发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
speckit-git-initialize
Initialize a Git repository with an initial commit
docker-commands
ICJC Docker service management and Make commands. Use when: (1) requests related to docker, make, containers, services, restarts, or logs; (2) restarting backend, frontend, or agents; (3) you need to build, access containers, check logs, or verify service status.
aad-init
Use this when the user wants to set up Angular Admin Design in a project for the first time, or runs /angular-admin-design:aad-init explicitly. Auto-detects the Angular project's profile (NgRx layout, shared modules path, domain prefixes, i18n flow) and writes .claude/angular-admin-design.json.
dotnet-build
.NET build configuration and error handling. Use when building projects, diagnosing build errors, or configuring build options.
static-analysis
.NET static analysis and code quality tools. Use when configuring analyzers, fixing warnings, or enforcing code standards.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: the user asks "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or otherwise explicitly requests enhanced prompt quality. Also triggers on equivalent Chinese queries (e.g., the user expresses the same requests in Chinese). DO NOT TRIGGER when: the user wants the task executed directly or says "just do it". DO NOT TRIGGER when the user asks to "optimize code", "optimize performance", or similar requests — those are refactoring/performance tasks, not prompt optimization.
refactor-code
Intelligently refactor and improve code quality with incremental, test-backed changes. Use when the user asks to "refactor", "clean up code", "improve code quality", "restructure", or "simplify this code".
wrong
Reset and re-evaluate when current approach isn't working. Use when user says "wrong", "this isn't working", "wrong approach", "start over", "try again", "bad direction", or when the current solution path has hit a dead end and needs a fresh perspective.
compliance
Ensure regulatory compliance. Use when implementing GDPR, HIPAA, PCI-DSS, or SOC 2 requirements. Covers compliance frameworks and controls.
Audit Dataset Access
<!-- Copyright (C) 2017-2026 Dremio Corporation
Cross-Platform File Operations
Handle file operations correctly across macOS, Windows, and Linux
cardiology-content-repurposer
Transform long-form cardiology content (YouTube transcripts, newsletters, PDFs, knowledge bases) into high-quality thought leadership content across multiple formats. Use when the user wants to repurpose medical/cardiology content into: (1) Short newspaper-style articles (Inshorts style), (2) Atomic essays, (3) Tweets, (4) Twitter threads, or (5) Medium-style blogs. Maintains an authentic interventional cardiologist voice with clinical authority, uses the 4A framework, targets specific patient archetypes, and leverages PubMed for evidence-based citations when needed.
x-post-creator-skill
Create scientifically rigorous, engaging X (Twitter) posts for cardiology thought leadership. Use when generating social media content for a cardiologist targeting patients, caregivers, health optimizers, people with lifestyle diseases (hypertension, diabetes, high cholesterol), and sedentary individuals seeking prevention. Produces batches of 10 unique posts using strategic combinations of 300+ cardiology seed ideas, 215+ modifiers, 5 audience archetypes, awareness levels, and proven copywriting frameworks (4A, Magical Multipliers). Features iterative self-improvement through accumulated feedback.
research-statement
Write, review, and revise academic Research Statements / Research Visions / Research Plans / 5-Year Plans for faculty, postdoc, fellowship, and promotion applications across disciplines and regions. Covers Mission/Strategy/Evidence/Story, US-school guidance from Cornell, CMU, MIT, Caltech, Penn, Yale, Harvard, UConn, Notre Dame, Delaware, Berkeley, length tiers, openings, past-work theming, fundable future lines, department fit, funding vectors, rubric scoring, red flags, and examples. Use when asked to write, draft, outline, edit, critique, score, red-team, or improve any research statement, research vision, research plan, future research statement, or research pitch.
deprecation-and-migration
Use when removing old APIs, migrating to new patterns, or cleaning up legacy code — treats code as liability and follows a structured removal process
heroku-managed-inference
Use Heroku Managed Inference and Agents with the current Heroku AI workflow. Use when the agent needs to install or inspect the Heroku AI CLI plugin, provision Heroku inference access on the current standard plan, review the latest Managed Inference model catalog, attach model resources, make test inference calls, or review Heroku-managed AI model operations.
clean-code
Applies principles from Robert C. Martin's 'Clean Code'. Use this skill when writing, reviewing, or refactoring code to ensure high quality, readability, and maintainability. Covers naming, functio...
clawdbot-update-plus
Full backup, update, and restore for Clawdbot - config, workspace, and skills with auto-rollback
agent-money-tracker
Intelligent budget tracking and financial management library for AI agents - expense tracking, income management, budgets, savings goals, and LLM-powered insights
ranked-gym
Gamify your gym sessions with XP, levels, achievements, and workout streaks
create-plan
Creates comprehensive implementation plans through codebase exploration, research, and iterative clarification. Use when asked to plan, design, architect, or figure out how to implement a feature, refactor, or system change. Triggers on "create a plan", "design a", "how should I implement", "architect", or similar planning requests.
linkedin-outreach
LinkedIn prospecting automation using Apify scrapers, ICP-based filtering, connection sequences, and CRM sync. Use when the user says 'find prospects on LinkedIn', 'LinkedIn outreach', 'scrape LinkedIn', 'connection request', or needs to build a LinkedIn prospecting pipeline.