lc-python
File a LeetCode **Python** solution into this repo the way the existing ones are filed — find the problem's real slug, write the Python file in the house layout (problem docstring, V0 with an IDEA block and a time/space line; the standard, readable approach with explanatory comments and no clever syntactic sugar; every other good approach filed as V1, V2, …), smoke-test it against the examples, and insert the README row. Use when asked to "add LC <number>" in Python, to file a problem just solved in a weekly contest, to turn a pasted draft into a committed solution, or to wire an existing solution file into README. For the Java counterpart use lc-java instead. Triggers - "add LC 4038 to Hash_table", "/lc-python 239 slide_window", "add this python solution and update the README", "file yesterday's contest Q1".
lc-site-data
Add a topic to the Study Roadmap (data/roadmap.json) or a question to the Complexity Quiz (data/complexity_quiz.json), satisfying the build-time validators in one pass — a row strictly below every prereq, no cycle and no edge the graph already implies, sheet slugs and LC numbers that exist, no duplicate quiz id, accept always an array, and every answer parseable by site/complexity.js's single-letter identifiers. Use when asked to add a roadmap topic, wire a topic's prerequisites, add a complexity question or drill, or fix a build that a roadmap or quiz entry failed. Triggers - "add monotonic stack to the roadmap", "/lc-site-data quiz for LC 239", "add a complexity question", "the roadmap build is failing".
lc-zh-translate
Translate cheatsheet or FAQ sections into 繁體中文 as a sparse overlay under i18n/zh/, using script/zh.js's sync → todo → write → sync → status loop. Keeps every <!--CODE--> marker in order, takes structure and heading order from the English document, leaves link targets and API names in English, and adapts the entries a sync parked rather than starting them from nothing. Use when asked to translate a cheatsheet or FAQ, to work the translation backlog, to fill in the untranslated sections of a sheet, or to refresh the progress docs. Triggers - "translate dp_loop_order", "/lc-zh-translate heap", "work the zh backlog", "what is still untranslated?", "refresh the translation progress".
markdown-doc-writer
Technical documentation writer specializing in creating clear, well-structured markdown documents for algorithms, system design, interview preparation, and code documentation. Use when writing README files, algorithm explanations, system design docs, or technical guides.
system-architecture
System design and architecture expert for creating scalable distributed systems. Covers system design interviews, architecture patterns, and real-world case studies like Netflix, Twitter, Uber. Use when designing systems, writing architecture docs, or preparing for system design interviews.
first-principles-mentor
|
five-why
|
gidlin-law
吉德林法则顾问，通过六步结构化提问帮用户将模糊困扰转化为清晰问题陈述。触发场景：(1) 用户说"帮我理清思路"、"我很迷茫"、"我说不清楚问题在哪"、"吉德林"，(2) 用户面对复杂问题但表达模糊、情绪和事实交织，(3) 用户在使用其他思维工具（5Why、第一性原理、私董会）之前需要先定义问题。
gif-splitter
GIF动图切分工具，将超过指定帧数的GIF文件自动拆分成多个小文件。适用于微信公众号等平台上传GIF时遇到"帧数超限"的问题。
magazine-layout
|
peers-advisory-group
私董会专家助手，引导用户完成完整的私董会流程。通过四位顶级幕僚（巴菲特、比尔·盖茨、马斯克、乔布斯）的多轮提问和反馈，帮助用户深入剖析问题本质并获得可执行的解决方案。融合百度搜索和百度百科实时数据，让幕僚"带着数据聊"。触发场景：(1) 用户说"开始私董会"、"私董会"、"peers advisory"，(2) 用户需要多角度分析复杂决策问题，(3) 用户希望获得不同商业领袖视角的建议，(4) 用户面临职业、创业、投资等重大决策需要深度咨询。支持自定义幕僚阵容。
sales-ai-assistant
帮助销售人员将业务场景转化为AI提示词并自动生成销售内容（邮件、方案、分析等），无需学习如何编写提示词
six-thinking-hats
|
stock-advisor
|
tvc-ad-film
当用户上传产品图或产品信息，想要一条品牌投放级别的广告短片时加载——典型说法：『给我的产品做一条 TVC / 拍条广告片 / 产品宣传片 / 品牌短片 / 新品上市视频 / 让我的产品看起来像大牌广告』。产出 15-25 秒纯视听语言的品牌叙事短片：先给 6 个策略互异的创意方案供用户挑选，选定后走『分镜脚本 → 逐镜头视听提示词 → 分段生成 → 合成』。不加载的情况：用户要达人口播 / UGC 种草 / 开箱测评 / 带货视频（那是口播形态，本 skill 无人物对镜说话）；用户只要海报、图文、静态物料（本 skill 只产视频）；用户要多集剧情片（本 skill 只做单条广告）。
video-downloader
Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, etc.) using yt-dlp. Use this skill when users provide video URLs and want to download videos, extract audio, or need help with video download issues.
email-best-practices
Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, making emails accessible (alt text, headings, contrast, screen readers), or deciding transactional vs marketing.
