All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 419,197 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
Skill Claude Code needs its repo
Verify UI implementation against Stitch design via a token audit (HTML ↔ Code, with X-component default-render checks) and an X-components compliance check.
Skill Codex
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
j1ngg/tech-marketing-framework
Agent Claude Code
Analyzes paid ad performance data and produces actionable audit reports with health scoring. Use when you have campaign metrics to review.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "fal-ai", hosted remotely at mcp.fal.ai, as configured in Top3d-ai/world-builder.
Cursor rule Cursor
Cursor rule "google-style-guide" from runpod/docs, covering google developer style guide for technical documentation, document structure, lists and formatting, language and tone and links and references.
Skill Claude CodeCodex
Structured 5-step workflow for producing long-form research reports that satisfy rubric-based evaluation across 6 axes (Explicit, Implicit, Synthesis, Communication, Instruction Following, References).
fuwenhao12/academic-ref-inserter
Skill Claude CodeCodex needs its repo
Insert, format, and cross-reference academic citations in Word (.docx) documents. Supports GB/T 7714-2015 (Chinese), IEEE, and APA 7th.
Skill Claude CodeCodex
WORKFLOW SKILL — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE…
Skill Claude CodeCodex
Use when optimizing or iterating on prompts for a student LLM — a prompt produces wrong-shaped output, hallucinations, refusals, poor instruction-following, or when migrating a prompt between models with different quirks. Also use when hardening a prompt against indirect prompt injection from untrusted external data.
Skill Claude Code needs its repo
Add, modify, or delete a skill or plugin in this repo — frontmatter shape, the seven metadata files a plugin touches, and the create/delete checklists. Use when creating a new skill or plugin, removing one, or asking which files a plugin change must update.
Plugin Claude Code
Bundles 2 skills · 104 tokens together
Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.
norman-finance/norman-mcp-server
Plugin Claude Code
Bundles 20 skills, 2 MCP servers · 1,088 tokens together
AI-powered bookkeeping, accounting, invoicing, and tax workflows for European businesses through MCP.
JJenglert1/gtm-engineer-starter-kit
Skill Claude CodeCodex
Generates a personalized 3-email outreach sequence for a prospect. Each email is short, human, and built around a specific signal — not a generic pitch.
Skill Claude CodeCodex
Redact or remove PII (SSNs, EINs, names, addresses, phones, emails, account numbers) from documents while keeping the file in its original format and style. Use when asked to redact, mask, anonymize, scrub, sanitize, or de-identify a document.
Skill Claude CodeCodex
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
whoamihappyhacking/lazycat-skills
Skill Claude CodeCodex
A guide to advanced networking for Lazycat MicroServer apps. It covers routing, multiple domains, TCP and UDP forwarding, cross-origin access, and complex proxy rules.
Cursor rule Cursor
Archcore knowledge base context — document types, MCP tools, and conventions for working with .archcore/ documents.
Skill Claude CodeCodex
Help the user design, write, compile, and install a Silo extension from a natural-language description. The extension follows the same format as any publishable Silo extension and can be shared via npm or a tarball URL when ready.
Skill Claude Code
Medical/scientific paper writing workflow skill. Manages the full pipeline from literature search to submission-ready manuscript. Creates and manages a project directory with IMRAD-format section files, literature matrix, reference management, and quality checklists. Supports both English and Japanese papers.…
Plugin Claude Code
Publishes Claude Code session context from a REMOTE host to localvoxtral on your Mac, over an SSH RemoteForward tunnel. Command hooks running a bundled POSIX-sh shim that POSTs via curl — needs only sh and curl on the remote host, and fails open silently when either is missing.
LinkedInLearning/mastering-ai-assisted-development-10666010
Command Claude Code
Review the current git diff for code quality and issues.
Stars-Shen/Paper-insight-skill
Skill Codex
Structured scholarly paper reading and research ideation. Use when Codex needs to read or summarize papers/PDFs, judge innovations, score paper quality and reading priority, compare related work, draft related work sections, expand a literature map with backward/forward citation chaining, identify limitations…
richardhe-fundamenta/practical-gcp-examples
Skill Claude CodeCodex
Manages datasets, tables, and jobs in BigQuery, and integrates with BigQuery ML and Gemini for advanced data analytics and AI-driven insights. Use when you need to interact with BigQuery, run SQL queries, manage BigQuery resources, or leverage BigQuery's built-in ML capabilities. Also use when performing data…
Skill Claude Code
The conventions this team actually follows — naming, branching, review, and the decisions someone already made so nobody re-litigates them. Use when writing or reviewing code here, opening a PR, or when unsure "how do we do this".
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: