SkillForge
From public sourcesA skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor, cross-runtime compile, and an opt-in proactive advisor.
Overview
- agent-skills
- claude-ai
- claude-code
- claude-skills
- codex
- evals
Installation
Commands are shown, never run by the marketplace. Check them against the official documentation.- Build from sourceFrom public sourcesfrom catalog metadata
Build from source: no validated build recipe — follow the repository instructions.
github.com/tripleyak/SkillForge ↗
Compatibility
Unknown means no evidence was found — not that the product is incompatible.| Platform | Status | Architecture | Evidence | Confidence |
|---|---|---|---|---|
| Claude Code | Unknown | — | — | — |
| Claude (web & desktop) | Unknown | — | — | — |
| OpenAI Codex | Unknown | — | — | — |
| ChatGPT | Unknown | — | — | — |
| Cursor | Unknown | — | — | — |
| GitHub Copilot | Unknown | — | — | — |
| Gemini CLI | Unknown | — | — | — |
Releases
checked Oct 29, 2026Files in 6.0.0
This release has no attached files.
Release history
- v5.1.0Feb 25, 2026Official source ↗
- v5.0.0Feb 25, 2026Official source ↗
- v4.0.0Dec 30, 2025Official source ↗
Quality profile
algorithm quality-v1.0 · assessed Oct 15, 2026Quality Score82
Risk Score0
Quality Score and Risk Score are different measures. A high score does not guarantee safety.
Score components
Maintenance · 2016
Documentation · 1515
Ready to use · 156
Metadata · 108
Releases · 1010
Category confidence · 1010
Adoption · 107
License clarity · 55
Community · 55
License
MITThis is the catalog policy status, not legal advice.
Sources
github.com/tripleyak/SkillForgePrimary★ 909 starslast activity Jul 29, 2026Primary repository · Confidence 1.00
Reviews
No reviews yet.
Alternatives
video-shotcraftSimilar
AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 152 shot recipe cards, 209 motion previews, a production-ready templateApache-2.0 · AI Skillsoil-uiSimilar
UI design skill for Claude Code, Codex and other AI agents: explore distinct directions, compare them side by side, refine against real screenshots. 给 AI Agent 用的 UI 设计 Skill。MIT · AI SkillsarchifySimilar
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.MIT · AI SkillsmarketingskillsSimilar
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.MIT · AI Skillsplanning-with-filesSimilar
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, deterministic completion gate. Manus-style. Install from npm, the Claude Code plugin marketplace, or npx skMIT · AI Skills
oh-story-claudecodeSimilarREADME
From tripleyak/SkillForge · license MIT · fetched Oct 29, 2026SkillForge v6
A skill creator that proves its skills work.
SkillForge routes any skill-related request (use, improve, create, compose), creates new skills through an evidence-driven pipeline, and maintains the health of your whole skill ecosystem. Its core principle: skill quality is a property of behavior, not documents - a skill is done when a fresh agent demonstrably does better with it than without it.
