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.
Skill Claude CodeCodex
Make Chinese agent replies concise and answer-first, without filler, repetition, or jargon. Use when users request brief replies, less unnecessary output, or concise.
daviihub/interview-todo-case-transfer
Skill Codex
A Chinese-language interview-preparation method that matches a job description with evidence from a candidate's résumé and past projects.
Skill Claude Code
Generate or refresh /docs/architecture/ — the current-state source of architectural truth for this codebase, grounded in code and git history (NOT in .designs/). Produces an anchor-dense corpus (invariants.md, idioms.md, trust-boundaries.md, seams.md, subsystems/.md, history.md, gaps.md) plus a high-level overview…
Plugin Claude Code
Bundles 1 skill · 115 tokens together
Check whether a repository agrees with itself, for Claude Code and Codex, then work through the findings one at a time. An exact layer finds broken links, dangling heading anchors, orphaned files, duplicate content, translations that have fallen behind and drift between docs and code, with no model, no network and no…
Skill Claude Code
Kit-maintainer diagnostic (LOCAL-ONLY, not distributed) that audits the README and docs/ for staleness against the repo's real command/skill/CLI roster, stamped tree, and cross-doc consistency. Read-only; produces a severity-ranked findings report.
Skill Claude Code needs its repo
A strict editorial reviewer that checks writing principles inspired by George Orwell's "Politics and the English Language" rules and Matthew Butterick's Practical Typography. Use this skill whenever the user says "red pen", "check my prose", "edit this for clarity", "typography check", "tighten this up", "review this…
Skill Claude CodeCodex
Generate a complete blog post with cross-platform social media copy, all organized in a dated directory structure. Use this skill whenever someone wants to write a blog post, create blog content, draft an article for their blog, or needs social media copy to promote a blog post. Also trigger when the user mentions…
Plugin Claude Code
Bundles 1 skill, 4 agents · 670 tokens together
Read a group of related Markdown files and assemble one self-contained, strongly human-readable HTML overview of the system as a whole. View, not storage: regenerates on demand from the current source .md, never modifies the sources. S0-S5 pipeline: Preflight -> Parse (deterministic Python) -> Render (N parallel…
Cursor rule Cursor
Apply the ontario-bud persona when the user wants ontario-bud-styled prose, uses trigger phrases ("ontario bud", "letterkenny mode", "pitter patter", "talk like wayne", "/ontario-bud", "/wayne"), or has already activated this persona earlier in the session. The register changes only the prose; code, paths, commits…
Plugin Claude Code
Bundles 15 skills · 2,123 tokens together
Turn any idea — or an existing tutorial — into a step-by-step build guide that teaches while it builds. A gated pipeline of skills that plan, draft, clarify, review, modernize, audit, scaffold, version-update, and check-your-work-against learn-as-you-go developer guides.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 hook · 66 tokens together
Detects documentation made stale by code changes and patches it in the same commit. Your docs can never lie again.
Plugin Claude Code
Bundles 6 skills, 10 commands, 2 agents, 7 hooks · 1,267 tokens together
Vibe-coding seatbelt for Claude Code — durable docs and measurement evidence + AI discipline (root-cause first, no unfounded claims) + machine enforcement (ruff/eslint/import cycles).
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 57 tokens together
Build Jamdesk documentation sites with Claude. Complete reference for 50 MDX components, docs.json configuration, 8 navigation patterns, CLI commands, and writing standards.
Plugin Claude Code
Bundles 1 skill, 2 commands, 2 hooks · 58 tokens together
Writing coach for non-native speakers — checks the user's English before each response.
toBzh30/Claude-Project-Bootstrap
Plugin Claude Code
Bundles 4 skills, 3 hooks · 442 tokens together
Bootstrap a new repo with working-agreements, GitHub Project, and CLAUDE.md hub-and-spokes — runs github-project-setup, split-claudemd, and bootstrap-working-agreements as one flow or individually.
Command Claude Code
Generate a review-oriented TLDR of a feature's spec.md / plan.md — a self-contained HTML dashboard plus PR-native Markdown — that floats ambiguities, open questions, and spec↔plan mismatches to the top so a reviewer gets oriented fast. An entry point into the document, not a replacement for reading it.
Plugin Claude Code
Bundles 3 skills, 4 hooks · 102 tokens together
Automatic codebase index + per-module READMEs for Claude Code (hooks + auto-sync).
product-on-purpose/writing-style-catalog
Plugin Claude Code
Bundles 3 skills · 183 tokens together
Composable writing instructions on four orthogonal axes (Voice, Tone, Style, Format): pick one entry per axis and the builder assembles a ready-to-paste prompt prefix that steers any LLM toward a precise register, reasoning pattern, and layout. Ships 98 entries, 1205 worked examples, 158 diff-pairs, and 14 recipes…
OpenAnalystInc/10x-Research-Skill
Plugin Claude Code
Bundles 4 skills, 12 commands · 461 tokens together
Team 10x.in research system for autonomous deep research, content creation, web scraping, and AI image generation. Supports MCP-first workflows with Tavily, Firecrawl, and Playwright plus local fallback scripts and brand-aware delivery.
Plugin Claude Code
Bundles 8 skills · 572 tokens together
Keeps a project's architectural documentation in sync with its code by having Claude maintain modular docs as it works, instead of relying on a single static file or a human-run doc pass.
Plugin Claude Code
Bundles 2 skills · 201 tokens together
Generate and maintain a branded, interactive user's manual from any codebase: clickable headings file notes that become developer tickets (optionally synced to Jira or GitHub Issues), roadmap previews show planned changes, a glossary explains concepts on first use, and readers reorder sections by dragging the contents.
Plugin Claude Code
Bundles 1 skill, 6 commands, 16 agents, 4 hooks, 10 MCP servers · 1,217 tokens together
Vedix — research workbench that turns a topic into a venue-ready manuscript via cross-host CLI orchestration.
Wechat-ggGitHub/prefer-html-output-skill
Skill Claude CodeCodex
When the agent is about to output long markdown (weekly reports, PR reviews, design comparisons, concept explainers, flowcharts, design systems and other deliverables meant for human reading), proactively evaluate whether to render it as HTML instead. Based on the 20 examples from ThariqS/html-effectiveness. Only…
Skill Claude CodeCodex
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice…
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: