Communitygithub.com

技能偵察員

在建立新技能之前,搜尋本地、市集、GitHub 和網路上現有的技能來源,避免重複勞動。

技能偵察員 是什麼?

Skill Scout 是一個 AI 代理技能,旨在防止重複發明輪子。當使用者表達「建立技能」、「尋找技能」或描述一個工作流程時,此技能會主動攔截,並引導代理先搜尋既有的技能來源。它依序掃描本地安裝的技能、市集外掛、GitHub 儲存庫以及一般網路,透過關鍵字比對與同義詞擴展,找出最相關的候選項目。找到後,它會要求對外部來源進行安全審查(檢查未預期的 Shell 命令或憑證處理),最終以排名表格呈現結果,讓使用者選擇直接使用、分叉擴充或新建技能。此技能支援 Claude Code 和類似工具,可與 `search-first`、`skill-stocktake` 等技能搭配,形成完整的技能管理生命週期。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/skill-scout

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

技能偵察員 是做什麼的?

在建立新技能之前使用此技能。目標是避免重複現有社群或市集的工作,同時在採用任何外部技能前先進行審查。

來源:由 redminwang 從社群 PR #1232 中搶救回來。

使用時機

  • 使用者說「建立技能」、「構建技能」、「製作技能」或「新技能」。
  • 使用者問「有沒有技能可以做 X?」或「是否存在能做 Y 的技能?」。
  • 使用者描述一個工作流程,而你正打算建議建立一個新技能。
  • 使用者想要分叉或擴充現有技能。

如果使用者明確表示要跳過搜尋或從頭建立,請確認並繼續執行要求的建立流程。

運作方式

步驟 1 - 捕捉意圖

提取:

  • 技能應執行的任務。
  • 使用技能的觸發條件。
  • 涉及的領域、工具、框架或資料來源。
  • 三到五個搜尋關鍵字以及可用的同義詞。

步驟 2 - 搜尋本地來源

首先搜尋已安裝和市集的技能名稱。本地來源的優先級較高,因為它們已經是使用者環境的一部分。

find ~/.claude/skills -maxdepth 2 -name SKILL.md 2>/dev/null | grep -iE "keyword|synonym"
find ~/.claude/plugins/marketplaces -path '*/skills/*/SKILL.md' 2>/dev/null | grep -iE "keyword|synonym"

然後搜尋 frontmatter 說明:

grep -RilE "keyword|synonym" ~/.claude/skills ~/.claude/plugins/marketplaces 2>/dev/null

步驟 3 - 搜尋遠端來源

使用可用的 GitHub 和網路搜尋工具。偏好簡潔的查詢:

gh search repos "claude code skill keyword" --limit 10 --sort stars
gh search code "name: keyword" --filename SKILL.md --limit 10

對於網路搜尋,最多使用三個針對性查詢,例如:

"claude code skill" keyword
"SKILL.md" keyword
"everything-claude-code" keyword

步驟 4 - 審查外部匹配

在推薦任何外部技能供採用或分叉之前:

  • 閱讀 SKILL.md 的 frontmatter 和說明。
  • 檢查是否有未預期的 Shell 指令、檔案寫入、網路呼叫、憑證處理或套件安裝。
  • 檢查儲存庫是否維護中。
  • 偏好複製到全新的本地分支並檢視 diff,而不是直接編輯市集原始內容。

步驟 5 - 排名結果

依以下條件為候選項目排名:

  1. 技能名稱中的精確關鍵字匹配。
  2. 說明中的關鍵字或同義詞匹配。
  3. 本地已安裝或市集來源。
  4. 有近期活動的 GitHub 維護來源。
  5. 僅網路提及。

最終列表最多 10 個結果。

步驟 6 - 呈現決策選項

為使用者提供一個簡短表格:

選項含義
使用現有直接叫用或安裝匹配的技能。
分叉或擴充複製最接近的技能並修改。
新建在確認無接近匹配後建立新技能。

僅在使用者選擇該路徑或搜尋未找到接近匹配後,才建立新技能。

範例

結果表格

| # | 技能 | 來源 | 匹配原因 | 差距 |
| --- | --- | --- | --- | --- |
| 1 | article-writing | 本地 ECC | 撰寫文章和指南 | 不專注於發行說明 |
| 2 | content-engine | 本地 ECC | 多格式內容工作流程 | 比所需更重 |
| 3 | blog-writer | GitHub | 部落格寫作技能,有近期提交 | 需安全審查 |

面向使用者的摘要

我找到兩個接近的本地匹配和一個外部候選項目。最接近的是 `article-writing`;它涵蓋草稿和修訂,但不包含您要求的發行說明檢查清單。我可以原樣使用它、將其分叉為發行說明變體,或建立一個新技能。

反模式

  • 不應在可以合理搜尋時直接跳轉到新技能建立。
  • 不應未經閱讀就安裝外部技能。
  • 不應呈現一長串未排序的弱匹配結果。
  • 不應將僅網路提及視為可信來源。
  • 不應就地編輯已安裝的市集原始內容。

相關

  • search-first - 通用「先搜尋再建立」工作流程。
  • skill-stocktake - 審計已安裝技能的健康狀態、重複項和缺口。
  • agent-sort - 分類並整理現有的代理和技能。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

相關技能