Sahir619/fable-method: 5 Agent Skills
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
| Repository | Sahir619/fable-method |
|---|---|
| GitHub stars | 2,298 |
| Skills | 5 |
| Category | Software engineering |
| License | MIT |
| Last updated | Oct 3, 2026 |
| Install counts | Sahir619/fable-method on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
Install Sahir619/fable-method
| All skills, any agent | npx skills add Sahir619/fable-method |
|---|---|
| One skill | npx skills add Sahir619/fable-method --skill release-helper |
| Only for Claude Code | npx skills add Sahir619/fable-method -a claude-code, or copy a skill folder to ~/.claude/skills/ (all projects) or .claude/skills/ (one project) |
npx skills is the open-source skills CLI; it asks which agents to install for. Skills can include scripts that your agent will run: read a skill before installing it, as you would any code.
Skills in Sahir619/fable-method
| Skill | What it does |
|---|---|
| release-helper | Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production. |
| fable-domain | Discuss a domain with the user, research it from real sources, then generate a trusted skill bundle for it - a step-by-step workflow with a flowchart, a domain adapter, a trap fixture, and a smoke eval. Use when the user says "/fable-domain SECTOR", "make a skill for DOMAIN", "add a domain to the… |
| fable-judge | 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… |
| fable-loop | End-to-end orchestrated workflow that runs a task the way Fable ran sessions - parallel evidence subagents, one committed plan, surgical execution with an intent gate, adversarial verification agents, honest outcome-first report. Use for non-trivial multi-step tasks when the user says… |
| fable-method | A step-by-step problem-solving loop (classify the ask, define done, gather evidence, decide, act surgically, verify by observation, report outcome-first). Use when the user says "/fable-method", "use the fable method", or "approach this like Fable", or proactively when starting any multi-step task… |
Names and descriptions come from each skill's SKILL.md and are written by the pack's authors.
More software engineering skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
obra/superpowers An agentic skills framework & software development methodology that works.
|
15 | 297K | 2026-10-08 |
| 2 |
mattpocock/skills Skills for Real Engineers. Straight from my .agents directory.
|
38 | 281K | 2026-10-08 |
| 3 |
addyosmani/agent-skills Production-grade engineering skills for AI coding agents.
|
25 | 103K | 2026-10-03 |
| 4 |
ComposioHQ/awesome-claude-skills A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
|
864 | 76.7K | 2026-09-18 |
| 5 |
github/awesome-copilot Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
|
445 | 39.8K | 2026-10-08 |
| 6 |
anthropics/claude-plugins-official Official, Anthropic-managed directory of high quality Claude Code Plugins.
|
33 | 37.6K | 2026-10-08 |