Skip to content
Back to search

self-improving-agent

Self-improvement skill for OpenClaw. It captures learnings, errors, and feature requests to support continuous improvement across sessions.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/pskoett-self-improving-agent/badge.svg)](/listings/pskoett-self-improving-agent)

HTML

<a href="/listings/pskoett-self-improving-agent"><img src="/api/listings/pskoett-self-improving-agent/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

With OpenClaw's built-in skill installer — this installs into the active OpenClaw workspace:

openclaw skills install @pskoett/self-improving-agent

Or with the ClawHub CLI (`npm i -g clawhub`). Note this installs into `./skills` under the current working directory, not the workspace:

clawhub install @pskoett/self-improving-agent

Or manually — copy the skill subfolder (not the repo root):

git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 85 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # self-improving-agent
  2. Self-improvement skill for OpenClaw. It captures learnings, errors, and feature requests to support continuous improvement across sessions.
  3. **This version is OpenClaw-only.** To use the skill with other agents
  4. (Claude Code, Codex, GitHub Copilot, …), use the original multi-agent
  5. version instead:
  6. https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement
  7. ## Repository Layout
  8. The publishable skill package is the [`self-improving-agent/`](self-improving-agent/)
  9. subfolder — that is what ClawHub installs and what you copy into
  10. `~/.openclaw/skills/`. Repo-level files (this README, `.github/` CI) stay
  11. outside the package on purpose.
  12. - Skill entry point: [`self-improving-agent/SKILL.md`](self-improving-agent/SKILL.md)
  13. - OpenClaw hook: [`self-improving-agent/hooks/openclaw/`](self-improving-agent/hooks/openclaw/)
  14. ## Development and Amp orbs
  15. Use the Node.js version in `.nvmrc`, then run:
  16. ```bash
  17. npm ci
  18. npm test
  19. npm run typecheck
  20. npm run check:shell
  21. ```
  22. The root npm manifest and lockfile are development-only; the publishable skill
  23. subfolder remains dependency-free. Tests use an OpenClaw type stub, so no
  24. OpenClaw installation, credentials, or backing services are required.
  25. Amp runs `.agents/setup` to install the pinned Node.js toolchain and locked
  26. development dependencies before taking an orb snapshot. Warm setup runs reuse
  27. installed dependencies. A repository-scoped login-shell hook selects this Node
  28. version without replacing the orb's system Node. `.agents/resume` intentionally
  29. does no installation because there is no per-wake repair or authentication work.
  30. ## Installation
  31. With OpenClaw's built-in skill installer — this installs into the active
  32. OpenClaw workspace:
  33. ```bash
  34. openclaw skills install @pskoett/self-improving-agent
  35. ```
  36. Or with the ClawHub CLI (`npm i -g clawhub`). Note this installs into
  37. `./skills` under the current working directory, not the workspace:
  38. ```bash
  39. clawhub install @pskoett/self-improving-agent
  40. ```
  41. Or manually — copy the skill subfolder (not the repo root):
  42. ```bash
  43. git clone https://github.com/pskoett/self-improving-agent.git /tmp/self-improving-agent-repo
  44. cp -r /tmp/self-improving-agent-repo/self-improving-agent ~/.openclaw/skills/self-improving-agent
  45. ```
  46. ## Attribution
  47. Remade for OpenClaw from the original repo:
  48. - https://github.com/pskoett/pskoett-ai-skills
  49. - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement
  50. ## Upgrading
  51. See `self-improving-agent/CHANGELOG.md` for version history and per-version
  52. upgrade notes. If using the optional hook, follow
  53. [Install or Upgrade the Hook](self-improving-agent/references/openclaw-integration.md#install-or-upgrade-the-hook).
  54. Locate the active copies, review local patches, preserve the old hook outside
  55. hook discovery, and restart the gateway after replacement. Do not blindly
  56. re-copy the directory: a repeated `cp -r` can nest it without updating the
  57. active handler.
  58. ## Uninstalling
  59. See `self-improving-agent/references/uninstall.md` for disable vs.
  60. full-removal steps. Review `.learnings/` before deleting — it contains your
  61. captured learnings, not skill code.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.