Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add isalicema/skill-doctor --skill zh-cngit clone --depth 1 https://github.com/isalicema/skill-doctorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/isalicema/skill-doctor/zh-cn)<a href="https://agentmods.dev/skills/isalicema/skill-doctor/zh-cn"><img src="https://agentmods.dev/badge/skills/isalicema/skill-doctor/zh-cn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/isalicema/skill-doctor/zh-cn"><img src="https://agentmods.dev/badge/skills/isalicema/skill-doctor/zh-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00136 | $0.02004 |
| Opus 5.5 | $0.00054 | $0.00802 |
| Sonnet 5.5 | $0.00027 | $0.00401 |
| Haiku 4.5 | $0.00014 | $0.00200 |
Grade A, and why
skill-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Doctor 2.0 - Agent 工作流架构与 Skill 体检元技能
方法论演进:
- v1.0(Matt Pocock《Building Great Agent Skills: The Missing Manual》):管提示词瘦身——谁触发 → 步骤 vs 参考材料 → Deletion Test。
- v2.0(在 v1 之上的实战扩展):从「提示词编辑器」升级为「Agent 工作流架构评审器」。新增运行现实对齐、模型/脚本/运行时的职责分配、模型升级后的脚手架复检、多出口事务恢复四道防线。
语言:用用户使用的语言出报告(用户写英文就用英文),表格结构不变。
🔒 两道同意门(最高铁律,任何情况不得跨越)
- 门一 · 体检:确认要体检哪个 Skill 后,只读取、只核对运行态、只出报告,绝不修改任何文件。
- 门二 · 改造:出完报告后,必须等用户明确说"改造/优化/动手改"才能动手。用户没点头,就停在报告。
报告 ≠ 授权改动。哪怕问题很明显,也先给建议、等用户拍板。改造只碰目标 Skill 目录及其专属脚本,绝不动用户其他内容/数据。
首次使用引导(Onboarding · 不知道体检哪个时)
用户第一次用、或问"哪些 skill 该体检"时:
- 跑分诊扫描:
bash ~/.claude/skills/skill-doctor/scripts/scan-skills.sh [skills目录 ...](默认扫~/.claude/skills;项目级 skill 在<项目>/.claude/skills,可一并传入),输出按风险 × 复杂度排序的分诊表(行数 / 是否拆分 / 外部副作用风险分 / 近改天数)。 - 挑出 🔴🟠 高优先项——尤其是短小但带定时任务/外发/写状态副作用的隐形高危 Skill,或刚换了底层模型的 Skill——再结合用户确认的"实际最常用哪几个"(文件系统看不到真实使用频率,必须问用户)给出建议。
- 用户选定后,进入下面的体检流程。始终止于门一,改造要等门二。
体检流程(按 Skill 类型自适应展开)
先用 Read 读完目标 Skill 的 SKILL.md(长文分段读完;必要时连同 scripts/、references/),再按关卡审:
- 纯写作 / 只读研究类 Skill:重点跑关卡 1、2、3(重审品味类描述与模型脚手架)。
- 定时 / 外发 / 写状态 / 跨系统类 Skill:必须跑满关卡 0~4。
关卡 0:运行现实核对(Runtime Reality Check)
原则:Skill 文档写的是意图,运行账本才是生产事实。
- 查谁真正触发它:核对 hooks 配置、定时任务(cron / launchd / 云端 routine / CI)、
CLAUDE.md或其他入口文件里的路由。 - 查双重真相漂移:Skill 里写的模型名、参数阈值(如最少几条证据)、投递目标,与定时任务 payload / 校验脚本是否一致?
- 查最近运行证据:若有近期报错或刚升级过模型,先看日志 / 历史会话里的真实卡点,不凭空猜。
关卡 1:谁触发(入口设计)
- 判断该 自动触发(高频、低风险、边界清楚)还是 手动/受控触发(低频、影响大、需判断时机)。
- 检查
description触发语是否清晰、是否和CLAUDE.md等其他文件里的真实触发语一致——入口真相收敛到一处,剥离跨系统混入的无关叮嘱。 - 记住:每个自动触发 Skill 的 description 都常驻上下文,是实打实的 token 成本。
关卡 2:结构(步骤 vs 参考材料 vs 机械脚本)
- 主文件只留核心决策步骤与分支指向,目标:十分钟内读完。
- 只在特定分支用到的模板、长名单、命令字典 → 拆到
references/,主文件留一句指向。 - 输入输出固定的机械操作(格式校验、字数统计、固定参数投递、状态更新)→ 拆到
scripts/,不在主文件里教模型手敲长串 Shell。
关卡 3:三维删减测试(Deletion / Delegation / Scaffold Test)
逐段用三个问题过筛(判定口径见 references/checklist.md):
- Deletion Test(有效性):删掉这段,行为会不会变?不变就是 no-op / 重复 / 沉积物,删或合并。
- Delegation Test(职责分配):这步需要开放性语义判断/品味(留给模型),还是确定性执行(交给脚本),还是生命周期/兜底播报(交给运行时/调度器)?严禁让模型手工模拟复杂 API 客户端(如把几千字正文塞进一个手拼的 JSON 参数)。
- Scaffold Test(模型代际适配):这条限制是在约束最终结果边界(永久保留,如证据门禁、红线),还是为上一代弱模型搭的过程脚手架(如死板的凑字微雕、逐步教拼参数)?模型升级后,保留结果门禁,拆除束手束脚的旧过程脚手架。
- 反向保护:能压住整套做法的 leading 短句/短词(如
fail-closed、polished report is not evidence,或 Pocock 的vertical slice、read first、deletion test)务必保留,别误删。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 77 lines · 136 tokens per session scan A e467255f0aee
skill-doctor is a skill published in the GitHub repository isalicema/skill-doctor (7 stars, last pushed 8d ago), licensed MIT. It adds 136 tokens to every session and 2,004 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.
skill-doctor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-doctorisalicema/skill-doctor | Skill | 7 | 8d ago | MIT | A | 136 | Claude Code, Codex |
| yao-meta-skillyaojingang/yao-meta-skill | Skill | 2.7k | 4d ago | MIT | A | 76 | Claude Code, Codex |
| create_profile_style_skillFireRedTeam/FireRed-OpenStoryline | Skill | 3.7k | 3mo ago | Apache-2.0 | A | 64 | Claude Code, Codex |
| biomed-skill-creatorPharMolix/OpenBioMed | Skill | 1.1k | 3mo ago | MIT | A | 89 | Claude Code, Codex |
| repo-quality-system-lifecycleArenukvern/skill_steward | Skill | 13 | 4d ago | MIT | A | 73 | Claude Code |
| structured-thinkingellmos-ai/skills | Skill | 9 | 2d ago | MIT | A | 215 | Claude Code, Codex |
| your-skill-nameArenukvern/skill_steward | Skill | 13 | 4d ago | MIT | A | 43 | Claude Code |