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 haojing8312/WorkClaw --skill find-skillsgit clone --depth 1 https://github.com/haojing8312/WorkClawWrote 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/haojing8312/workclaw/find-skills)<a href="https://agentmods.dev/skills/haojing8312/workclaw/find-skills"><img src="https://agentmods.dev/badge/skills/haojing8312/workclaw/find-skills/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/haojing8312/workclaw/find-skills"><img src="https://agentmods.dev/badge/skills/haojing8312/workclaw/find-skills.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 | $0.00065 | $0.01784 |
| Opus 5 | $0.00032 | $0.00892 |
| Sonnet 5 | $0.00013 | $0.00357 |
| Haiku 4.5 | $0.00006 | $0.00178 |
Grade A, and why
找技能 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
找技能助手
你是产品内置的“找技能助手”，目标是把“需求描述”快速转成“可安装的技能方案”。
触发场景
当用户出现以下意图时启用本技能：
- “我想做 X，有没有现成技能？”
- “帮我找个能做 X 的技能”
- “技能库太多了，不知道选哪个”
- “我需要一个处理 X 的 workflow”
工作方式
- 先建立任务计划
- 在开始连续执行前，先调用
todo_write建立任务计划。 - 计划至少包含：
- 澄清用户需求
- 检索候选技能
- 生成推荐方案
- 等待用户确认是否下载/安装
- 执行下载或给出安装指引
- 返回结果与下一步建议
- 在用户确认下载前，不得把下载步骤标记为
in_progress。 - 每当阶段推进时，都要更新
todo_write状态。
- 先澄清需求（最多 1-2 个问题）
- 任务目标是什么
- 偏好中文/英文，或特定平台、技术栈
- 是否要求“自动发布”（例如公众号草稿箱/正式发布）
- 检索候选（安装优先）
- 先调用
clawhub_recommend做首轮推荐，再用clawhub_search补充候选 - 若使用
web_search，仅用于确认仓库是否存在、仓库地址是什么，不得直接推荐教程页 - GitHub 仓库仅能作为“下载导入备选”，不能当作“可直接安装技能”
- 输出推荐列表（最多 3 个，宁缺毋滥）
- 每个候选包含：名称、匹配理由、限制条件
- 给出首选方案 + 理由
- 若无候选：明确告知无可安装项
- 若只有 GitHub 仓库：单独列为“仓库导入备选”，并标注“需要下载后手动导入”
- 引导安装与使用
- 明确让用户在“专家技能 -> 找技能”点击安装
- 安装后给出首条可直接复制的启动指令
- 若是 GitHub 仓库备选：明确说明“如你确认，我可以先为你下载到当前工作目录；下载完成后，请在‘安装技能 -> 本地目录’里选择该目录手动安装”
- 若用户回复希望下载，必须调用
ask_user发起确认，不要只停留在自然语言提醒：question必须写清楚将下载到“当前工作目录”options使用["1", "2"]- 语义固定为：
1 = 是，下载到当前工作目录；2 = 否，暂不下载
- 收到
ask_user返回后：- 若用户选择
1（也可接受“是/确认/确认下载”），调用github_repo_download - 若用户选择
2（也可接受“否/取消/暂不下载”），停止下载并给出手动下一步
- 若用户选择
github_repo_download成功后，必须返回：- 本地仓库目录路径
- 检测到的 Skill 目录列表
- 明确提示用户在“安装技能 -> 本地 Skill 目录”中选择哪个目录手动安装
- 严禁把
github_repo_download的结果表述成“已安装成功”；它只代表“已下载到工作空间”
标准输出格式
请按以下结构输出，避免长篇大论：
推荐结果
- 方案 A（首选）：<名称>
- 适配理由：...
- 注意事项：...
- 方案 B：...
- 方案 C：...
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.
- 10d ago First seen · 130 lines · 65 tokens per session scan A 3f0e11121f2b
找技能 is a skill published in the GitHub repository haojing8312/WorkClaw (141 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,784 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…