self-improve SKILL.md skillA

self-improve from eai-org/agent-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add eai-org/agent-toolkit/self-improve@v1.13

Pins v1.13 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
eai-org/agent-toolkit
Path
skills/self-improve/SKILL.md
Versions recorded
8
Latest version
v1.13, committed Nov 2, 2026
First version recorded
Jun 25, 2026
Size
6,938 bytes
Repository stars
82
License
MIT

Capture durable user feedback into the governing skill, doc or check, or propose creating a new skill when no suitable one exists, so future sessions don't repeat the mistake. Use when the user rejects, reverts, or overrides the agent's output or approach on something a skill, doc or check covers or should cover, and when manually invoked to improve or create guidance.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Self-improve

**Suggest** durable improvements to the skill, doc or check that should have steered the agent,
so the next session gets it right without being told again — and apply them only after the user
approves. The skill proposes; the user stays in control of every change. Three ways in:

- **Manual** — the user invokes `/self-improve` to deliberately improve a skill or doc.
- **Self-triggered** — the agent notices it was corrected on something a skill, doc or check
  governs (or should). Don't silently correct and move on, but don't derail the task either: note
  the lesson, finish what the user asked for, and offer to persist it at the next natural
  breakpoint.
- **Driven by another skill** — a caller (or its launch command, pasted by the user) hands over
  lessons already phrased as durable guidance, sometimes with all or part of a target it settled
  with the user (scope, form, path — possibly a new file or a merge into an existing one). Skip
  step 1; skip step 2 for a lesson whose target the caller settled fully, run it for the rest
  keeping what the caller settled — its Mechanical lesson bullet and new-doc indexing requirement
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add eai-org/agent-toolkit/self-improve@sha256:0893b608a64f2a0c

The line at the top of this page pins the label v1.13, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_tj6twm2lxcf3svbt.svg)](https://markdownregistry.com/a/art_tj6twm2lxcf3svbt)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 8 versions of this file, between Jun 25, 2026 and Nov 2, 2026, about one every 19 days.

versioncommittedcommitsizeaudit
v1.13 latest2026-11-02 b2cf2cd 6,938 BA view · diff
v1.122026-10-21 e430af4 6,609 BA view · diff
v1.112026-10-09 e497c06 5,766 BA view · diff
v1.102026-08-03 ba051f0 4,995 BA view · diff
v1.92026-07-26 6cfa47d 4,869 BA view · diff
v1.92026-06-26 d6d85d0 4,896 BA view · diff
v1.82026-06-25 86e6dec 4,442 BA view · diff
v1.72026-06-25 3abfd2f 4,216 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6938 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

eai-org/agent-toolkit · 82 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_tj6twm2lxcf3svbt
GET https://markdownregistry.com/api/v1/resolve?ref=eai-org/agent-toolkit/self-improve
GET https://markdownregistry.com/api/v1/blob/0893b608a64f2a0c41c3e1524c7dd1d571d46c2b209479ba70f631bbf4903ede

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from eai-org/agent-toolkit

AGENTS.md AGENTS.md file
eai-org/agent-toolkit · AGENTS.md
git:20260913.f03ac1e · audit A · 82 stars
CLAUDE.md CLAUDE.md file
eai-org/agent-toolkit · CLAUDE.md
git:20260817.0a229c6 · audit B · 82 stars
agentify-project SKILL.md skill
eai-org/agent-toolkit · skills/agentify-project/SKILL.md · Make a project agent-ready by converging it toward a canonical agent-neutral structure. Re-runnable, and doubles as an…
v0.5 · audit A · 82 stars
attach-to-ticket SKILL.md skill
eai-org/agent-toolkit · skills/attach-to-ticket/SKILL.md · Attach pasted images, files or URLs to a fetched ticket, saved beside its ticket file and referenced from it, or fill…
v0.4 · audit A · 82 stars
check-ticket-implementation SKILL.md skill
eai-org/agent-toolkit · skills/check-ticket-implementation/SKILL.md · Check how much of a ticket is already implemented and save a per-requirement status report.
v1.3 · audit A · 82 stars
compact-docs-writer SKILL.md skill
eai-org/agent-toolkit · skills/compact-docs-writer/SKILL.md · Draft, rewrite, or refine a doc for maximum token economy without losing any rule or intent. Use for docs kept in…
v1.8 · audit A · 82 stars
compact-skill-creator SKILL.md skill
eai-org/agent-toolkit · skills/compact-skill-creator/SKILL.md · Author or refine a skill for maximum token economy without losing intent. Use when creating any new skill or editing an…
v1.25 · audit A · 82 stars
context-checkup SKILL.md skill
eai-org/agent-toolkit · skills/context-checkup/SKILL.md · Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens.
v1.4 · audit A · 82 stars
create-implementation-plan SKILL.md skill
eai-org/agent-toolkit · skills/create-implementation-plan/SKILL.md · Turn a refined requirements document into a structured implementation PLAN.md a fresh session can execute. Planning…
v1.20 · audit A · 82 stars
create-manual-test-instructions SKILL.md skill
eai-org/agent-toolkit · skills/create-manual-test-instructions/SKILL.md · Turn a ticket, requirements document or code change (branch, PR, commit range, diff) into a concise QA manual-test file…
v1.9 · audit A · 82 stars
execute-plan-tasks SKILL.md skill
eai-org/agent-toolkit · skills/execute-plan-tasks/SKILL.md · Execute one task of a plan's task breakdown, then stop for review.
v0.7 · audit A · 82 stars
explain-in-simple-language SKILL.md skill
eai-org/agent-toolkit · skills/explain-in-simple-language/SKILL.md · Explain code, a decision, a recap, or a question to the user, or write a document a human reads, so a fluent but often…
v1.1 · audit A · 82 stars

Every file in eai-org/agent-toolkit

Other files named self-improve

self-improve SKILL.md skill
yeachan-heo/oh-my-claudecode · skills/self-improve/SKILL.md · Autonomous evolutionary code improvement engine with tournament selection
git:20261013.42b37b7 · audit A · 40,624 stars
self-improve SKILL.md skill
zereight/gitlab-mcp · .github/skills/self-improve/SKILL.md · Autonomous evolutionary code improvement engine with tournament selection. Activate when user says: self-improve, self…
git:20260412.9d9ce51 · audit A · 2,088 stars
self-improve SKILL.md skill
tobihagemann/turbo · codex/skills/self-improve/SKILL.md · Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the…
git:20260927.fa1ba5a · audit A · 418 stars
self-improve SKILL.md skill
tobihagemann/turbo · claude/skills/self-improve/SKILL.md · Extract lessons from the current session, or sweep the project's past sessions when asked, and route them to the…
git:20260927.fa1ba5a · audit A · 418 stars
self-improve SKILL.md skill
danmcinerney/orchflows · example-workflows/self-improve/skills/self-improve/SKILL.md · Review selected native agent history to improve the local environment, custom workflows, or Orchflows itself.
git:20260922.d4c0161 · audit A · 126 stars
self-improve SKILL.md skill
nitinjain999/platform-skills · plugins/platform-skills/skills/self-improve/SKILL.md · Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors…
git:20261018.90b97a9 · audit A · 71 stars
self-improve SKILL.md skill
nitinjain999/platform-skills · skills/self-improve/SKILL.md · Bootstrap and operate a self-improving agent workspace. Scaffolds .learnings/ and memory/ directories, captures errors…
git:20261017.144a17b · audit A · 71 stars
self-improve SKILL.md skill
nguyenthienthanh/aura-frog · archon-os/skills/self-improve/SKILL.md · Full learning loop for the Archon OS plugin: analyze collected learning data from Supabase to identify success…
git:20261029.ef4dc34 · audit A · 26 stars

Browse by kind, by grade A, or by owner.