Self Improvement
Log agent mistakes, user corrections, and feature gaps into `.learnings/` markdown so future sessions improve instead of repeating errors.
Overview
Self-Improvement is a journey-wide agent skill that captures errors, corrections, and insights into `.learnings/` markdown—usable whenever a solo builder needs durable agent memory before committing to the next task.
Install
npx skills add https://github.com/peterskoett/self-improving-agent --skill self-improvementWhat is this skill?
- First-use bootstrap for `.learnings/` without overwriting existing logs
- Categories: correction, insight, knowledge_gap, best_practice in LEARNINGS.md
- ERRORS.md for command and integration failures
- FEATURE_REQUESTS.md when users ask for missing capabilities
- Triggers on user corrections, API failures, outdated knowledge, and pre-major-task review
- Four log surfaces: LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md, and `.learnings/` directory bootstrap
Adoption & trust: 1.1k installs on skills.sh; 641 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your coding agent keeps repeating wrong assumptions because failures and user corrections vanish when the chat ends.
Who is it for?
Solo builders on long-horizon repos who want lightweight, git-friendly agent memory without standing up a full observability stack.
Skip if: One-shot scripts with no repo continuity, or teams that already enforce a formal knowledge base the agent must not duplicate.
When should I use this skill?
Command or operation fails unexpectedly; user corrects the agent; user requests missing capability; external API or tool fails; knowledge is outdated; better approach found; or before major tasks.
What do I get? / Deliverables
Persistent categorized logs exist in the repo so later agent runs—and promoted project memory—reflect what actually failed and what users fixed.
- Initialized `.learnings/` tree
- Timestamped entries in LEARNINGS, ERRORS, or FEATURE_REQUESTS
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Log a user correction on MVP boundaries before the agent writes an oversized plan.
Record an external API failure pattern so the next integration attempt uses the fixed auth flow.
Capture review insights as best_practice entries before merge.
Document recurring support confusion as knowledge_gap for future content or UX fixes.
Append production incident learnings after a hotfix so Operate runs do not repeat the same misdiagnosis.
How it compares
Project-local learning files—not a substitute for production error monitoring or automated test suites.
Common Questions / FAQ
Who is self-improvement for?
Indie developers using agentic coding tools who want corrections and integration failures preserved in the repo for the next session.
When should I use self-improvement?
Use it journey-wide when commands fail, users correct the agent, tools break, knowledge is stale, better approaches emerge, or before major Validate scoping, Build features, Ship reviews, Launch pushes, Grow experiments, or Operate incident work.
Is self-improvement safe to install?
It writes markdown under `.learnings/` in your workspace; review the Security Audits panel on this page and avoid logging secrets into those files.
SKILL.md
READMESKILL.md - Self Improvement
# 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: ```bash 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. If you want automatic reminders or setup assistance, use the opt-in hook workflow described in [Hook Integration](#hook-integration). ## Quick Reference | Situation | Action | |-----------|--------| | Command/operation fails | Log to `.learnings/ERRORS.md` | | User corrects you | Log to `.learnings/LEARNINGS.md` with category `correction` | | User wants missing feature | Log to `.learnings/FEATURE_REQUESTS.md` | | API/external tool fails | Log to `.learnings/ERRORS.md` with integration details | | Knowledge was outdated | Log to `.learnings/LEARNINGS.md` with category `knowledge_gap` | | Found better approach | Log to `.learnings/LEARNINGS.md` with category `best_practice` | | Simplify/Harden recurring patterns | Log/update `.learnings/LEARNINGS.md` with `Source: simplify-and-harden` and a stable `Pattern-Key` | | Similar to existing entry | Link with `**See Also**`, consider priority bump | | Broadly applicable learning | Promote to `CLAUDE.md`, `AGENTS.md`, and/or `.github/copilot-instructions.md` | | Workflow improvements | Promote to `AGENTS.md` (OpenClaw workspace) | | Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) | | Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) | ## OpenClaw Setup (Recommended) OpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading. ### Installation **Via ClawdHub (recommended):** ```bash clawdhub install self-improving-agent ``` **Manual:** ```bash git clone https://github.com/peterskoett/self-improving-agent.git ~/.openclaw/skills/self-improving-agent ``` Remade for openclaw from original repo : https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement ### Workspace Structure OpenClaw injects these files into every session: ``` ~/.openclaw/workspace/ ├── AGENTS.md # Multi-agent workflows, delegation patterns ├── SOUL.md # Behavioral guidelines, personality, principles ├── TOOLS.md # Tool capabilities, integration gotchas ├── MEMORY.md # Long-term memory (main session only) ├── memory/ # Daily memory files │ └── YYYY-MM-DD.md └── .learnings/ # This skill