25,035 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.
fikrilal/engineering-agent-skills
Skill Claude CodeCodex
Create or revise an engineering proposal from a technical discussion and repository evidence. Use when the user asks to formalize a feature, refactor, architecture direction, platform integration, migration, or other non-trivial change before implementation. Produces a repository-specific proposal rather than filling…
kolascoco/Neuroscience-Agent-Skills
Skill Codex
Expert guidance for writing DFG (Deutsche Forschungsgemeinschaft / German Research Foundation) research grant proposals — from first idea to elan submission. Use this skill whenever the user is preparing, drafting, reviewing, or improving a DFG proposal, including Individual Research Grants (Sachbeihilfe), Emmy…
mikonos/zettelkasten-agent-skills
Skill Claude CodeCodex
High-output meeting/conversation notes (decisions, alignment, disagreements, decision trail, assumptions, risks/opportunities, action items) + Zettelkasten links. Use when asked to summarize meeting notes or turn a conversation into reusable knowledge.
Skill Codex
A resume and CV writing workflow for turning real work experience into concise, evidence-based application content.
harrystamatoukos/ai-conversation-extractor
Plugin Claude Code
Bundles 2 skills, 3 commands, 1 hook · 148 tokens together
Extract valuable insights, decisions, patterns, and ideas from AI conversation exports (ChatGPT, Claude, Claude Code) into Obsidian-compatible notes. Includes a mirror analysis feature that builds a living psychological profile from your conversation patterns. Processes your chat history day-by-day using a Ralph…
bitia-srl/bitia-vs-code-copilot-examples
Skill Claude Code
Generate and maintain concise API documentation from route handlers and data models.
MCP server Claude CodeCodexCursor +2
Model Context Protocol server for Apifox API documentation management. Import/export OpenAPI specifications, maintain API docs with AI assistance. Runs locally from the apifox-openapi-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server for TypeWhisper local dictation, transcription, history, and dictionary automation. Runs locally from the @typewhisper/mcp npm package.
conorbronsdon/avoid-ai-writing-mcp
MCP server Claude CodeCodexCursor +2
Local, deterministic MCP server for auditing AI-writing patterns. Runs locally from the avoid-ai-writing-mcp npm package.
MCP server Claude CodeCodexCursor +2
WordPress MCP server: publish posts, AI images, SEO and full site management, self-hosted. Remote server at mcp.getwpagent.com.
junaid18183/novel-architect-skills
Skill Claude CodeCodex
Stepwise scaffolding, brainstorming, and draft-generation for literary novels using interactive interviews. TRIGGERS - Use this skill when user says: "create a novel project" / "start a new novel" "help me brainstorm my novel" / "plan my story" "/novel-architect [language] novel named [name] [core idea]" "set up novel…
MCP server Claude CodeCodexCursor +2
Deterministic prose linter for LLM-generated text — flags filler phrases, AI buzzwords, hedges, and clichés. No model required. Python API + CI exit codes + RL reward signal. Runs locally from the defluff Python package.
Skill Claude CodeCodex
Create public Google Docs or Google Sheet files without requiring OAuth. Use this skill to create and edit Google Docs and Sheets, no Google sign-in required. Documents are viewable at shareable links. Registration is automatic on first use.
Skill Claude CodeCodex
The most comprehensive AI text humanization skill available. Detects and rewrites 45 AI writing patterns using an 8-step pipeline with self-audit, perplexity/burstiness engineering, voice calibration from writing samples, and domain-specific modes. Based on Wikipedia's "Signs of AI writing" guide plus 2026 AI…
Plugin Claude Code
Bundles 1 skill · 196 tokens together
Build evidence-backed resumes, career knowledge vaults, career coaching artifacts, detailed interview resumes, ATS-safe DOCX files, high-quality visual HTML/PDF/Figma/Canva-ready resumes, job match reports, LinkedIn recommendations, interview prep, and redaction reviews.
Command Claude Code needs its repo
Score a file or pasted text against CLEAR-100 on four axes (Plain, Human, Structured, Dense) and list every finding with the fix. Read-only, changes nothing.
Skill Claude CodeCodex
Use when asked to proofread, review, or 校对 code or documents for correctness, logical consistency, or quality issues. Covers general code logic review (any language), plus formal-verification backends for C (ACSL contracts via Frama-C static proof and E-ACSL runtime checks), Python (icontract + CrossHair), Rust (Kani…
Skill Claude Code
Audit and surgically fix the marketplace's documentation so every shipped command is discoverable — checks each plugin README's Skills section against SKILL.md frontmatter, the root README's plugin list and command index, manifest/description sync, and docs-site parity. Use when docs may have drifted from the code…
Cursor rule Cursor
User-facing copy — dry technical voice, no AI slop.
mushroomfk/long-novel-agent-kit
Skill Codex
Long-form novel continuity kit for local desktop agents. Use when planning, initializing, continuing, revising, checking, or handing off long novels with many chapters, source notes, structured facts, character states, foreshadowing, plot debts, chapter contracts, research notes, or existing manuscripts. Provides a…
Plugin Claude Code
Bundles 1 skill, 16 commands · 690 tokens together
Long-form content distilled into presentations and reading guides.
Plugin Claude Code
Bundles 2 skills · 111 tokens together
Agent Skills for Podlite markup language.
Skill Claude CodeCodex
An interactive writing assistant for developing and reviewing online articles. It supports work from choosing a topic through publication and reviewing weak results afterward.
Skill Claude CodeCodex
Two related workflows for a locally-cloned codebase, in one skill. Documentation mode produces a single, comprehensive, verifiable architecture document primarily by reading files on disk (local-first) — use it whenever the user wants to understand, map, document, research, or onboard onto a codebase ("research 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: