File Ops
File manipulation and management
omo-ralplan
by Trochez
Consensus planning with Planner/Architect/Critic loop - OpenCode model-agnostic version
lead-research-assistant
by prabha-oss
B2B lead generation and research assistant. Use when asked to find leads, build a prospect list, research companies, find LinkedIn contacts, do lead generation, create an ICP, B2B prospecting, company research, LinkedIn scraping, find decision-makers, build a sales list, lead scoring, or export leads to CSV.
wprdc
by ianpcook
Query Pittsburgh's Western PA Regional Data Center (WPRDC) — 363+ datasets covering property assessments, air quality, 311 requests, jail census, overdose data, permits, violations, and more. Run SQL queries against live tables without downloading. Use when user asks about Pittsburgh/Allegheny County public data, property lookups, civic data, or regional statistics.
artifacts-builder
by arielperez82
Suite of tools for creating elaborate, multi-component HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
blockrun
by automindtechnologie-jpg
Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")
Compile Paper
by midhunxavier
Compile/build documents (LaTeX to PDF or finalize DOCX). Includes integrated page checking and error handling. All build artifacts go to build/ folder.
research-and-synthesis
by htooayelwinict
Fetch and summarize authoritative external sources into actionable guidance using MCP helpers. EXCLUSIVE to researcher agent.
typesense
by manifoldhiker
Search, index, and manage documents in Typesense collections. Use when the user mentions Typesense, asks about search indexing, needs help with search queries, collection schemas, or document import/export for Typesense.
tool-grok-search
by captaindpt
Use the grok_search tool to search X/web/news via xAI Grok Live Search (paid) and return an answer plus citations.
Add Feishu Channel
by stephanz1101
Typing indicators are not supported by the Feishu API
plan-skill
by rnldsalili
Create read-only, inspection-first execution plans and analysis without modifying files or running state-changing commands. Use when the user asks for a plan, a checklist, scoping guidance, a strategy, or wants a proposal before any implementation work.
canvas-design
by ederheisler
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
web-design-guidelines
by yldgio
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
backend-development
by carvalab
PROACTIVELY build backend APIs with Node.js/TypeScript and Go. Use when designing APIs, implementing auth, or building microservices. Applies Clean Architecture, SOLID, DRY, YAGNI, KISS principles.
internal-comms
by zhuxining
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
optimize-md
by jkappers
Optimizes markdown documents for token efficiency, clarity, and LLM consumption. Use when (1) a markdown file needs streamlining for use as LLM context, (2) reducing token count in documentation without losing meaning, (3) converting verbose docs into concise reference material, (4) improving structure and scannability of markdown files, or (5) preparing best-practices or knowledge docs for agent consumption.
code-review-claude
by tomwangowa
Perform native code review (< 30 seconds) using Claude Code's built-in capabilities without external dependencies. Use for rapid validation checks during development. Triggered by 'quick review', 'native review', or 'fast code check'.
managing-agent-secrets
by chrbailey
Prevents AI agents from exposing secrets, API keys, and credentials. Enforces rules for handling .env files, environment variables, and sensitive configuration. Use when working with environment variables, API keys, database credentials, or any sensitive configuration that AI agents might accidentally log, commit, or expose.
parallel-dispatch
by BaxterCooper
Use when facing multiple tasks or failures. Provides decision framework for concurrent vs sequential execution. Invoke before dispatching multiple subagents.
skill-learn
by rxdaozhang
Consolidate actionable lessons after another skill is used and required multiple correction rounds. Use this skill at task closure to extract concrete failures from the current conversation, propose safe incremental updates to the original skill files, show a diff first, and only apply changes after explicit user confirmation. Works for Claude and Codex skill workflows.
council
by rahulgi
Consult an advisory council of three AI personas — Cato (skeptic), Ada (optimist), Marcus (pragmatist) — backed by different frontier LLM agents (Gemini, Claude, Codex). Each persona runs as a separate agent process with full repo context and returns independent feedback. Use when the user says "/council", asks for a second opinion, wants feedback on code changes, needs a premortem, wants to pressure-test a decision, or asks "what do you think about this approach?" Claude may also proactively suggest consulting the council before major architectural decisions, risky deploys, or ambiguous trade-offs (but should ask for user approval first).
plan-enhanced
by OneBoxCream
增强 Plan Mode 的质量。进入规划模式时自动激活，强制执行深度探索、多方案对比、风险评估和验证策略。
carbon-icons
by CoRLab-Tech
Carbon Design System icon usage for React components. MANDATORY when any component includes an icon. Use when implementing UI components that need icons, building atoms/molecules/organisms with icon elements, or adding icons to buttons, inputs, navigation, or any other UI element. Covers icon imports, sizing, color, alignment, touch targets, and the V-Shield Design System icon labeling system.
tmux
by trancong12102
Remote-control tmux sessions for interactive CLIs (python, gdb, etc.) and long-running/background processes. Be very proactive about activating this skill whenever starting background or interactive tasks.