Loading...
Loading...
Found 10,556 Skills
Apply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", or "technical debt". Covers smell-driven refactoring, safe transformation sequences, and testing guards. For code quality foundations, see clean-code. For managing complexity, see software-design-philosophy.
Add a new sound effect to @remotion/sfx
Breaks work into bite-sized tasks before coding. Activates when a multi-step task needs planning — creates tasks small enough for a junior developer to follow (2-5 minutes each), with exact file paths, complete implementation details, and verification steps. References Linear issue context and project-specific test commands from CLAUDE.md.
Collaborative problem-solving protocols: write technical specifications (spec, or alspec), create implementation plans (plan, or alplan), or use Align-and-Do Protocol (AAD). Also generates PR/MR descriptions (aldescription).
Claude-Codex-Gemini tri-model orchestration via ask-codex + ask-gemini, then Claude synthesizes results
Multi-platform social media publishing automation - schedule, post, and track content across TikTok, Instagram, YouTube, LinkedIn, and more
Write bold, minimal slide content with punchy headlines, concise body text, and impactful bullet points. Use when writing slides, asking "write content for...", "draft slides about...", or "help me phrase this slide...". Transforms ideas into presentation-ready copy designed for speaking to, not reading from.
This skill should be used when the user requests phrases such as "list teams", "team list", "view team configurations", or "what teams are available". It scans the .team-profiles/ directory and displays summary information of all available configurations.
Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol. TRIGGER when: user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that needs multiple sessions. DO NOT TRIGGER when: task is completable in a single PR or fewer than 3 tool calls, or user says "just do it".
Clarify ambiguous or conflicting requests by researching first, then asking only judgment calls. Use when prompts say "$grill-me"/"grill me", ask hard questions, request relentless interrogation, pressure-test assumptions, clarify scope/requirements, define success criteria, or request system-design/optimization decisions before implementation; stop before implementation.
Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Supports push-only (webhook) and interactive (bidirectional) modes. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.
Use this skill when performing exploratory data analysis, statistical testing, data visualization, or building predictive models. Triggers on EDA, pandas, matplotlib, seaborn, hypothesis testing, A/B test analysis, correlation, regression, feature engineering, and any task requiring data analysis or statistical inference.