learn SKILL.md skillA

learn from chan4lk/specclaw is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add chan4lk/specclaw/learn@git:20261016.d5964b7

Pins git:20261016.d5964b7 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: chan4lk/specclaw
Path: plugins/specclaw-review/skills/learn/SKILL.md
Versions recorded: 1
Latest version: git:20261016.d5964b7, committed Oct 16, 2026
Size: 1,533 bytes
Repository stars: 14
License: MIT

Use when the user wants the review rules to learn from past review findings, to promote recurring lessons into repo rules, or to import an existing pitfalls/standards file into specclaw-review rules.

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

# specclaw-review: learn rules from this repo's own review cycle

Rules are never written silently. Every write needs the human's yes.

## Promote recurring lessons

1. Run `specclaw-review learn` (or call the `learn_propose` MCP tool). It is a dry-run that lists the lessons
   seen two or more times, each with its fingerprint.
2. Show the list to the user. For each lesson, ask whether a **guard test** (an automated check) would be better
   than a prose rule. A guard is what actually changes behaviour; a rule only reminds the reviewer. If they want
   a guard, propose it as a new change instead.
3. On a yes, run `specclaw-review learn --apply <fp> [<fp>…]`. That appends `L<n>` rules to
   `.specclaw/review/rules/learned.md` and marks those lessons `ruled`.

## Bootstrap from existing files

For a repo that already keeps review knowledge, such as a `REVIEW-PITFALLS.md`, reviewer standards or agent
hints:

1. Run `specclaw-review learn --import <file>…` first. This is a dry-run: show the user what would be written.
2. On a yes, re-run with `--apply`. Each file becomes `.specclaw/review/rules/imported-<name>.md`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add chan4lk/specclaw/learn@sha256:14abf12d0ec397ae

The line at the top of this page pins the label git:20261016.d5964b7, 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](https://markdownregistry.com/badge/art_k7pkeqdfdtfzqa4w.svg)](https://markdownregistry.com/a/art_k7pkeqdfdtfzqa4w)

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

Versions

The registry has recorded 1 version of this file, committed on Oct 16, 2026.

version	committed	commit	size	audit
git:20261016.d5964b7 latest	2026-10-16	d5964b7	1,533 B	A	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 (1533 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

chan4lk/specclaw · 14 stars · license MIT · pushed 2026-11-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_k7pkeqdfdtfzqa4w
GET https://markdownregistry.com/api/v1/resolve?ref=chan4lk/specclaw/learn
GET https://markdownregistry.com/api/v1/blob/14abf12d0ec397ae880cc939706806ceb263f144cba41fee6f495f5e32085840

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 chan4lk/specclaw

specclaw SKILL.md skill

chan4lk/specclaw · .agents/skills/specclaw/SKILL.md · Run the SpecClaw spec-driven lifecycle in this repository when a request needs proposal, planning, build, verification…

git:20261011.f968269 · audit A · 14 stars

CLAUDE.md CLAUDE.md file

chan4lk/specclaw · CLAUDE.md

git:20261029.e7b3be8 · audit A · 14 stars

llms-full.txt@docs llms.txt file

chan4lk/specclaw · docs/llms-full.txt

git:20261011.f968269 · audit A · 14 stars

llms.txt@docs llms.txt file

chan4lk/specclaw · docs/llms.txt

git:20260717.fc3814b · audit A · 14 stars

bf-analyze SKILL.md skill

chan4lk/specclaw · plugins/specclaw-bf/skills/bf-analyze/SKILL.md · Use when onboarding to an existing or legacy codebase that needs a grounded stack, dependency and risk report.