analyst
14041Agent Claude Code
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 375,374 indexed, measured the same four ways as everything else here.
Agent Claude Code
You must fully embody this agent's persona and follow all activation instructions exactly as specified. NEVER break character until given an exit command.
Skill Claude CodeCodex
Use before answering when past context would help — pulls relevant memories from the local brain, tunnelled to the current project.
Command Claude Code
A command for checking the current code against a mobile-adaptation checklist. Mobile adaptation means making a website work well on small screens.
dvasyliev/ai-dev-tools-getting-started
Skill Claude CodeCodex
Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance.
Plugin Claude Code
Bundles 1 skill, 1 hook · 67 tokens together
Clone your customers from real call transcripts, then run them as a standing focus group. Discovers customer archetypes, builds composite personas, and convenes them to react to any offer, hook, price, page, or email before it goes live.
Antropocosmist/triz-engineering-solver
Skill Claude CodeCodex
Apply Altshuller's TRIZ (Theory of Inventive Problem Solving) to resolve engineering contradictions and produce inventive concepts instead of compromise solutions. TRIGGER when the user describes a technical trade-off ("improving X makes Y worse"), a physical contradiction (one element must have opposite properties)…
MCP server Claude CodeCodexCursor +2
A portable, long-term agentic memory MCP server — a thumb drive for your AI context. Runs locally from the @rsl-innovation/mem-port npm package.
Skill Claude CodeCodex
A tool that turns legal analysis into a structured risk report with four visual views: a radar chart, risk matrix, impact path diagram, and decision tree. These show risks, their likelihood and severity, how they spread, and possible decisions.
Skill Claude CodeCodex
A set of formatting and quality rules for an AI assistant drafting the main text of a civil appeal for the plaintiff's lawyer, used only during the appeal-drafting stage.
Skill Claude CodeCodex
Hosted-gateway LLM router — save 87% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 82 models from OpenAI, Anthropic, Google, DeepSeek, xAI, NVIDIA, and more. 6 free models included. Also exposes realtime market data (global…
Skill Claude CodeCodex
Export the current Gephi map as a clean PNG, labeled PNG, and SVG after checking that it is laid out, styled, and visually valid. Use for publication-ready map export and caption handoff.
DiegoFleitas/letterboxd-movie-justwatch
MCP server Claude CodeCodexCursor +2
One of 3 in .mcp.json
MCP server "sonarqube", hosted remotely at api.sonarcloud.io, as configured in DiegoFleitas/letterboxd-movie-justwatch.
Skill Claude CodeCodex
Use web-ai-sdk documentation and package references to build with the Web AI surface.
Plugin Claude Code
Bundles 1 skill · 33 tokens together
Claude Code running in an isolated Docker container, driven via interactive shell, one-shot exec, an HTTP REST API, an OpenAI-compatible chat/completions adapter, an MCP server, a Telegram bot, and a YAML cron scheduler.
Plugin Claude Code
Bundles 1 skill, 4 commands, 3 hooks · 105 tokens together
Enforce architectural decisions and engineering standards before Claude Code writes changes.
MCP server Claude CodeCodexCursor +2
MCP server "openapi.com", hosted remotely at 127.0.0.1, as configured in openapi/mcp-server.
Plugin Claude Code
Bundles 2 skills · 226 tokens together
Learn Anthropic products hands-on from the Claude Academy curriculum, and review your Claude Code sessions against Academy best practices.
MCP server Claude CodeCodexCursor +2
MCP server "transcriptor-mcp" as configured in samson-art/transcriptor-mcp. Runs in Docker (docker.io/artsamsonov/transcriptor-mcp:1.5.1).
Plugin Claude Code
Bundles 1 skill · 39 tokens together
Brief prose. Short common words. Trust context. State what matters. Omit what reader can infer.
Skill Claude CodeCodex
Recalibrate dash-p's recognition profile when a new Claude Code version ships. Drives the new TUI through a diverse SCENARIO BATTERY (short/long input, long output, code, markdown, tables, unicode, tool use), cross-checks every result against the session JSONL (ground truth), then fixes the profile/recognizer and…
Skill Claude CodeCodex
Scans a repo's GitHub Actions workflows for the ten critical CI/CD attack vectors — template injection, fork code executed with privileges (pwn requests), cache poisoning, impostor action SHAs, secrets dumps, GITHUBENV hijack, write-token untrusted triggers, credentials in caches/artifacts, unverified remote code…
Skill Claude CodeCodex
Gate dependency installs (npm/pip/cargo/go/gem/maven/nuget) with OSV-backed advisory checks, approved-spec ledger, and post-install reorg rollback. Run safedeps check @ before any install command.
Plugin Claude Code
Bundles 1 skill · 66 tokens together
Fetch the latest arXiv papers and generate an on-demand digest. The agent judges relevance itself — no API keys needed.
Plugin Claude Code
Bundles 9 commands, 7 agents, 3 hooks, 1 MCP server · 602 tokens together
Lifecycle kanban for Claude Code projects (PRD → architecture → plan → tasks → walkthroughs).
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: