github-cli
使用 GitHub CLI 与 GitHub 资源交互；适用于 repo、issue、PR、comment、release、workflow 等查看、更新或创建场景。创建任何 GitHub Issue 时，统一使用本 skill 的 github_issue.py，保留模板 labels/assignees 并在创建后回读验证。
gitlab-cli
使用 GitLab CLI（glab）与 GitLab 资源交互；适用于 project、issue、MR、comment、wiki 等查看、更新或创建场景，含自建实例。
golang-lo
Go >= 1.18 项目中希望用 samber/lo（Lodash 风格泛型库）简化集合/映射/字符串、错误处理、重试/节流/防抖、通道并发或指针空值场景时使用。
arkts-syntax-assistant
|-
brainstorming
Collaborative refinement of rough ideas into clear requirements/designs through systematic questioning. Use when requirements are vague or exploring architectural options.
codebase-design
Shared vocabulary for designing deep modules — module, interface, depth, seam, adapter. Use when designing or improving a module's interface, deciding where a seam goes, hunting for deepening opportunities, or making code more testable.
completion-validation
Use when about to claim work is complete, fixed, passing, or ready to commit/PR — requires running verification commands and reading fresh output before any success claim. Evidence before assertions, always.
domain-modeling
Build and sharpen a project's domain model — challenge terms, resolve them into a glossary, and record hard-to-reverse decisions as ADRs. Use when codebase terminology is fuzzy or contested, when writing or editing a glossary, or when recording an architectural decision.
explain-in
Rewrite engineer-to-engineer content for leadership audiences — VPs, directors, PMs, release managers. Shapes for the channel: JIRA comment, Slack post, standup note, email, or meeting talking-points. Use after post-mortem or any technical update that needs to flow up the org.
grill-with-docs
Grilling that leaves a paper trail — runs the grilling interview while capturing resolved terminology and hard-to-reverse decisions into docx/ as they settle.
grilling
Relentless round-based interview that stress-tests a plan before building. Maps the plan as a design tree and works it in rounds, asking every unblocked question at once with a recommended answer for each, until nothing is left silently assumed.
handoff
Compact the current conversation into a handoff document so a fresh agent can pick up the work.
investigate
Research a question against high-trust primary sources and capture the findings as a cited Markdown file. Use when a topic needs researching, docs or API facts gathered, or reading legwork delegated to a background agent.
more-creativity
Use when generating ideas, hypotheses or options — "give me ideas", "what are the possibilities", "I'm stuck", "what else could cause X", "hypotheses for why X". Forces divergence before convergence — suppresses evaluation while generating, requires a cross-domain technique, and gates every survivor on non-obviousness. Not for factual questions, live incidents, or narrowing options into a design — `brainstorming` owns that.
post-mortem
Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Use after a debug session lands a validated fix, before closing the bug.
prototype
Build a throwaway prototype to answer a design question. Use when sanity-checking whether a state model or logic feels right, or exploring what a UI should look like, before committing the decision to real code.
scrutinize
Outsider-perspective deep review of a plan, PR, design doc, or code change — questions intent first (should this exist?), then traces the actual code path end-to-end to verify the change does what it claims. Use for serious PR reviews, design audits, or second opinions. Lighter pre-commit checks use `review` instead.
spawn-agents
Use when facing 2+ independent problems (different test files, unrelated bugs, separate subsystems) that can be investigated in parallel without shared state — covers the dispatch decision, the actual Claude Code parallelism mechanism, prompt construction, and integration after agents return
spec-driven-implementation
Execute spec-driven implementation — auto-detects Quick (plan.md) or Full (tasks.md) mode and runs step-by-step with verification. Use when implementing a planned feature or running TDD tasks.
spec-driven-planning
Plan new features using spec-driven workflow — auto-picks Quick (single plan.md) or Full (3-file EARS spec) mode. Use when creating features, writing requirements, or designing architecture.
spec-review
Review feature spec files with 3 focused agents — spec quality (business+correctness+ambiguity), completeness (missing scenarios+safety+testability), and buildability (compatibility+blockers+traceability). Sequential by default.
