skill-forge SKILL.md skillA

skill-forge from bjcoombs/ai-native-toolkit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add bjcoombs/ai-native-toolkit/skill-forge@git:20261007.747a8f8

Pins git:20261007.747a8f8 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
bjcoombs/ai-native-toolkit
Path
skills/skill-forge/SKILL.md
Versions recorded
6
Latest version
git:20261007.747a8f8, committed Oct 7, 2026
First version recorded
Jun 4, 2026
Size
28,435 bytes
Repository stars
32
License
Apache-2.0

Harden a skill or any agent instruction file (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules, .github/copilot-instructions.md) through judge-panel refinement rounds until it clears a 3-tier promotion gate, then promote it. A quality gate that runs after authoring, not an authoring tool. TRIGGER when the user types /skill-forge, asks to test/harden/forge/prove a skill or an instruction file, wants a CLAUDE.md or AGENTS.md driven through adversarial rounds before shipping, asks 'is this skill…

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

# Skill-forge - judge-panel skill-hardening harness

A lead (the Forge Master) chairs ephemeral runner teammates that exercise a draft document via prompt-injection, and a persistent judge panel that scores the transcripts. The lead amends one thing per round and applies a strict 3-tier promotion gate, until the document promotes or hits a budget ceiling. It is proven by forging itself.

The target is a `SKILL.md` by default, but the same loop hardens **any agent instruction file** - `CLAUDE.md`, `AGENTS.md`, `GEMINI.md`, `.cursor/rules/*`, `.github/copilot-instructions.md` - because those files have the same failure surface as a skill: they steer an agent and can mislead it. The artifact type is detected deterministically and drives three adaptations (the lens set, the runner variant, and the canonical intent); see [Artifact type and the lens-selector](#artifact-type-and-the-lens-selector) below.

## Boundary
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add bjcoombs/ai-native-toolkit/skill-forge@sha256:aedb359c016e0c7b

The line at the top of this page pins the label git:20261007.747a8f8, 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_vmoftmdftbqkjkfs.svg)](https://markdownregistry.com/a/art_vmoftmdftbqkjkfs)

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

Versions

The registry has recorded 6 versions of this file, between Jun 4, 2026 and Oct 7, 2026, about one every 25 days.

versioncommittedcommitsizeaudit
git:20261007.747a8f8 latest2026-10-07 747a8f8 28,435 BA view · diff
git:20260625.d42d1802026-06-25 d42d180 27,362 BA view · diff
git:20260624.87091612026-06-24 8709161 27,749 BA view · diff
git:20260618.9c357352026-06-18 9c35735 21,228 BA view · diff
git:20260617.d990bfb2026-06-17 d990bfb 20,647 BA view · diff
git:20260604.c5c35b92026-06-04 c5c35b9 20,583 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 (28435 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

bjcoombs/ai-native-toolkit · 32 stars · license Apache-2.0 · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vmoftmdftbqkjkfs
GET https://markdownregistry.com/api/v1/resolve?ref=bjcoombs/ai-native-toolkit/skill-forge
GET https://markdownregistry.com/api/v1/blob/aedb359c016e0c7b3ffb585030e98697f80bdd9d7dec9c75fdcdd786c5376e33

