81,561 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.
pencil20388-eng/content-topic-judgment
Skill Claude CodeCodex
A decision framework for content operators: given a topic, decide whether to write it, and if so, with what priority. Distilled from real-world brand content operations.
Command Claude Code
A command for searching for jobs each day and tracking the application process. The input also refers to candidate details and companies already contacted.
Skill Claude CodeCodex
Before you execute a drafted plan/spec/design doc, run a multi-agent adversarial cross-review to surface the flaws that cause downstream rework, aggregating "evidenced, cross-family-verified" objections into a verdict. Use when the user asks to "review this plan/spec", "can this approach be executed", "poke holes /…
Skill Claude CodeCodex
Astro security review — render-mode attack surface (SSG/SSR/hybrid), set:html and MDX content collections (XSS + author trust), API routes and middleware (auth, scope), adapter-specific runtime models (Cloudflare/Vercel/Netlify/Node), env-var hygiene (PUBLIC prefix), and Decap CMS pairing (OAuth backend, token…
Skill Claude CodeCodex
This skills instructs the agent how to maintain the knowledge base in the wiki. Use it when you want to ingest documents or query the wiki.
Skill Claude CodeCodex
Curious, non-committal mapping session modeled after how the human mind wanders through unfamiliar territory — building a mental model without reaching for a conclusion. Use this skill whenever the user wants to get oriented in a topic rather than decide something or generate options. Trigger on: "/explore", "help me…
Skill Claude CodeCodex
Provides Django web framework expertise including project structure, models, views, admin, Celery tasks, testing, and Python best practices. Use when generating, analyzing, refactoring, or reviewing Django/Python code.
Skill Claude Code needs its repo
Draft a new post (single image, carousel, or a series) from a brief. Reads the brand profile from memory/brand.md plus theme.css, interviews the user, proposes the best format, then writes posts/ / with post.json, caption files, and slide HTML. Use when the user wants to create content, draft an image post, make a…
Plugin Claude Code
Bundles 39 skills, 1 hook · 2,841 tokens together
Production-tested skills for auditing, improving, shipping, and preserving repo memory with AI coding agents.
Plugin Claude Code
Bundles 4 skills · 120 tokens together
Skills for an AI critic that helps writing and proofreading texts: argument analysis, prose rewriting, plain-text formatting, and subtitle proofreading.
Skill Claude Code
Study a task, ask me clarifying questions, then proceed.
Plugin Claude Code
Bundles 1 skill · 44 tokens together
Get plans right on the first try — the agent interviews you one question at a time and won't accept vague answers.
BechsteinDigital/claude-shiploop
Plugin Claude Code
Bundles 8 skills · 433 tokens together
Autonomous delivery skills for Claude Code — pitch an idea, get an MVP. CEO/PO/DEV/Reviewer agent team with contracts, gates, and evidence rules.
AgentCommander/exploration-map
Skill Claude Code
Review exploration progress. Use to get a tree health report, ingest hypothesis feedback events, decide what to explore next, audit cross-direction lessons, or get a cross-tree review of the current state. Wide read across the whole map, narrow write — proposes and routes; doesn't change tree substance.
Skill Claude Code
A tool that builds a digital model of a person from chat records and descriptions, then uses it to rehearse or preview future conversations.
Skill Claude CodeCodex
A raccoon that digs through your Claude/ChatGPT chat history, pulls out the valuable artifacts, and files them into a local markdown "den" organized by project. Triggers on "/dig", "/den", "/sniff", "/feed", "/wash", "/nap", or natural language like "go dig through my chats", "what piled up", "drag the good stuff into…
Skill Claude CodeCodex
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.
Skill Claude CodeCodex ⚠ unsafe
Autonomously sets up, configures, and manages a Cloudflare Tunnel and its domain on mycrab.space, enabling agents to host public content, manage local services, and deploy personalized web presences. Supports both free auto-generated subdomains and custom paid domains.
Plugin Claude Code
Plugin marketplace listing 1 plugin: rocky.
Skill Claude Code
Intelligent skill orchestrator that automatically finds, creates, executes, and improves skills. When you need to accomplish a task, this skill searches for existing skills (internal, GitHub via MCP, web), creates new skills if none found, executes them, and reviews execution to improve skills based on actual usage.…
Plugin Claude Code
Bundles 70 skills, 48 commands · 3,865 tokens together
Product thinking and PM craft. 516 skills and 48 commands across product strategy, discovery, execution, analytics, growth, experience, conversion, and communication.
akirtok/preflight-security-audit
Plugin Claude Code
Bundles 1 skill, 1 command, 6 agents · 979 tokens together
Comprehensive 360 pre-ship audit: 61 checks across security, reliability, performance, AI/LLM, privacy/compliance, and launch readiness — including live-database, serverless/edge, GraphQL, client-side, and modern-attack (Trojan Source) checks. Reports a 0–100 security score with severity-ranked findings and proposes…
Plugin Claude Code
Bundles 8 skills · 960 tokens together
ANK Skills — small, composable Claude Code skills for an agentic engineering workflow.
Pitchdrive/investor-update-skill
Skill Claude CodeCodex
Draft a monthly or quarterly investor update for your startup — structured like the updates VCs actually enjoy reading. Use when the founder asks to write, prepare, or send an investor update. Pulls KPIs from connected tools when available, asks for numbers when not, tracks commitments between updates, and renders a…
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: