Is the Self Improving Agent skill free?

Yes. The skill itself is free from jdrhyne/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Self Improving Agent SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.

How do I install Self Improving Agent?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Self Improving Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Self Improving Agent

Logs corrections, errors, and feature gaps into a local .learnings knowledge base

by jdrhyne · jdrhyne/agent-skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · f11f8be

Fetched SKILL.md via raw GitHub; the skill dir contains only SKILL.md (no external scripts to break), frontmatter has name+description, storage path is relative (.learnings/), no security smells. Verified the install block in a clean mktemp HOME: clone+cp placed SKILL.md at ~/.claude/skills/self-improving-agent/SKILL.md. For output I logged one representative correction ("project uses pnpm not npm") two ways: a 3-line free-form baseline note vs the skill's template — the skill artifact is a stable-ID entry (LRN-20260731-001) with Priority/Status/Area triage fields and Summary/Details/Suggested Action/Metadata (Source, Related Files, Tags, See Also) written to a canonical .learnings/LEARNINGS.md, making entries greppable, cross-linkable, and reviewable-before-work — a real retrievability gain over the ad-hoc note, though only a schema-level improvement.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 5/5

What Self Improving Agent does

A convention skill that captures learnings, reproducible errors, and feature requests as structured, ID-tagged entries in a local .learnings/ directory (LEARNINGS.md, ERRORS.md, FEATURE_REQUESTS.md). Triggers when a command fails, the user corrects an assumption, a better workflow is found, or a missing capability should be tracked, and when reviewing prior lessons before major work. Pure markdown templates with no external scripts or dependencies.

How to install Self Improving Agent

git clone --depth 1 https://github.com/jdrhyne/agent-skills.git /tmp/self-improving-agent-src
mkdir -p ~/.claude/skills
cp -R /tmp/self-improving-agent-src/clawdbot/self-improving-agent ~/.claude/skills/self-improving-agent
# No external deps, scripts, or API keys. Pure-markdown skill.
# It creates a .learnings/ directory in your project cwd on first use.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Self Improving Agent

/self-improving-agent Logs corrections, errors, and feature gaps into a local .learnings knowledge base

It also activates on plain-language prompts like these:

Remember that this API call keeps failing
Log this correction so you don't repeat it
Review past learnings before starting this task

Frequently asked questions

Is the Self Improving Agent skill free?: Yes. The skill itself is free from jdrhyne/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Self Improving Agent work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched SKILL.md via raw GitHub; the skill dir contains only SKILL.md (no external scripts to break), frontmatter has name+description, storage path is relative (.learnings/), no security smells. Verified the install block in a clean mktemp HOME: clone+cp placed SKILL.md at ~/.claude/skills/self-improving-agent/SKILL.md. For output I logged one representative correction ("project uses pnpm not npm") two ways: a 3-line free-form baseline note vs the skill's template — the skill artifact is a stable-ID entry (LRN-20260731-001) with Priority/Status/Area triage fields and Summary/Details/Suggested Action/Metadata (Source, Related Files, Tags, See Also) written to a canonical .learnings/LEARNINGS.md, making entries greppable, cross-linkable, and reviewable-before-work — a real retrievability gain over the ad-hoc note, though only a schema-level improvement.
What is the Self Improving Agent SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Self Improving Agent?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Self Improving Agent with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.