Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 272,453 indexed, measured the same four ways as everything else here.
When the user wants to create or update their product marketing context document. Also use when the user mentions "product context", "marketing context", "positioning", "messaging foundation", "who is my audience", "brand voice", "ideal customer profile", or "product marketing." This skill creates the foundational…
Create new agent skills for the HoloViz ecosystem. Use when adding a skill to this repository — covers repo conventions, directory layout, routing skills, the docs pipeline, and the eval system.
Decompose initiative Features into detailed User Stories, one folder per HU (body + assets), keep a table of contents in the Feature spec, flag HUs that need enrichment (architect and/or designer), and emit a lean impact-map.yaml.
Signs every Claude Code tool call with an offline-verifiable Ed25519 receipt. Lets you audit exactly what Claude did and when, without trusting any server.
Guided intake pipeline for learning materials — transcripts, course lessons, Drive folders, PDFs. ALWAYS trigger on /ingest-material. Also triggers when you paste a transcript, drop a file path, share a Google Drive link to course content, or say anything like "ingest this", "add this to my vault", "I just watched a…
When the user wants to audit, review, or diagnose SEO issues on their site. Also use when the user mentions "SEO audit," "technical SEO," "why am I not ranking," "SEO issues," "on-page SEO," "meta tags review," "SEO health check," "my traffic dropped," "lost rankings," "not showing up in Google," "site isn't ranking,"…
Create professional CSS animations, transitions, micro-interactions, and complex motion design. Use when adding animations, hover effects, loading states, page transitions, scroll animations, or any motion design work.
A skill that downloads long posts from Twitter, now called X, and converts them into neatly formatted Markdown files. Markdown is plain text with simple formatting marks, and the files are saved locally for sharing.
Use this skill when the user wants to run a full structured AI red team audit, generate a red team report, compile findings from multiple techniques across multiple models, produce a markdown or JSON report of jailbreak test results, score model resilience, summarize which techniques succeeded or failed, or wrap up an…
A software security review based on South Korea’s KISA 2021 security weakness guide. It checks 69 design and implementation categories and labels each one as passed, vulnerable, needing review, or not applicable.
Decompose complex work into a Beads-backed execution graph with generated WORKGRAPH.md views, then run an NTM-style swarm by ready frontier with no write overlap. Use before parallel execution for large-ish, UI-facing, multi-file, multi-domain, naturally parallel, naturally orchestrated, subgoal-oriented, or…
Quickly audit the current project for obvious malicious or untrustworthy behavior so the user can decide whether it is safe to run, build, or install. This is a triage pass, not a full security review — aim for a dozen targeted checks, not an exhaustive audit.
Analyze competitors with feature comparison matrices, positioning analysis, and strategic implications. Use when researching a competitor, comparing product capabilities, assessing competitive positioning, or preparing a competitive brief for product strategy.
Analyze code for code smells from the Fowler / Beck / Kerievsky catalog (including the Industrial Logic Smells-to-Refactorings reference), then refactor them away one by one using named refactorings from Fowler's Refactoring and Kerievsky's Refactoring to Patterns. Each smell is fixed in isolation with a…
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
IRS Publication reference for business expenses, home office, travel/car, investments, retirement plans, HSAs, IRAs, and asset basis. Use when calculating deductions, determining eligibility, looking up tax rules, or answering specific tax questions about deductibility, limits, or requirements.
Analyzes newly-added or significantly-modified types in a pull request for invariant strength, encapsulation, and enforcement. Produces 1-10 ratings on encapsulation/expression/usefulness/enforcement with concrete improvement suggestions. Use when reviewing PRs that introduce or substantially change types, classes…
Upload CSV lead lists (AI Ark, Prospeo, Store Leads) to Neon Postgres, clean company names, enrich sales reps via AI Ark API, scrape company websites, AI-powered website analysis (competitors, ICP, descriptions, pricing, categorization) via Workers AI, custom enrichment, ICP scoring. Triggers on: upload leads, lead…
Discovers home network devices via nmap, SSH, and DNS. Creates machine-readable inventory with topology diagrams. USE WHEN user says "scan home network", "discover home network", "map home network", "home network inventory", "homenet scan", "homenet discovery", "network topology", or scanning/mapping home network…
Technical Debt Scanner — Scan any codebase for TODOs, FIXMEs, duplicated logic, unused exports, oversized files, circular dependencies, and code smells. Generates a prioritized debt report with estimated effort. Use when the user asks to: (1) audit technical debt, (2) find TODOs or FIXMEs, (3) detect code duplication…
Scan project dependencies for known CVEs, outdated packages, and supply chain risks. Use when the user asks to audit dependencies, check for vulnerabilities, scan packages, run a security check on nodemodules, or wants to know if their dependencies are safe. Supports npm, pip, cargo, go mod, maven, gem, and nuget.
Instructions for starting a separate Claude Code session in another terminal workspace or development environment. Claude Code is an AI coding assistant, and the instructions use a server that handles its startup confirmation.
★not rated 5 9d agoA0 tokens
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: