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