self-improvement
Originally frompskoett/pskoett-ai-skills
Installation
Summary
Captures learnings, errors, and corrections to enable continuous improvement across agent sessions.
- Logs to three markdown files (
.learnings/LEARNINGS.md,ERRORS.md,FEATURE_REQUESTS.md) with structured entry formats including priority, status, area tags, and metadata for tracking and deduplication - Supports promotion of broadly applicable learnings to permanent project memory files (
CLAUDE.md,AGENTS.md,.github/copilot-instructions.md) and workspace-level guidance (SOUL.md,TOOLS.md) for OpenClaw - Includes automatic detection triggers for corrections, feature requests, knowledge gaps, and errors; optional hook-based reminders for Claude Code, Codex, and other agents
- Enables recurring pattern detection via
Recurrence-CountandPattern-Keymetadata, with promotion rules for patterns seen 3+ times across multiple tasks within 30 days - Provides inter-session communication tools for OpenClaw (sessions_list, sessions_history, sessions_send) and skill extraction workflow for converting high-value learnings into reusable agent capabilities
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.