self-reflection SKILL.md skillA

self-reflection from rolandbrecht/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rolandbrecht/agent-skills/self-reflection@git:20260308.d6256ba

Pins git:20260308.d6256ba in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rolandbrecht/agent-skills
Path
self-reflection/SKILL.md
Versions recorded
4
Latest version
git:20260308.d6256ba, committed Mar 8, 2026
First version recorded
Mar 7, 2026
Size
4,436 bytes
Repository stars
4
License
MIT

Execute this meta-skill ALWAYS at the end of complex tasks, debugging sessions, or when learning a new project codebase quirk. You MUST trigger this skill to codify hard-won lessons into reusable project rules (saving them to project-specific AI instruction files or a new SKILL.md). Do NOT close a complex task without running this skill to ensure future agents don't make the same mistakes you did!

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-Reflection (Continuous Improvement Protocol)

## Overview

AI coding agents are naturally "stateless." You might spend 2 hours debugging a complex Webpack configuration, a subtle race condition, or a confusing project directory layout, eventually fix it, and then completely "forget" the lesson when a new conversation starts.

The core goal of this skill is to turn you from a "temporary worker" into a "systematic documenter."

**Core Principle:** Hard-won knowledge must be persisted. If a task was difficult because of an undocumented project quirk or architectural gotcha, you MUST write a rule so the *next* agent (or yourself in the future) doesn't repeat your mistakes.

## When to Use

You must trigger this protocol **automatically** before declaring a task "done" and notifying the user in the following scenarios:

- After successfully fixing a complex or confusing bug (especially if it took multiple attempts, required new context, or reading multiple files).
- After struggling with a framework configuration.
- After discovering a codebase-specific convention ("In this project, we always use `X` instead of `Y`").
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rolandbrecht/agent-skills/self-reflection@sha256:f05d5b37fc907091

The line at the top of this page pins the label git:20260308.d6256ba, 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_o6fnuwm7kio5z5u3.svg)](https://markdownregistry.com/a/art_o6fnuwm7kio5z5u3)

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

Versions

The registry has recorded 4 versions of this file, between Mar 7, 2026 and Mar 8, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20260308.d6256ba latest2026-03-08 d6256ba 4,436 BA view · diff
git:20260307.ead86632026-03-07 ead8663 4,423 BA view · diff
git:20260307.15df2cf2026-03-07 15df2cf 4,425 BA view · diff
git:20260307.87e5d122026-03-07 87e5d12 3,124 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 (4436 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

rolandbrecht/agent-skills · 4 stars · license MIT · pushed 2026-09-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_o6fnuwm7kio5z5u3
GET https://markdownregistry.com/api/v1/resolve?ref=rolandbrecht/agent-skills/self-reflection
GET https://markdownregistry.com/api/v1/blob/f05d5b37fc907091d7214475b75ad4fc7e9406295b28f74f0c49f33356645982

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 rolandbrecht/agent-skills

AGENTS.md AGENTS.md file
rolandbrecht/agent-skills · AGENTS.md
git:20260309.3872ac0 · audit A · 4 stars
CLAUDE.md CLAUDE.md file
rolandbrecht/agent-skills · CLAUDE.md
git:20260309.3872ac0 · audit A · 4 stars
ast-code-graph SKILL.md skill
rolandbrecht/agent-skills · ast-code-graph/SKILL.md · Use this skill ANY time you need to search for code structure, refactor symbols, analyze impact, find dead code, or…
git:20260330.9ca8f98 · audit A · 4 stars
ast-grep SKILL.md skill
rolandbrecht/agent-skills · ast-grep/SKILL.md · AST-based structural code search, lint, and rewrite via the `ast-grep` (`sg`) CLI. Use when a search or edit is about…
git:20260921.83744c4 · audit A · 4 stars
llms.txt llms.txt file
rolandbrecht/agent-skills · llms.txt
git:20260309.3872ac0 · audit A · 4 stars
structural-refactor SKILL.md skill
rolandbrecht/agent-skills · structural-refactor/SKILL.md · Use this skill for any structural code search or replacement task — it is the right choice whenever grep/sed would feel…
git:20260309.39975cf · audit A · 4 stars
systematic-debugging SKILL.md skill
rolandbrecht/agent-skills · systematic-debugging/SKILL.md · Trigger this AUTOMATICALLY anytime you encounter a stack trace, test failure, production bug, or unexpected behavior…
git:20260307.ead8663 · audit A · 4 stars

Every file in rolandbrecht/agent-skills

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