring workflow lessons to a lightweight .learnings/ directory, then promote only repeat... It is an AI Agent Skill for Claude Code / OpenClaw, with 74 downloads so far.

How do I install Self-Improving Agent?

Run "/install amitpnyc-self-improving-agent" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Self-Improving Agent free?

Yes, Self-Improving Agent is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Self-Improving Agent support?

Self-Improving Agent is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Self-Improving Agent?

It is built and maintained by AmitPNYC (@amitpnyc); the current version is v1.0.0.

💬 Comments