81,896 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Falsification-first investigation workflow: convert every assertion into a labeled falsifiable hypothesis, predict before measuring, run controlled experiments, verify findings adversarially (REFUTE-first), and persist verdicts in a hypothesis ledger so killed ideas are never re-attacked.
Run a bounded audit-remediation-audit loop for an authorized design set or implementation plan, whether produced as plain documents, OpenSpec artifacts, Superpowers plans, or equivalent formats. Use when one invocation should select DESIGN READY or PLAN READY, normalize artifact roles, apply risk-proportionate review…
Autonomous worker for openbridge pools. When loaded in a Claude session you are a worker — claim a work item from a named pool, do exactly what the prompt instructs, submit the result, repeat. Operates fully autonomously: never asks the user for direction, never voluntarily stops, never summarises mid-loop, resumes…
Use when the user wants a UX / UI / interaction-design review or redesign of an app, dashboard, editor, canvas, AI/agentic product, web app, or mobile app — including microinteractions, motion, loading, error recovery, empty states, accessibility, perceived performance, and AI trust/observability. Triggers on "audit…
Develop and automate Electron apps using the electron-dev-bridge. Trigger on: Electron app, desktop app, UI automation, DOM inspection, IPC handler, screenshot, BrowserWindow, webContents, CDP tools, electron-mcp, preload script, contextBridge.
Multi-step git commit workflow. Gathers state, triages sensitive content and secrets, groups changes into logical units, runs the project's test/lint gate, proposes a plan for approval, and commits with conventional messages and no AI attribution. Use when changes need to be committed — when the user says "commit"…
Grilling session that walks the design decision tree Socratically and exports it as a self-contained interactive HTML decision form. Use when the user wants a design interview or existing decisions exported as a reviewable HTML decision form; ordinary plan discussion does not require this export workflow.
Generate bespoke, stack-aware Claude Code agent files for tech teams. Creates specialized AI agent personas (backend, frontend, fullstack, AI/ML, DevOps, QA, security, code reviewer, performance engineer, system architect, tech lead) that Claude Code autonomously picks up from .claude/agents/. Use this skill whenever…
Generates a well-structured, conventional Git commit message from the user's staged changes or a description of what they did. Use when the user says "write a commit message", "format my commit", or "help me commit this". Outputs a ready-to-paste commit message following the Conventional Commits specification.
Outsourcing-first product discovery skill pack. 25 skills across 7 groups (foundation, discovery, evidence, synthesis, scoping, validation, deliverables) — drives a BA / agency / consultant from rough brief to validated proposal, prototype, or go/no-go decision. Skills run independently or via the optional…
★not rated 1 6mo agoA
tokens not measured
originalMIT
Run an autonomous build loop across many goals without per-step prompting (Addy Osmani's "loop engineering"). Use when the user wants to "keep going on your own", "run until done", grind through a backlog unattended, set up a maker/checker workflow, run a self-improving or nightly loop, or keep a durable spine (goals…
MCP server "memory" as configured in blockmandev/ai-memory. Runs D:/(project-folders)/memory/memory-mcp-server.js with node. Needs 2 environment variables to run.
Investigate why a strange piece of code exists before anyone deletes it (Chesterton's fence). Use when the user points at a weird line, hack, magic constant, or workaround and asks why it's there, whether it's still needed, or if it's safe to remove.
Restaurant marketing work you can finish today — review replies in your own voice, the patterns hiding in your reviews, and menu copy built from real ingredients. You paste what you have; every draft comes back for you to read. Nothing goes out in your name without your okay.
★not rated 1 3mo agoA
tokens not measured
originalMIT
A prompt-writing guide that turns a vague request into a clear goal, its fixed limits, and the main obstacle. It then produces a structured prompt that an AI can act on.
Transcribe YouTube videos and podcast episodes in high quality (Whisper via a configurable API endpoint) and distill compact findings with timestamps. Use whenever the user wants a video "watched", summarized, transcribed or analyzed, drops a YouTube or podcast URL together with a question, asks "what does he say…
Interactive wizard to configure Claude Code permission rules. Sets up granular allow/ask permissions so you can work without --dangerously-skip-permissions while keeping safety nets for destructive commands. Use when user says "configure permissions", "set up permissions", "permission settings", or "stop asking me for…
★not rated 1 9mo agoA✓ AI review65 tokens
originalMIT
Production-tested Claude Code skills for professional development workflows — code review, smart commits, PR generation, spec-driven development, and context management.
★not rated 1 9mo agoA
tokens not measured
originalMIT
MCP server for the Socials browser extension — post, engage, search, and manage social media from Claude Code. Runs locally from the @brainrotcreations/socials npm package.
★not rated 1 1mo agoA
tokens not measured
originalMIT
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.
Turn Claude's plan into an editable flowchart in your browser. Approve, reorder, rewrite, add, or delete steps before Claude touches a single file.
★not rated 1 3mo agoA
tokens not measured
originalMIT
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: