Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 390,947 indexed, measured the same four ways as everything else here.
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
How an AI coding agent should operate inside CodeGrid — the macOS canvas that runs Claude, Codex, Gemini, Cursor, Grok, and shells side by side and lets them collaborate. Use this skill whenever you are running in a CodeGrid pane, or a user asks you to spawn/list/control agents, open a project, drive the workspace, or…
Guard task boundaries and preserve confirmed critical project state across Codex compaction. Use when a user wants topic-switch guidance, write-through critical memory, compact HANDOFF checkpoints, PreCompact and compact-resume hooks, four-layer Markdown memory initialization, or memory workflow auditing.
Finalize completed PR or local checkout work, use force to waive missing PR approvals, or close a local review branch with nocheck. Use when explicitly invoked.
Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtimeevals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval…
Use android-automation-agent to run precise Android UI automation tasks via ADB and LLM vision on the connected Android device. Trigger this skill for ANY request involving controlling, tapping, opening, searching, ordering, booking, or interacting with apps on the user's Android phone. Also trigger for "what's on my…
Python SQL toolkit and Object Relational Mapper (ORM). Use when working with databases in Python, defining models, building queries, managing sessions, or interacting with SQL databases using Python objects.
Top-level conductor skill that routes Solana tasks across four specialized sub-skills: orquestra-researcher (program discovery), orquestra-pda-explorer (account resolution), orquestra-tx-builder (transaction construction), and orquestra-signer (sign + send via @orquestradev/signer-mcp). Use when a user says 'build a…
Applies GAIA's patterns and conventions for writing and editing React components and hooks. Use this skill whenever writing or reviewing React components, hooks, or event handlers, or deciding on component extraction. Also trigger when deciding whether a manual memo or "use no memo" is justified under React Compiler…
Marketing analysis suite with 7 skills and 4 parallel agents — audit paid campaigns, find SEO opportunities, detect churn signals, and generate branded PDF reports. Powered by a tested analysis engine (dsutils.py, 113 functions). Works automatically with Dataslayer MCP or manually with CSV/JSON data.
★not rated 26 7mo agoA
tokens not measured
originalMIT
Achieve flow state safely with Claude Code. Auto-approves routine work, gates risky actions, hard-blocks dangerous patterns. Dual enforcement (skill + hooks), token cap for cost governance, full audit trail. Zero dependencies.
★not rated 26▲
+2 4mo agoA
tokens not measured
originalMIT
MCP server "polar-flow-server" as configured in StuMason/polar-flow-server. Runs in Docker (docker.io/stumason/polar-flow-server:1.6.2). Needs 4 environment variables to run.
★not rated 26
changed 20d agoA
tokens not measured
Review a specific GitHub pull request with gh — fetch the diff, fan out reviewers, consolidate, and optionally post the review. Requires the gh CLI or the GitHub MCP server.
Establish reusable brand facts from an official website, use the shared PostPlus brand and file library, and maintain optional local project context. Keep saved brand facts and research separate.
Grade a video file with your AI agent as the colorist — it looks at frames, diagnoses casts/exposure/saturation, authors a readable ffmpeg grade, previews side-by-side, iterates, renders. Non-destructive. Nine named looks (Golden Hour, Honey, Linen, Super 8, Oat Milk, Espresso, Velvet, Popsicle, Terracotta)…
Create and update AgentCore runtime agents in a DEPLOYED instance of this accelerator. Use whenever the user wants to create a new agent, build an orchestrator/swarm/graph agent, add or remove tools/MCP-servers/skills from an existing agent, change an agent's model or system prompt, or otherwise modify a live runtime…
★not rated 26▲
+1 24d agoA
tokens not measured
MIT-0
Comprehensive pentesting toolkit using Kali Linux Docker container. Provides direct access to 200+ security tools without MCP overhead. Use when conducting security assessments, penetration testing, vulnerability scanning, or security research. Works via direct docker exec commands for maximum efficiency.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
A tool for creating educational comics, including biography and tutorial comics. It supports different visual styles and plans comics as sequences of panels before generating the images.
★not rated 26▲
+1 7mo agoA59 tokens
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: