Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
runtime-behavior-probe
Plan and execute runtime-behavior investigations with temporary TypeScript probe scripts, validation matrices, state controls, and findings-first reports. Use only when the user explicitly invokes this skill to verify actual runtime behavior beyond normal code-level checks, especially to uncover edge cases, undocumented behavior, or common failure modes in local or live integrations. A baseline smoke check is fine as an entry point, but do not stop at happy-path confirmation.
openai/openai-agents-js 2,570
-
integration-tests
Run the integration-tests pipeline that depends on a local npm registry (Verdaccio). Use when asked to execute integration tests or local publish workflows in this repo.
openai/openai-agents-js 2,570
-
changeset-validation
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages/ or .changeset/ are modified, or when verifying PR changeset compliance and bump level.
openai/openai-agents-js 2,570
-
test-coverage-improver
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose high-impact tests, and confirm with the user before writing tests.
openai/openai-agents-js 2,570
-
pr-draft-summary
Create the required PR-ready summary block, branch suggestion, title, and draft description for openai-agents-js. Use in the final handoff after moderate-or-larger changes to runtime code, tests, examples, build/test configuration, or docs with behavior impact; skip only for trivial or conversation-only tasks, repo-meta/doc-only tasks without behavior impact, or when the user explicitly says not to include the PR draft block.
openai/openai-agents-js 2,570
-
code-change-verification
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents JS monorepo.
openai/openai-agents-js 2,570
-
csv-workbench
Analyze CSV files in /mnt/data and return concise numeric summaries.
openai/openai-agents-js 2,570
-
skill-optimizer
Skill 瘦身優化器 — 減少 token 使用同時保持功能完整
miles990/claude-domain-skills 10
-
knowledge-acquisition-4c
從未知領域到專業的系統化學習方法論
miles990/claude-domain-skills 10
-
consistency-checker
內容一致性檢查器 — 確保程式碼、文檔、多來源之間保持一致
miles990/claude-domain-skills 10
-
tech-spec-gen
設計文件 → 技術規格生成器 — 將任何設計文件轉換為 AI 可執行的技術實作規格
miles990/claude-domain-skills 10
-
research-analysis
研究分析：文獻回顧、競品分析、市場調研、數據分析方法論
miles990/claude-domain-skills 10
-
knowledge-management
知識管理：第二大腦、筆記系統、資訊整理、數位工具流
miles990/claude-domain-skills 10
-
side-income
副業與被動收入：網路賺錢、自媒體變現、投資理財、多元收入來源
miles990/claude-domain-skills 10
-
personal-growth
人生規劃：目標設定、個人品牌、時間管理、職涯發展
miles990/claude-domain-skills 10
-
brainstorming
創意發想：頭腦風暴、靈感激發、創意思維框架、發散與收斂思考
miles990/claude-domain-skills 10
-
deckbuilder-roguelike
類 Slay the Spire 的卡牌構築 Roguelike 遊戲設計框架
miles990/claude-domain-skills 10
-
ui-ux-design
UI/UX 設計：介面設計原則、用戶體驗、可用性、無障礙設計
miles990/claude-domain-skills 10
-
storytelling
故事創作：小說寫作、漫畫腳本、影片企劃、敘事結構、角色塑造
miles990/claude-domain-skills 10
-
visual-media
影像創作：攝影、影片製作、動畫、電影、短影音、後製剪輯
miles990/claude-domain-skills 10
-
game-design
遊戲設計理論、機制設計與玩家體驗
miles990/claude-domain-skills 10
-
galgame-master
Galgame 創作大師 — 角色類型庫、劇本架構、對話生成、美術指示
miles990/claude-domain-skills 10
-
game-planner
專業遊戲企劃框架，產出業界標準的遊戲設計文件 (GDD)
miles990/claude-domain-skills 10
-
strategy-optimization
交易策略優化方法論，從診斷到達標的迭代流程
miles990/claude-domain-skills 10