跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
开发与测试

Claude Fable 5 Skills

10 Fable 5-native agent skills — Works with Claude Code, Cursor, Copilot

kpab · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add kpab/claude-fable-5-skills

技能说明

claude-fable-5-skills

10 battle-ready Agent Skills for Claude Fable 5 — the first skill collection designed around how Claude Fable 5 actually behaves, not how older models needed to be babysat.

日本語版 README はこちら →

Anthropic's own guidance for Fable 5 notes that skills written for prior models are often too prescriptive for it and can degrade output quality. Old skills micromanage; Fable 5 needs intent, boundaries, and verification hooks instead. Every skill here is written Fable 5-first.

Works with Claude Code, Claude Cowork, Cursor, Copilot, Gemini CLI, and any harness that reads SKILL.md files (agentskills.io-style: YAML frontmatter + Markdown body).

The 10 skills

#SkillWhat it fixes
1skill-refactorerThe meta-skill. Audits your pre-Fable-5 skills/prompts, deletes capability-compensation scaffolding, keeps real guardrails.
2act-when-readyOver-planning at high effort: re-deriving settled facts, surveying options it won't pursue.
3effort-calibratorPicking the right effort level per workload; Fable 5 at lower effort often beats older models at xhigh.
4no-gold-platingDiffs bigger than the ask: unrequested refactors, speculative abstractions, impossible-state error handling.
5grounded-progressStatus reports on long runs must point at tool-result evidence — no more "tests passing" that never ran.
6scope-guard"Diagnose" ≠ "fix". No unrequested actions, no state changes on pattern-matched evidence.
7subagent-orchestrationParallel delegation, long-lived workers, and fresh-context verifier subagents that out-perform self-critique.
8[markdown-memory](s