AGENT SKILL

Skill Onboarding Guide

Skill Onboarding Guide (技能上架 SOP)

License 许可
MIT
最近更新
2026-04-16
Stars
★ 52
Forks
13

01 前言 Front Matter

name
Skill Onboarding Guide
description
Skill Onboarding Guide (技能上架 SOP)

03 SKILL.md 正文

Skill Onboarding Guide (技能上架 SOP)

此技能定義了在 SKILLS_All-in-one 平台中新增一個 AI 技能的標準流程。請務必遵循以下步驟以確保系統的一致性與功能的完整性。

? 初始步驟

當下載新的技能檔案後,請先將其放入: @public\SKILLS\Uncategorized\**

?️ 作業流程

1. 分類該 SKILL (Classification)

  • 根據技能的功能,從現有的分類中選擇最合適的一個(例如:Development & Code Tools, Data & Analysis 等)。
  • 將檔案夾從 Uncategorized 移動到 @public\SKILLS\{Category}\{FolderName}\。

2. 資料庫同步 (Database Update)

  • 在 @database/init_skills.sql 的最底部新增一段 INSERT INTO Skill ... 的 SQL 語法。
  • 欄位注意事項:
    • id: 請接續目前最高的 ID。
    • downloadCount: 預設為 0。
    • createdAt: 使用目前的日期 (YYYY-MM-DD)。
    • folderName: 必須與實體資料夾名稱一致。

3. 前端元資料同步 (Frontend Metadata)

  • 在 @src/data/skills.ts 中新增該技能的物件。
  • 欄位包含 id, name, nameZh, description, descriptionZh, category, tags, downloadCount (預設為 0) 等。

4. 資源清單同步 (Manifest Update)

  • 在 @public/skills-manifest.json 中新增該技能的檔案結構。
  • 格式範例:
    "folder-name": {
      "category": "Category Name",
      "files": ["SKILL.md", "references/readme.md"]
    }
    

✅ 最終檢查清單 (Checklist)

  • [ ] 實體檔案路徑正確且包含 SKILL.md。
  • [ ] init_skills.sql 已加入該筆資料。
  • [ ] src/data/skills.ts 已加入該筆資料且 ID 無衝突。
  • [ ] skills-manifest.json 已更新,確保前端下載功能正常。
  • [ ] 執行 npm run prebuild (若適用) 以重新生成清單。

04 同仓库更多 Skills

eric861129
eric861129/SKILLS_All-in-one

what-if-oracle

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.

Skill与智能体开发
★ 52
eric861129
eric861129/SKILLS_All-in-one

venue-templates

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

内容创作者写作与文案资料检索与研究
★ 52
eric861129
eric861129/SKILLS_All-in-one

the-fool

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

开发工程师Skill与智能体开发
★ 52
eric861129
eric861129/SKILLS_All-in-one

scientific-writing

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

内容创作者写作与文案Skill与智能体开发
★ 52
eric861129
eric861129/SKILLS_All-in-one

scientific-brainstorming

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

Skill与智能体开发
★ 52
eric861129
eric861129/SKILLS_All-in-one

research-lookup

Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.

开发工程师后端与接口资料检索与研究
★ 52