Fable Judge
Fable Judge is an agent skill (a SKILL.md file) from Sahir619/fable-method. Adversarial verification of finished work. It works with Claude Code, Codex and Cursor and has 2,317 GitHub stars. Install it by copying the skill folder into your agent's skills directory.
github.com/Sahir619/fable-method/skills/fable-judge (opens in a new tab)
Data as of from the GitHub API; description from the skill's SKILL.md. Report an error
- Plugin marketplace
- Testing & QA
- Active
Add this skill
Claude
This repository is a Claude Code plugin marketplace. In Claude Code:
/plugin marketplace add Sahir619/fable-method
/plugin install fable@fable-methodIn the Claude apps, zip the fable-judge folder and upload it under Customize > Skills > + > Upload a skill (code execution must be on).
ChatGPT / Codex
Codex reads skills from .agents/skills/ in a repo or ~/.agents/skills/ for every project:
git clone --depth 1 https://github.com/Sahir619/fable-method.git
cp -r fable-method/skills/fable-judge .agents/skills/fable-judge # repo; ~/.agents/skills for all projectsStandalone skills also load in the ChatGPT desktop app.
Cursor
Cursor loads skills from .cursor/skills/ (or ~/.cursor/skills/) and also reads .claude/skills/:
git clone --depth 1 https://github.com/Sahir619/fable-method.git
cp -r fable-method/skills/fable-judge .cursor/skills/fable-judge # project; ~/.cursor/skills for all projectsSource (checked Oct 7, 2026): code.claude.com/docs/en/skills (opens in a new tab), code.claude.com/docs/en/plugin-marketplaces (opens in a new tab), support.claude.com/en/articles/12512180-using-skills-in-claude (opens in a new tab), learn.chatgpt.com/docs/build-skills (opens in a new tab), cursor.com/docs/context/skills (opens in a new tab)
What this skill does
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?".
When it triggers
- "done"
- "/fable-judge"
- "judge this work"
- "verify what it did"
- "did that actually work?"
- "/fable-judge suite TARGET"
Similar skills
More testing & qa skills
Tourmind Booking
tourmind-com/Tourmind-Booking-Skills
MUST USE for any hotel or accommodation intent in any language, including hotel search, hotel recommendations, nearby accommodation, hostels, guesthouses, resorts, where-to-stay questions, room…
Active · last commit Oct 19, 2026
Testing & QAPython1688 Sourcing Agent
LeoYeAI/agent-master-skills
Your intelligent companion for mastering 1688.com procurement.
Active · last commit Nov 13, 2026
Testing & QAPythonCreate Business
wondelai/skills
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead.
Active · last commit Nov 13, 2026
Testing & QAShellMCP App Builder
alpic-ai/skybridge
Guide developers through creating and updating MCP Apps.
Active · last commit Nov 13, 2026
Testing & QATypeScriptMemory Recall
zilliztech/memsearch
Search and recall relevant memories from past sessions via memsearch.
Active · last commit Nov 13, 2026
Testing & QAPythonSkillevaluator
NVIDIA/SkillEvaluator
Run and interpret SkillEvaluator for agent skills.
Active · last commit Nov 16, 2026
OfficialTesting & QAPython
How do I install the Fable Judge skill?
In Claude Code, run /plugin marketplace add Sahir619/fable-method and then /plugin install fable@fable-method. For Codex or Cursor, copy the fable-judge folder into .agents/skills/ or .cursor/skills/.
Is the Fable Judge skill free?
Yes. The repository is open source under the MIT license.
Is Fable Judge maintained?
The repository's most recent commit was on Oct 3, 2026. Its latest release is v1.4.0. appsgit only lists skills from repositories with a commit in the last six months.