self-improvement
Originally frompskoett/pskoett-ai-skills
Installation
Summary
Captures learnings, errors, and corrections to enable continuous improvement across agent sessions.
- Logs failures, user corrections, knowledge gaps, and API errors to structured markdown files (
.learnings/LEARNINGS.md,ERRORS.md,FEATURE_REQUESTS.md) with consistent ID, priority, and status tracking - Supports promotion of broadly applicable learnings to project memory files (
CLAUDE.md,AGENTS.md,.github/copilot-instructions.md) and workspace files in OpenClaw (SOUL.md,TOOLS.md) - Includes OpenClaw workspace integration with automatic session injection, inter-session communication tools, and optional startup hooks for learning reminders
- Provides skill extraction workflow to convert recurring, verified learnings into reusable agent skills with quality gates and multi-agent support
SKILL.md
Self-Improvement Skill
Log learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.
First-Use Initialisation
Before logging anything, ensure the .learnings/ directory and files exist in the project or workspace root. If any are missing, create them:
mkdir -p .learnings
[ -f .learnings/LEARNINGS.md ] || printf "# Learnings\n\nCorrections, insights, and knowledge gaps captured during development.\n\n**Categories**: correction | insight | knowledge_gap | best_practice\n\n---\n" > .learnings/LEARNINGS.md
[ -f .learnings/ERRORS.md ] || printf "# Errors\n\nCommand failures and integration errors.\n\n---\n" > .learnings/ERRORS.md
[ -f .learnings/FEATURE_REQUESTS.md ] || printf "# Feature Requests\n\nCapabilities requested by the user.\n\n---\n" > .learnings/FEATURE_REQUESTS.md
Never overwrite existing files. This is a no-op if .learnings/ is already initialised.
Do not log secrets, tokens, private keys, environment variables, or full source/config files unless the user explicitly asks for that level of detail. Prefer short summaries or redacted excerpts over raw command output or full transcripts.