mrtooher/fable-mode是从https://github.com/mrtooher/fable-mode.导入的特工技能候选人。
概览
mrtooher/fable-mode是从https://github.com/mrtooher/fable-mode.导入的特工技能候选人。
概述(AI 翻译)
当前:v6(2026-10-10)。 实时技能:
fable-mode(根SKILL.md),fable-opus,fable-sonnet,double-check,execution-guardrails。积分榜:俳句→ Opus → → 用户。fable-fable、fable-haiku以及 v3agents/路由 已退役——详见 SUPERSEDED.md。下面有相关章节介绍它们 被保留为历史。
克劳德在大型任务中的执行纪律:书面舞台地图,委派给 在运行时间允许的情况下,指定代理,每个阶段都进行验证检查,可以 实际上不及格,一个怀疑的自我评估,以及必须的冷核复核 任何东西都能送达。
它只是一个清单,不是能力移植。经过三次基准测试,所以要用README说明 可以说明它的作用和不的功能(见证据)。
梯子
每个等级一个技能,同一个核心循环,调校到该等级已知的失败模式:
| 技能 | 模型 | 使用时 | 已知的缺口它守护 |
|---|---|---|---|
fable-mode |
运行的 | 默认;根据模型调整强度 | — |
fable-fable |
克洛德寓言 5。 |
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
fable-mode
Current: v6.1 (2026-10-24) — adds an error-first judgment check and a dissent check to step 3 for prose with no answer key (see
bench/judgment/). Live skills:fable-mode(rootSKILL.md),fable-opus,fable-sonnet,double-check,execution-guardrails. Ladder: Haiku → Sonnet → Opus → the user.fable-fable,fable-haikuand the v3agents/routing are retired — see SUPERSEDED.md. Sections below that describe them are kept as history.
Execution discipline for Claude on large tasks: a written stage map, delegation to named agents where the runtime allows, a verification check at every stage that can actually fail, a skeptical self-review, and a mandatory cold double-check before anything is delivered.
It is a checklist, not a capability transplant. Benchmarked three times so the README can say what it does and does not do (see Evidence).
The ladder
Haiku → Sonnet → Opus → Fable 5.1 → the user
One skill per rung, same core loop, tuned to that tier’s known failure mode:
| Skill | Model | Use it when | Known gap it guards |
|---|---|---|---|
fable-mode |
whatever is running | default; adapts intensity to the model | — |
fable-fable |
Claude Fable 5.1 | the deliverable needs an audit trail (worklog, reproducible checks, flagged judgment calls) or spans sessions | none measured — a provenance runner, not an accuracy runner |
fable-opus |
Claude Opus | peak synthesis short of Fable; orchestrates Sonnet/Haiku workers | trusts its own introspection; scope growth |
fable-sonnet |
Claude Sonnet | balanced default for thorough work | skips the failable check, substitutes “looks right” |
fable-haiku |
Claude Haiku | bulk, cheap, parallel mechanical work | skips verification under time pressure |
Two always-on companions:
execution-guardrails— verify-before-flag, warning batching, word-boundary find-and-replace. Every model, every task, whether or not the loop runs.double-check— the delivery gate. A panel of fresh checker agents (Haiku for mechanical checks, Sonnet for requirements, Opus to adjudicate) attacks the finished artifact. Every fable runner calls it before handing anything over.
Core loop
- Stage map first. Numbered stages, expected output each, one verifiable artifact per stage. Living document; at most two full replans per run — a third means the requirements are ambiguous, go back to the user.
- Delegate by name. Reasoning stages to a Sonnet worker, mechanical stages to a Haiku worker, cold checks to a read-only verifier. Workers don’t spawn workers.
- Verify with a check that can fail. A test that runs, a file in the expected shape, a source actually fetched, an output diffed against spec. “I reviewed it and it looks right” is not a check. Name the exact command or mark the stage unverified.
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add mrtooher/fable-mode