superpower
claudecodexCore development workflow skills: brainstorming, spec and plan writing, code review, and subagent-driven execution (uses core for TDD and debugging)
12 skills
Every plugin for OpenAI Codex on GitHub — repos with a .codex-plugin/plugin.json or a Codex marketplace. Install with codex plugin marketplace add owner/repo then codex plugin add name@marketplace. Many work in both tools; see Claude Code plugins.
Core development workflow skills: brainstorming, spec and plan writing, code review, and subagent-driven execution (uses core for TDD and debugging)
12 skills
Connect Lusha to Claude to pull verified B2B data, contact data, and company data — including verified emails, direct dials, mobile numbers, and real-time buying signals — straight into your conversation. Lusha is the B2B data layer behind 300M+ verified contacts, used for sales intelligence, prospecting, data enrichment, and lead enrichment across sales, marketing, and RevOps workflows. Backed by GDPR, CCPA, SOC 2 Type II, and ISO 27701 compliance. Perfect for building prospect lists, researching accounts before a call, qualifying inbound leads, and natural language prospecting inside Claude. Use Lusha to: - Find contacts and decision makers by role, company, industry, or seniority — "Find 10 VPs of RevOps at Series B SaaS companies in NYC" - Pull verified emails, direct dials, and mobile numbers with 98% email deliverability and 85% phone accuracy — "Get the verified work email and mobile number for the Head of Marketing at Notion" - Enrich CRM records and inbound leads with firmographics, technographics, headcount, revenue, and buying signals — "Enrich these 25 webinar signup domains with industry, tech stack, and recent hiring signals" - Track signals across target accounts — funding rounds, leadership hires, hiring surges, and tech stack changes — "Show me the buying signals from the last 90 days for these 15 accounts" - Find lookalike accounts based on your closed-won customers — "Find 20 companies that look like these 5 customers"
11 skills · 1 MCP server
Skills for r2sql AI connector tool
11 skills
Skill Heaven is live. Summon one skill into a session with nothing installed: manual /summon at every rung, a clean-room launcher floor (/skill-zero), converge and explore bands over one relevance-ranked summon (/skill-heaven, /skill-hell), and the crown rung (/skill-ultra), from a Skill Tree or a flat GitHub repository. Its output is reference data, never standing authority; what each rung means in behaviour is still provisional.
5 skills · 5 commands · 1 MCP server
Connect Claude Code to the agentnetwork agent network: one global user, one auto-described per-project agent, sync/async messaging with peers across fleets, plus private organizations and rooms (persistent or ephemeral) for team-scoped Q&A. Ships /agentnetwork:setup, /agentnetwork:listen, /agentnetwork:stop-listening, /agentnetwork:rooms, /agentnetwork:slack-setup and /agentnetwork:local-test.
10 skills · hooks
Review-centered workflows for rare-disease constitutional and germline genetic counseling.
10 skills · 1 agent
Reach your money goals with Claude: goals and a budget from your real accounts, and a review that raises what's worth talking through.
10 skills · 1 MCP server
Portable Chinese brand-marketing workflows for briefs, research, strategy, proposals, content, and execution.
11 skills
Agent self-improvement + retrieval. Captures learnings via colon-namespaced sub-skills (reflect, reflect:consolidate, reflect:ingest, reflect:recall, reflect:status) and auto-injects relevant prior learnings via SessionStart/UserPromptSubmit hooks. PostToolUse arms low-cost mini-learning capture; Stop enqueues short-session reflection. v4 cost rearchitecture: a $0 skip-gate + cascade slice the drain so it runs on Sonnet under hard caps (8 turns / 180s / 2M-token poison), with cost observability (reflect cost) and a weekly Opus synthesis pass. Philosophy: Correct once, never again; recall everything next time.
10 skills · hooks
Access Agiflow tools, skills, and MCP-backed workflows directly from Claude Code.
10 skills · 1 MCP server
Eclipse corona processing skills: first steps with your own photos (English); calibration and stacking, post-processing, artefact repair (Catalan); structure images, unrolled views and coronal motion with the ael package, and checks against coronagraphs (K-Cor, SOHO/LASCO, SDO/AIA) in structure and in mean solar brightness (English); a whole case to an editable master the photographer accepts, contributed by Raúl Hussein (English).
11 skills
科研基建插件:哲学级过程 skill + 常驻原则页。
10 skills · hooks
Research foundation plugin: philosophy-level process skills and permanent principles in English.
10 skills · hooks
Personal AI Agents harness: skills and subagents
6 skills · 5 agents
Personal collection of agent skills for token efficiency, Python dependency audits, comment writing, and local Nextflow modules
10 skills
Build data products on Databricks with Declarative Automation Bundles and Lakeflow Spark Declarative Pipelines, integrated with Entropy Data.
9 skills · hooks
Kismet for Operators — the authenticated workspace for running your Kismet business from your AI: curate catalogs, analyze guest journeys, run the guest CRM (search guests, audiences, notes), generate demand, run Insiders email, manage ads and audiences, configure automations, and produce the client-facing Booking Channel & Group Performance report.
9 skills · 1 MCP server
Persistent SQLite memory and retrieval tools for Claude Code
9 skills · 1 MCP server
Find and track apps, understand what users complain about, and find keyword opportunities — analyst workflows over the AppFollow MCP, using your own OAuth-authenticated session.
5 skills · 4 commands · 1 MCP server
Core Agent Steroids skills and workflow helpers, including Skill inventory auditing
9 skills · 1 command
33 MCP tools (24 atomic browser/mobile primitives + 9 composite workflows) + 9 user-invocable skills. Works standalone today; pair with the `rolepod` parent plugin (detected via the marker file `<git-root>/.rolepod/parent-active`) and uiproof becomes the verify-phase UI provider — evidence routes to `<git-root>/.rolepod/evidence/` with `manifest.json` per Extension Protocol v1. Replaces chrome-devtools-mcp and playwright-mcp for UI testing. Web production-ready via Playwright; mobile (iOS/Android) via Appium scaffolded — see `rolepod-uiproof doctor` for readiness.
9 skills · 1 MCP server
Image-first visual content design, generation, review, and delivery.
10 skills
Evidence-based community SOPs with safe AI handoffs and verified execution.
10 skills
Codex-native research architecture for empirical social science, with default-installed workflow skills, critic gates, and explicit runtime activation checks.
10 skills
BugBug test automation workflows for AI agents
9 skills · 1 MCP server
Search the academic literature, save papers to your Paperpile library, read and annotate their full text, and keep the library organised.
9 skills · 1 MCP server
Subagents that take one work ticket to a reviewed pull request: verified spec, build, review before push, and a browser check for page changes.
2 skills · 2 commands · 6 agents
Points to all AI skill catalog entities in the rh-virt agentic pack for Red Hat OpenShift Virtualization management.
10 skills
Ask Gina is a research assistant for crypto, prediction markets, perpetuals, and equities. Use it to fetch real-time prices and historical data for tokens, Hyperliquid markets, and Polymarket prediction markets, and to analyze your Gina wallet, positions, and accounts. Gina cannot place trades or transfer assets inside Claude.
4 skills · 4 commands · 1 MCP server
Official Kestral plugins for Claude Code, Codex CLI, etc.
9 skills