What v6 changed (and why)
v6 is a ground-up rework following a deep external audit (see SKILLFORGE_AUDIT.md on the repo, not shipped with the skill). The headline shifts:
| v5 | v6 |
|---|---|
| 4-agent "unanimous synthesis panel" reads the skill | Skills are executed: baseline (RED) runs before writing, with-skill (GREEN) runs after, behavioral delta is the gate |
| Self-scored "timelessness >= 7" approval | Falsifiable checks moved to lint (validate_skill.py); one adversarial reviewer refutes what lint can't catch |
5,049-word SKILL.md with <details> "progressive disclosure" | 1,158-word SKILL.md; depth lives in references/ loaded on demand |
| Descriptions = "what this skill does" | Descriptions = trigger conditions only (workflow summaries make agents skip the body) |
launchd background advisor that analyzed / and queued into a file nothing read | Advisor delivered through Claude Code hooks (SessionStart + UserPromptSubmit), caps enforced, opt-in |
| Personal-directory scanning on by default, hardcoded GitHub handles | Personal Context strictly opt-in with recorded consent; no shipped defaults |
| Hand-rolled YAML parser that failed SkillForge's own SKILL.md | One shared typed parser (scripts/frontmatter.py), 100+ unit tests, and a regression test that SkillForge validates itself |
| Index missed the Claude Code plugin cache entirely | Cross-runtime discovery: personal, Codex, Claude Code plugin cache; deduped; auto-refresh |
The pipeline
Phase 0 TRIAGE index + word-boundary matching -> USE | IMPROVE | CREATE | COMPOSE | CLARIFY
Phase 0b RED GATE fresh subagent attempts the task WITHOUT the skill; no failure = no skill
Phase 1 ANALYSIS load-bearing lenses (Inversion, Pareto, Root Cause), failure-form matching
Phase 2 SPEC tiered (minimal default / full for infrastructure), decisions + WHY
Phase 3 GENERATE fresh-context subagent receives ONLY the spec + baseline failures
Phase 4 GREEN GATE with-skill runs must clear the recorded baseline failures; trigger tests
Phase 5 REVIEW lint (validate_skill.py) + ONE adversarial reviewer charged to refute
Phase 6 SHIP with evals/ - a per-skill regression suite runnable forever after
What no other skill creator has
- Dedup before create (Phase 0): an index of every skill across runtimes answers "should this exist?" first.
- Skills ship with their tests:
evals/(trigger queries + behavioral scenarios) +run_skill_evals.py= regression testing for skills. - Ecosystem doctor:
skillforge_doctor.pyfinds trigger collisions between skills, duplicates, stale file references, budget violations, and pinned models across your entire roster. - Cross-runtime compile: author once,
compile_skill.py --target claude|codex|agentskills. - Friction mining (opt-in):
mine_skill_friction.py --consentfinds skill gaps in your own local session history. - Proactive advisor (opt-in): evidence-backed skill suggestions delivered via hooks, never auto-invoked.
Install (Claude Code)
git clone https://github.com/tripleyak/SkillForge.git /tmp/skillforge
cp -r /tmp/skillforge ~/.claude/skills/skillforge
cd ~/.claude/skills/skillforge && rm -rf README.md LICENSE CONTEXT.md docs .git .gitignore .skillignore index.html assets/images scripts/tests SKILLFORGE_AUDIT.md
cp /tmp/skillforge/commands/skillforge.md ~/.claude/commands/skillforge.md # optional /skillforge command
Optional advisor + hooks (interactive, everything opt-in):
python3 ~/.claude/skills/skillforge/scripts/install_skillforge.py
Requirements: Claude Code (or Codex CLI), Python 3.8+ (stdlib only; PyYAML used if present).
Toolbox
| Command | Purpose |
|---|---|
python3 scripts/discover_skills.py | Build/refresh the skill index |
python3 scripts/triage_skill_request.py "<request>" --json | Route a request |
python3 scripts/validate_skill.py <dir> | Full validation + lint |
python3 scripts/run_skill_evals.py <dir> [--live] | Run a skill's regression evals |
python3 scripts/skillforge_doctor.py | Ecosystem health report |
python3 scripts/init_skill.py <name> --path <dir> | Scaffold (includes evals/) |
python3 scripts/compile_skill.py <dir> --target <t> | Cross-runtime compile |
python3 scripts/package_skill.py <dir> ./dist | Package as .skill |
python3 scripts/mine_skill_friction.py --consent | Mine local transcripts for skill gaps |
CI: copy assets/templates/github-workflow-skill-ci.yml into .github/workflows/ of any skill repo.
Releases
Version history and detailed release notes live on the releases page. v6.0.0 is a ground-up rework; the audit that drove it ships in-repo as SKILLFORGE_AUDIT.md.
License
MIT - see LICENSE