Menu

Individual skill

skill-forge

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 ready?' or 'is this CLAUDE.md safe for a cold-start agent?', or wants a skill or instruction file quality-gated by a judge panel.

skills/skill-forge/SKILL.md

Read pinned source

Source commit 82a6017d2079ff660452106e2f48e3030801feb5

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Local scripts
Last checked
Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
32
Repository last updated
Oct 16, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# 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

Skill-forge is a prove-and-promote quality gate that runs after authoring, not an authoring tool: it pairs with authoring skills (`brainstorming`, superpowers `writing-skills`) that produce a draft, then drives that draft through adversarial rounds before it ships. For an instruction file the same boundary holds - it gates a `CLAUDE.md`/`AGENTS.md` that already exists or has just been drafted; it does not write one from scratch.

## Input contract

| Input | Required | Notes |
|-------|----------|-------|