harness
TigerStyle development workflow harness. Wraps development tasks in a state machine (GROUNDING → PLANNING → IMPLEMENTING → VERIFYING → COMPLETE) with vision alignment, decision logging, and verification. Use wh...
发现 文档写作 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
TigerStyle development workflow harness. Wraps development tasks in a state machine (GROUNDING → PLANNING → IMPLEMENTING → VERIFYING → COMPLETE) with vision alignment, decision logging, and verification. Use wh...
Provides the "how-to" for workflow / task execution orchestration. Defines methods for planning multi-phase task/workflows, implementing them through agent delegation, and managing artifacts.
Apply Terraform changes safely in this infrastructure monorepo. Use when user asks to apply terraform, run terraform plan/apply, make infrastructure changes, update cloud resources, modify node pools, change cl...
Fast PRD updates - Quick version and feature status updates. Auto-activates on "更新 PRD", "update PRD", "PRD 版本", "完成功能" keywords. AMP principle: Automate the meta workflow.
Quality assurance standards and AI collaboration principles for career_ios_backend. Automatically invoked when discussing code quality, standards, refactoring, or optimization. Trigger keywords: "quality", "ref...
Self-diagnostic debugging - Agent decides diagnostic approach. Auto-activates on "bug", "error", "debug", "不work", "壞掉" keywords. AMP principle: Think > Follow - Agent writes own debug tools.
Ensures all AI-generated output fields have proper validation. Auto-activates on "AI 輸出", "LLM", "Gemini", "GPT", "truncate", "截斷" keywords. Lesson learned: 2026-01-08 Quick Feedback, Report, Deep Analyze t...
Monitors context token usage and warns when approaching limits. Automatically activates when context usage exceeds thresholds (30k, 50k, 70k tokens). Provides recommendations for context management and /clear u...
Fast PRD reference - Quick lookup for product requirements. Auto-activates on "PRD", "产品需求", "读取需求", "read PRD", "查看 PRD" keywords. AMP principle: Simple toolbox (47-line script mindset).
Git workflow best practices for the career_ios_backend project. Automatically invoked when user mentions git operations, commits, pushes, or version control. Trigger keywords: "git", "commit", "push", "pull", "...
Best practices for integrating third-party APIs and services in career_ios_backend. Automatically invoked when working with external APIs like ElevenLabs, OpenAI, Gemini, etc. Trigger keywords: "third-party", "...
Automatically invoked when user wants to develop new features using Test-Driven Development. Trigger keywords: "new feature", "add API", "implement", "create endpoint", "TDD", "test-driven", "新功能", "新增 API...
API development workflow and best practices for career_ios_backend FastAPI project. Automatically invoked when user wants to develop, test, or debug API endpoints. Trigger keywords: "API", "endpoint", "route",...
Error handling patterns and best practices for FastAPI endpoints. Auto-activates on "error", "exception", "validation", "錯誤處理", "異常" keywords. Provides consistent error responses and logging strategies.
Force requirements clarification BEFORE implementation to prevent misunderstandings. Auto-activates on "需求", "requirement", "客戶要", "新功能", "案主說", "用戶想要" keywords. Uses structured CARIO format to c...
Commit current changes by analyzing git status and grouping changes into logical commits
Set up deployment infrastructure for the project following aishift patterns
Add new instruction to the global CLAUDE.md file
Generate and edit images using Google Gemini's Nano Banana image generation API via undyapi.com proxy. Use when users want to generate images from text descriptions, edit existing images with AI, or create visu...
Given a research goal, use existing skills, training reports, and references to propose a small, concrete experiment plan.
Turn experiment reports and notes into summaries and new/updated result skills.
🔄 PHP-QA-CI TOOL ORCHESTRATOR - Automatic run→fix→run cycling for php-qa-ci tools. **ONLY for php-qa-ci pipeline tools** (./bin/qa -t toolname) NOT for ad-hoc tool execution outside php-qa-ci. Use when user...
Analyze existing PHPUnit test failure logs without running tests. Use when: - User says "fix the test failures" (after manually running tests) - User says "what tests are failing?" - User points to specific log...
Run PHPStan static analysis and fix errors using intelligent agent delegation. Use when user requests to: - Run static analysis - Fix PHPStan errors - Check code quality - Analyze type errors Delegates to runne...
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。