recipe-generator
自动生成高品质菜谱的技能。当用户需要创建详细的菜谱、烹饪教程、食谱配方时使用。输入菜品名称后，检索权威来源（米其林、舌尖上的中国等）的制作工艺，生成包含完整准备工作、详细制作步骤、注意事项和专业技巧的菜谱文档，并最终生成传统中式风格的菜谱海报生图提示词。
audit-claude-settings
Use when auditing Claude Code settings and env vars against the latest docs and suggest tailored changes
best-practices
Use when about to choose, configure, or refine a tool, library, config format, API pattern, or project setup, or before proposing a design of your own — research current guidance, pitfalls, and prior art first; already knowing an approach, or assuming no prior art exists, is not an exemption. Also use when the user asks about best practices, gotchas, or recommended patterns
blindspot
Use when the user asks for a blindspot pass or to find their unknown unknowns, or signals unfamiliarity with a domain, tool, or codebase area ("never used X", "first time doing Y", "no idea where to start", "don't know what I don't know") before working there. Maps the areas their request leaves unnamed, purpose and shape before mechanics, shows how people usually answer each and why, and asks which to explore next, so unknown unknowns become known unknowns they can prompt with. Recommendations on a tool already chosen belong to best-practices
commit
Use when making any git commit. Always pass what was wrong before the changes as the argument; when nothing was wrong, pass what the changes do instead — never an invented why.
difference
Compare A vs B, weigh pros and cons of A, B, C, ..., or explain the nuance between sentences — a quick answer from what the model already knows
fuck-over-engineering
Use when the user asks what could be deleted or reduced to simplify a codebase, says "simplify", "over-engineered", or wants a repo-, folder-, or file-wide audit for over-engineering — hunts dead code, reinvented stdlib, needless dependencies, and single-implementation abstractions, reports ranked cuts, applies only the picks. Not a diff review and not a bug hunt
pr
Use when the user explicitly asks to push the current branch and open a PR, rewrite an open PR's body from its commits, or wait for CI and merge it
refactor-agents-md
Use when about to refactor or refine a user-level or project-level AGENTS.md
refactor-claude-md
Use when about to refactor or refine a user-level or project-level CLAUDE.md
refactor-memory
Use when refactoring Claude Code or Codex memories to remove stale or derivable entries, resolve contradictions, promote standing instructions, or reorganize recall. Not for standalone CLAUDE.md, AGENTS.md, or rules cleanup
refactor-skill
Use when about to refactor or refine an existing skill, its SKILL.md or sibling files, from a full restructure down to a one-line wording fix; a change that looks too small to need this skill is not an exemption. Not for creating a skill from scratch or for fixing only its allowed-tools
simple-english
Use when the user explicitly asks for simple English, plain English, or for text a non-native English speaker can read easily — rewrites docs, READMEs, issues, comments, or UI text into plain words and translation-friendly grammar, still native-sounding. Prose the user signs in their own voice goes to write-like-me instead
update-allowed-tools
Use when creating or editing a skill that uses Bash commands, file writes, or external tools and the allowed-tools frontmatter may be incomplete or carry entries that grant nothing
write-like-me
Use before producing any English text the user signs — READMEs, PRs, issues, PR and issue comments, code comments, emails, blog posts, human-facing docs — drafted or rewritten at native fluency in the voice of the skill's author, Vinta Chen. Fires mid-task too: a comment drafted inside another skill's workflow, or text the user will approve before it ships. Not for text addressed to agents unless the user asks
maquina-ui-standards
Build consistent, accessible UIs in Rails using maquina_components. Use this skill when implementing UI for features, creating views, building forms, or reviewing UI specs. Triggers on view creation, UI implementation, form building, layout design, or mentions of maquina_components usage.
ai-assisted-development
Leveraging AI coding assistants and tools to boost development productivity, while maintaining oversight to ensure quality results.
code-readability
Writing clean, understandable, and self-documenting code that is easy to review and maintain over time.
code-refactoring
The practice of restructuring and simplifying code continuously – reducing complexity, improving design, and keeping codebases clean.
data-ml
Competence in data analytics and machine learning, enabling developers to build data-driven features and integrate AI/ML capabilities.
devops-cloud
Skill in automating software deployment pipelines and managing cloud infrastructure for scalable, reliable systems.
documentation
Communicating the intended behavior and context of code through clear documentation and comments, and sharing knowledge with the team.
full-stack-development
Ability to develop both front-end and back-end systems, integrating user interfaces with server logic and databases.
secure-coding
Incorporating security at every step of software development – writing code that defends against vulnerabilities and protects user data.
team-collaboration
Working effectively with others in coding projects – including code reviews, clear communication, and contributing to shared or open-source codebases.
testing-debugging
Ensuring software correctness and reliability by writing automated tests, using quality assurance tools, and systematically debugging issues.
bfl-api
BFL FLUX API integration guide covering endpoints, async polling patterns, rate limiting, error handling, webhooks, and regional endpoints with Python and TypeScript code examples.
flux-3-archival-formats
Use when a FLUX 3 video needs a period or archival look. Covers naming a recording format instead of a mood, per-format artifacts, and templates.
flux-3-audio-dialogue
Use when directing FLUX 3 audio, dialogue, or voiceover. Covers ambience, effects, music, silence, and timing.
flux-3-cinematic-inserts
Use when writing a FLUX 3 text-to-video prompt for a standalone shot. Covers shot craft, reliable concept patterns, camera, continuity, and review.
flux-3-generate
Use when submitting or polling a FLUX 3 video API job. Also covers drafts, downloads, and technical validation.
flux-3-keyframes-continuation
Use when a FLUX 3 video must be built from supplied images or video. Covers keyframes (i2v) and continuation (v2v).
flux-3-product-ads
Use when building a finished product ad from FLUX 3 - shot design, voiceover, action-to-word sync, evidence-gated copy, deterministic assembly, and QC gates that catch clipped audio, floating products, off-model plates, and reports that claim a pass the build did not give.
Page 541 of 1707 · 85303 results