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 bjcoombs/ai-native-toolkit

CLAUDE.md CLAUDE.md file
bjcoombs/ai-native-toolkit · CLAUDE.md
git:20261011.ef225e2 · audit A · 32 stars
6hats SKILL.md skill
bjcoombs/ai-native-toolkit · skills/6hats/SKILL.md · Six Thinking Hats Analysis
git:20261008.d56b7ee · audit A · 32 stars
ab-equivalence SKILL.md skill
bjcoombs/ai-native-toolkit · skills/ab-equivalence/SKILL.md · Compare two versions of an LLM-directed document - an original (teacher) and a candidate (student) - across a transfer…
git:20260625.d42d180 · audit A · 32 stars
assess-findings SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess-findings/SKILL.md · Renders the /assess report from the deterministic run-context.json and the layer scorecard - the scorecard, the…
git:20261011.6157131 · audit A · 32 stars
assess-pr SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess-pr/SKILL.md · The /assess end-of-run offers - open a PR with the report, track the Top 3 Actions in the user's issue tracker, freeze…
git:20260919.492572b · audit A · 32 stars
assess SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess/SKILL.md · Assess a codebase's readiness for AI agent contributors using the layered contract model, and generate a complexity…
git:20261011.6157131 · audit A · 32 stars
typo SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess/tests/fixtures/claude_config_plugin/extra-skills/typo/SKILL.md · Loaded through the manifest's skills path.
git:20261008.11a01e8 · audit B · 32 stars
clean SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess/tests/fixtures/claude_config_plugin/skills/clean/SKILL.md · A skill whose every field is documented.
git:20261008.11a01e8 · audit B · 32 stars
go-conventions SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess/tests/fixtures/lean_with_skills/.claude/skills/go-conventions/SKILL.md · Go conventions for this repo. TRIGGER when editing any *.go file or Connect-Go handlers.
git:20260529.d38243f · audit A · 32 stars
java-conventions SKILL.md skill
bjcoombs/ai-native-toolkit · skills/assess/tests/fixtures/lean_with_skills/.claude/skills/java-conventions/SKILL.md · Java conventions for this repo. TRIGGER when editing any *.java file, JUnit tests, or Maven modules.
git:20260529.d38243f · audit A · 32 stars
CLAUDE.md@skills/assess/tests/fixtures/lean_with_skills CLAUDE.md file
bjcoombs/ai-native-toolkit · skills/assess/tests/fixtures/lean_with_skills/CLAUDE.md
git:20260529.d38243f · audit A · 32 stars
deslop SKILL.md skill
bjcoombs/ai-native-toolkit · skills/deslop/SKILL.md · Detect and remove the telltale signs of AI-generated 'slop' from any written text - articles, reports, emails, essays…
git:20260920.ef322b2 · audit A · 32 stars

Every file in bjcoombs/ai-native-toolkit

Other files named skill-forge

skill-forge SKILL.md skill
aiskillstore/marketplace · pending/zztimur/skill-forge/SKILL.md · Audit, validate, pressure-test, and grade OpenAI or portable Agent Skills from ZIPs, folders, or SKILL.md drafts…
git:20260906.9f92cac · audit A · 450 stars
skill-forge SKILL.md skill
techygarg/lattice · dev-skills/skill-forge/SKILL.md · Create a new Lattice skill — atom, molecule, or refiner — following all framework conventions. Writing skill files…
git:20261009.a96f344 · audit A · 210 stars
skill-forge SKILL.md skill
lethe044/agentskill-kit · integrations/hermes/skills/skill-forge/SKILL.md · Lets a Hermes agent turn a task it keeps repeating into a tested, reusable skill, using askit to lint, scan, test and…
v2.0.0 · audit A · 48 stars
skill-forge SKILL.md skill
tonydzi/second-brain-starter-kit · skills/skill-forge/SKILL.md · Create a node-local skill on a follower machine and prepare its promotion into the shared set through a gate. Use when…
git:20261007.cd6c208 · audit A · 13 stars
skill-forge SKILL.md skill
frankxai/starlight-intelligence-system · plugins/starlight-foundry/skills/skill-forge/SKILL.md · Forge a reusable, portable skill from a proven workflow or capability brief. Use when the work needs repeatable…
git:20260906.3f9f53e · audit A · 11 stars
skill-forge SKILL.md skill
frankxai/starlight-intelligence-system · plugins/starlight-agent-designer/skills/skill-forge/SKILL.md · Forge a reusable, portable skill from a proven workflow or capability brief. Use when the work needs repeatable…
git:20261010.5aba309 · audit A · 11 stars
skill-forge SKILL.md skill
frankxai/starlight-intelligence-system · skills/foundry/skill-forge/SKILL.md · Forge a reusable, portable skill from a proven workflow or capability brief. Use when the work needs repeatable…
git:20260906.3f9f53e · audit A · 11 stars
skill-forge SKILL.md skill
calebnewtonusc/chewbacca · skills/skill-forge/SKILL.md · Write a new skill, or fix one that is not being obeyed. Use when the user asks for a new skill, says a skill is being…
git:20260921.3f3d9a0 · audit A · 9 stars

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