发现 研究与调研 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。
Review specifications to find gaps and generate clarifying questions. Use when reviewing spec.md, finding missing requirements, identifying ambiguities, or when you see "review spec", "find gaps", "what's missi...
RESTful API design following best practices with endpoint mapping, schema definition, and error handling. Use when mapping endpoints, defining schemas, or when you see "API", "endpoint", "REST", "OpenAPI", "sch...
Write functional requirements using FR-XXX format with RFC 2119 keywords (MUST, SHOULD, MAY), success criteria (SC-XXX), and edge case identification. Use when writing requirements, specifications, success crit...
Ensure CLAUDE.md mirrors constitution sections per explicit mapping. Use when synchronizing CLAUDE.md with constitution, validating alignment, or when you see "CLAUDE.md sync", "agent instructions", or need to...
Write enforceable, testable constitution content with proper principle structure, section templates, and RFC 2119 keywords. Use when creating constitutions, writing principles, defining governance, or when you...
Structure implementation tasks using vertical slicing with TDD discipline. Use when creating task mappings, generating implementation tasks, or when you see "vertical slice", "TDD", "test first", "cycle structu...
Review task artifacts (task-mapping, tasks.md) for quality and completeness. Use when reviewing task phase outputs, finding gaps in task planning, or when you see "review mapping", "review tasks", "task quality...
Review planning artifacts (research, data model, contracts) for quality and completeness. Use when reviewing plan phase outputs, finding gaps in design decisions, or when you see "review research", "review data...
Write constitutions for existing codebases using Essential Floor + Emergent Ceiling approach. Use when creating constitutions for brownfield projects, codifying existing patterns, or when you see "brownfield",...
This skill should be used when the user says "brainstorm", "deep analysis", "let's think through", "analyze this with me", or "help me think through". Also used by /humaninloop:specify for input enrichment when...
Evaluate technology alternatives and document decisions in ADR format. Use when making technology choices, comparing options, documenting decisions, or when you see "technology choice", "alternatives", "trade-o...
Write user stories with P1/P2/P3 priorities, Given/When/Then acceptance scenarios, and independent tests. Use when writing user stories, feature specifications, acceptance criteria, or when you see "user story"...
Create evolution roadmaps with prioritized gap cards for brownfield projects. Use when generating gap analysis, identifying improvement priorities, or when you see "roadmap", "gap analysis", "evolution plan", "...
DDD-style entity modeling from requirements including extraction, attributes, relationships, and state machines. Use when extracting entities, defining attributes, modeling relationships, or when you see "entit...
A simple test skill that creates a greeting file
Tests variable interpolation features like {baseDir}. Use for testing path expansion.
A comprehensive skill demonstrating all frontmatter fields. Use for testing complete SKILL.md parsing.
A simple skill for testing basic functionality. Use when you need to test the skillet CLI.
Set up promotional banners with optional countdown timers. Use when creating seasonal sales, limited-time offers, or marketing campaigns that need dismissable banners with i18n support and theme customization.
Use when creating skills, writing SKILL.md files, editing skill definitions, or adding new reusable techniques to ai-coding-config
Use when writing prompts, agent instructions, SKILL.md, commands, system prompts, Task tool prompts, prompt engineering, or LLM-to-LLM content
Use when rough ideas need design before code, requirements are fuzzy, multiple approaches exist, or you need to explore options before implementation
Use when debugging bugs, test failures, unexpected behavior, or needing to find root cause before fixing
Use when current web info needed, verifying APIs still work, checking latest versions, or avoiding outdated implementations
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。