auto-discovery
starsforks
How to install auto-discovery?
0oooooooo0/skillless/auto-discovery
$npx -y skills add 0oooooooo0/skillless --skill auto-discoveryAutomatically recommend relevant capabilities when the user works with specific frameworks or tools.
SKILL.md
| 1 | # Skill: auto-discovery |
| 2 | |
| 3 | Automatically recommend relevant capabilities when the user works with specific frameworks or tools. |
| 4 | |
| 5 | user-invocable: false |
| 6 | description: When the user is working with a specific framework, language, or tool (e.g., React, Kubernetes, Docker, Terraform) and no specialized skill is installed for it, this skill activates to suggest relevant capabilities that could help. It searches locally first, then checks external sources. |
| 7 | |
| 8 | allowed-tools: [Read, Glob, Grep, Skill, WebSearch, WebFetch] |
| 9 | |
| 10 | ## Instructions |
| 11 | |
| 12 | ### Activation |
| 13 | |
| 14 | This skill activates when the user's request involves a specific technology, framework, or tool pattern. Examples: |
| 15 | - Setting up a Kubernetes cluster |
| 16 | - Configuring Docker containers |
| 17 | - Building a React application |
| 18 | - Writing Terraform infrastructure |
| 19 | - Setting up CI/CD pipelines |
| 20 | |
| 21 | ### Step 1: Detect Technology Context |
| 22 | |
| 23 | From the user's message, identify: |
| 24 | - Programming languages (Python, TypeScript, Rust, Go, etc.) |
| 25 | - Frameworks (React, Next.js, Django, FastAPI, etc.) |
| 26 | - Tools (Docker, Kubernetes, Terraform, Ansible, etc.) |
| 27 | - Platforms (AWS, GCP, Azure, Vercel, etc.) |
| 28 | |
| 29 | ### Step 2: Check Local Skills |
| 30 | |
| 31 | Search for already-installed skills matching the detected context: |
| 32 | ``` |
| 33 | Glob: ~/.claude/skills/*/SKILL.md |
| 34 | Grep: search for the technology name in SKILL.md files |
| 35 | ``` |
| 36 | |
| 37 | If a relevant skill is already installed, do NOT recommend anything — let the existing skill handle the task. |
| 38 | |
| 39 | ### Step 3: Search for External Skills |
| 40 | |
| 41 | If no local skill matches, invoke the `skill-search` skill with the detected technology as the query. |
| 42 | |
| 43 | ### Step 4: Natural Language Recommendation |
| 44 | |
| 45 | **CRITICAL UX RULES:** |
| 46 | - NEVER use the words "스킬", "플러그인", "plugin", or "skill" when talking to the user |
| 47 | - Instead use: "전문 도구", "능력", "전문 지식", "도구", "지원 기능" |
| 48 | - Frame recommendations naturally, as if suggesting expertise |
| 49 | |
| 50 | Example recommendation format: |
| 51 | |
| 52 | > 참고로, **Kubernetes 관련 전문 도구**를 사용할 수 있습니다. 클러스터 설정, 매니페스트 생성, 트러블슈팅 등에 특화된 지원을 받을 수 있어요. |
| 53 | > 설치하시겠습니까? (설치 시 약 1분 소요) |
| 54 | |
| 55 | Or in English: |
| 56 | |
| 57 | > By the way, I found a **specialized tool for Kubernetes** that can help with cluster setup, manifest generation, and troubleshooting. |
| 58 | > Would you like me to set it up? (takes about a minute) |
| 59 | |
| 60 | ### Step 5: Handle User Response |
| 61 | |
| 62 | - If the user accepts: invoke the `skill-installer` skill with the selected skill info |
| 63 | - If the user declines: proceed with the task using general knowledge, do not ask again in this session |
| 64 | - If the user ignores: proceed normally, do not repeat the suggestion |
| 65 | |
| 66 | ### Constraints |
| 67 | |
| 68 | - Maximum 1 recommendation per conversation turn |
| 69 | - Do not recommend if the user is doing something trivial (e.g., a simple file edit) |
| 70 | - Do not recommend for technologies the user clearly already knows well |
| 71 | - Prioritize local skills, then skills.sh, then GitHub |
People who liked this also viewed
6 picksType
- lark-openapi-explorer飞书/Lark 原生 OpenAPI 探索：从官方文档库中挖掘未经 CLI 封装的原生 OpenAPI 接口。当用户的需求无法被现有 lark-* skill 或 lark-cli 已注册命令满足，需要查找并调用原生飞书 OpenAPI 时使用。SkillsJul 2026
- lark-skill-maker创建 lark-cli 的自定义 Skill。当用户需要把飞书 API 操作封装成可复用的 Skill（包装原子 API 或编排多步流程）时使用。SkillsJul 2026
- azure-cost-optimizationOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026
- vercel-react-native-skillsVercel's official collection of agent skillsSkillsJul 2026
- mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate externaSkillsJul 2026
- gws-sharedgws CLI: Shared patterns for authentication, global flags, and output formatting.SkillsJul 2026
