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 ChenShuo2004/cs-skills --skill cs-search-skillgit clone --depth 1 https://github.com/ChenShuo2004/cs-skillsWrote 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/chenshuo2004/cs-skills/cs-search-skill)<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-search-skill"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-search-skill/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/chenshuo2004/cs-skills/cs-search-skill"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-search-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.02140 |
| Opus 5 | $0.00051 | $0.01070 |
| Sonnet 5 | $0.00020 | $0.00428 |
| Haiku 4.5 | $0.00010 | $0.00214 |
Grade A, and why
cs-search-skill 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Skill
Overview
把一个模糊的调研请求变成可以支持决策的研究简报。默认围绕一个目标对象和 3-5 个代表性竞品,完成纵向发展史、横向现状、用户声音、商业模式与战略判断, 并为关键结论保留可追溯来源。
默认直接在对话中输出中文决策简报;只有用户明确要求时,才把完整结果写入
research.md 或其他文件。
适用范围与边界
适合以下任务:
- 研究一个产品、公司、技术、市场、商业模式或新概念。
- 分析目标对象与直接竞品、替代方案或潜在竞争者。
- 为“是否进入、是否购买、是否跟进、如何定位、下一步做什么”等问题提供依据。
- 需要当前信息、历史演进、用户反馈和多来源交叉验证的深度研究。
不要用于:
- 只需要一个简单定义、一个稳定事实或一次快速查找的问题。
- 纯粹写文章、改稿或包装研究结论;这类任务交给
$cs-writer。 - 没有任何公开证据却要求确认私有数据、内幕消息或确定性预测的任务。
简单事实问题应直接回答,不要为了触发完整流程而制造长报告。
输入契约
开始前识别以下信息:
- 研究对象:产品、公司、技术、市场或概念的明确名称及别名。
- 决策问题:用户希望研究后做什么决定,或需要验证哪一个判断。
- 范围:地区、时间点、行业边界、用户群和重点维度。
- 竞品名单:用户提供的名单优先;没有名单时自动发现 3-5 个代表性对象。
- 已有材料:链接、文档、截图、数据、用户观察或内部假设。
- 深度要求:默认输出决策简报;用户要求时扩展为完整研究报告。
- 交付格式:直接输出文字,或生成 PDF 报告。
只在以下情况提问:研究对象存在多个同名实体、决策问题完全缺失且会改变研究方向, 或研究范围过大到无法在当前任务中完成。其余信息采用合理默认,并在结果中写明。
工作流
1. 定义研究问题
先用一句话复述研究目标,并形成内部研究卡:
目标对象:
决策问题:
研究范围:
竞品集合:
关键维度:
交付形式:中文决策简报
如果用户没有指定竞品,先判断直接竞品、替代方案和潜在进入者,再选出 3-5 个 最有代表性的对象,并说明选择理由。不要为了凑数量加入无关产品。
2. 建立研究地图
根据对象和决策问题选择必要维度,不机械填满清单。通常覆盖:
- 纵向脉络:起源、创始团队或提出者、关键版本、转型、融资/收购、重大争议和当前状态。
- 当前产品:核心能力、目标用户、使用场景、定价、分发渠道、生态和限制。
- 横向竞品:定位、核心差异、产品体验、用户口碑、商业模式和竞争位置。
- 市场环境:需求变化、技术或政策约束、替代方案、进入壁垒和潜在变化。
- 战略判断:优势来源、短板、可持续性、机会、风险和对用户决策的影响。
3. 收集与记录证据
使用可用的网络搜索、页面打开和内容提取能力。先搜索发现线索,再打开原始页面核验, 不要只依赖搜索摘要。针对同一问题组合多个关键词和角度,必要时分别搜索目标对象、 竞品、用户评价和行业背景。
来源优先级:
- 一级来源:官方文档、产品页面、定价页、发布公告、公司披露、监管/法院文件、原始论文、 GitHub 仓库和当事人原始访谈。
- 二级来源:可信媒体的原创报道、行业报告、专业测评和有方法说明的调查。
- 三级来源:论坛、评论、社交媒体和聚合内容,只用于了解用户声音或发现线索,不单独支撑 关键商业判断。
对每条重要结论在内部保留证据记录:
claim:结论或事实
source:来源标题 + URL
published/updated:来源发布日期或更新时间
accessed:访问日期
tier:一级 / 二级 / 三级
confidence:高 / 中 / 低
notes:支持范围、冲突信息或限制
关键数字、当前状态、价格、融资、用户规模和产品能力必须优先使用最新来源; 在可行时用两个相互独立的来源交叉验证。多篇转载同一原始报道不算独立验证。
4. 分析与综合
先整理证据,再提出判断:
- 事实:来源直接支持的内容,紧邻结论放置来源链接。
- 推断:基于多个事实的分析,明确使用“推断”“更可能”“我的判断”等措辞。
- 未知:公开资料无法确认的内容,写明“暂未找到可靠证据”,不要补写确定答案。
What ships with it
1 file 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.
- 10d ago First seen · 200 lines · 101 tokens per session scan A 98a75329e333
cs-search-skill is a skill published in the GitHub repository ChenShuo2004/cs-skills (142 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 2,140 once invoked, about $0.0005 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…