systematic-debug
Systematic debugging framework — opens every session by reciting the 4-mantra block (reproduce, trace the fail path, falsify the hypothesis, cross-reference breadcrumbs), then applies multi-layer investigation. Use when diagnosing bugs, flaky tests, unknown failures, or cross-component issues.
test-driven-development
Strict RED-GREEN-REFACTOR enforcement with no exceptions. Use when implementing features or fixing bugs. No production code without a failing test first.
using-kisune
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
analyze
Technical analysis with indicators (RSI, MACD, MA), support/resistance, multi-timeframe trends, and sentiment. Use when analyzing markets or interpreting charts.
pattern
Chart pattern identification — head and shoulders, double tops, triangles, flags. Documents pattern library with entry/exit criteria.
research
Systematic trading strategy research — edge hypothesis, statistical validation, and strategy documentation (entry, exit, risk management).
translate
Convert strategy docs to Python (pandas, framework-agnostic) and TradingView Pine Script v5. Use when translating strategies to code for backtesting.
git-workflow
Smart git operations — commit messages, branch management, PR creation with summaries. Use for any git workflow.
review
25-point code quality checklist covering structure, errors, security, performance, and testing. Use before commits or when reviewing code.
security-review
OWASP Top 10 vulnerability detection. Use PROACTIVELY for code handling user input, auth, APIs, payments, or sensitive data.
skill-maker
Create and edit Claude Code skills with TDD methodology. Use when creating or editing skills. Test with subagents before deployment, iterate until bulletproof.
character-profile
基于故事文本分析人物特征，生成详细的人物小传。适用于深度理解故事人物设定、为演员塑造角色提供参考、为剧本创作建立人物档案
character-relationships
分析故事人物关系，识别类型、特点及发展变化。适用于深度理解人物关系网络、分析关系对情节推动作用、为情节设计提供关系支撑
novel-evaluator
严格细致判断与评分故事文本，从市场潜力、创新属性、内容亮点维度分析质量。适用于小说初筛选、多维度评估打分
novel-summarizer
阅读理解小说文本，总结成流畅的故事大纲。适用于小说初筛选、生成500-800字故事大纲
novel-truncator
智能截断文本，保持内容完整性。适用于小说文本预处理、确保文本不超过指定长度限制
score-analyzer
分析多轮评估结果评分数据，统计各项指标，计算评级等级。适用于分析评分趋势、计算S/A/B评级
output-formatter
整合智能体输出结果为结构化最终输出，支持多种格式。适用于整合分析报告、生成结构化报告
result-integrator
整合多情点分析结果为综合报告，通过去重、分类、排序、总结生成高质量分析。适用于整合多分析源、生成统一报告
series-analyzer
分析已播剧集，包括信息获取、拉片分析、五元素分析及联网搜索。适用于深度分析剧集创作技法、学习情节设计
detailed-plot-analyzer
基于大情节点，深入分析并生成详细情节点描述及情节发展说明。适用于细化故事大纲、指导剧本写作、分析情节内在逻辑
drama-analyzer
分析故事文本，提炼主要情节点并分析戏剧功能。适用于分析小说、剧本大纲、故事梗概等文本，识别关键转折点和情感节点
plot-keypoints
梳理故事主线，提炼并按发展阶段排列主要情节点。适用于快速掌握故事结构、制作大纲及剧本改编结构梳理
plot-points-analyzer
分析故事情节点，识别关键情节与转折点。适用于深度分析情节结构、评估情节发展有效性
story-five-elements
全面分析故事五元素：题材类型、故事梗概、人物小传、人物关系、大情节点。适用于深度分析故事、剧本改编准备、故事开发文档制作
story-outliner
阅读理解故事文本，总结人物、关系、情节，整理成流畅大纲。适用于快速了解故事核心、为剧本创作提供大纲基础
story-summarizer
基于故事文本提炼主要情节与要点，生成完整故事梗概。适用于快速了解故事内容、剧本改编、项目推介
story-type-analyzer
分析故事题材类型，提炼创意元素与故事特色。适用于识别题材定位、提炼创意、分析市场受众
file-reference
处理和分析用户上传的文件引用，提取关键信息并提供应用建议。适用于解析@符号引用、自然语言引用、提取短剧策划相关信息
Page 619 of 1646 · 82291 results