246,500 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
aryrabelo/serpapi-agent-toolkit
Skill Claude CodeCodex
Use when an agent needs live, structured search-engine data through SerpApi (web results, news, shopping, local, jobs, flights, scholar, images, video). Covers picking the right engine for the intent, choosing compact vs complete output, query operators, pagination, deduping and citing results, and when NOT to search.…
Skill Claude CodeCodex
Skill "intern-os" from poktalabs/intern-os, covering internos — workstreams (claude code), what "thread" means in claude code, resolution: pwd → workstream, returns workstream absolute path on stdout (exit 0), or and operating protocol.
Skill Claude CodeCodex
Run a coding agent unattended overnight, long running agent safety, stop a runaway loop, cap agent token spend. Sets up four guardrails around an agent loop you already have: a resumable handoff file so an interrupted run continues, a verification gate that fails closed so unchecked work is never accepted, a runaway…
Skill Claude Code
Audits your CLAUDE.md and Claude Code configuration, then generates a migration plan to the skills+hooks architecture. Classifies each section as invariant, workflow, or router. Outputs token savings estimate, stub skill files, and hook boilerplate. Use when CLAUDE.md exceeds 300 lines, skills aren't triggering…
nikitaCodeSave/claude-code-harness
Skill Claude Code needs its repo
A release checklist for publishing updates to the claude-code-harness plugin repository. It covers deciding whether a Git tag is needed, updating plugin versions, recording the change, staging files, publishing, and checking that the remote repository is synchronized.
zhiyingxia/claude-code-cache-diagnostics
Skill Claude CodeCodex
Use when diagnosing Claude Code prompt-cache breaks, 1h cache misses, cachecreation/cacheread anomalies, away summary or recap rebuilds, cc-switch proxy logs, or reports that Claude Code recreates cache after a few minutes.
louie-1515/claude-code-desk-pet
Skill Claude CodeCodex
Use when creating, adding, replacing, or polishing desk pet roles for the Claude Code desk pet project, especially when the user describes a role and expects the agent to generate prompts and guide the whole workflow.
panaversity/ca-cpa-practice-agents
Skill Claude CodeCodex
Extension encoding regulatory compliance calendar: filing deadlines, information checklists, penalty matrices, and automated monitoring schedules. Ships with Pakistan regulatory obligations (FBR, SECP, SBP).
Skill Claude CodeCodex
A guide for querying 360 Quake, a Chinese internet asset-mapping service that reports hosts, services, domains, and certificates.
Skill Claude CodeCodex
Manual for understanding CasAbot's structure and configuration.
xiaoshiyilangzhao1996-droid/yinyo-writer
Skill Claude CodeCodex
Load when the user needs a Yinyo-style Chinese long-form article, WeChat post draft, or article-quality review.
abertanha/md-to-wiki-docs-skills
Skill Claude CodeCodex
Turn markdown specification files into documentation sites.
chunyun1998-sudo/justin-sun-writing-dna
Skill Claude CodeCodex
A Chinese writing-style guide for producing very short, fragmented passages, with one sentence per paragraph and emotion conveyed through objects, numbers, and silence rather than stated directly.
Skill Claude Code
Set up a full Ghostty terminal environment with shell plugins, tools, and configs on a fresh Mac.
Skill Claude CodeCodex
A live role-playing experience set in an open world called 留风镇. Each turn describes the surroundings, the character's thoughts, choices, and the results of actions, with a progress line included.
Skill Claude Code
Review code changes for security, performance, and style issues.
linux-ur/discord-net-components-v2
Skill Claude CodeCodex
Reference and implementation guide for building Discord bot UIs with Discord.Net's Message Components V2 system (ComponentBuilderV2) in C#. Covers every V2-only component (Container, Section, Text Display, Thumbnail, Media Gallery, File, Separator), the shared V1/V2 interactive components (Action Row, Button…
Skill Claude CodeCodex
Analyze APKs from manifest to native libraries, statically and with instrumentation.
Skill Claude CodeCodex
NextDNS integration guides for third-party platforms and services. This skill should be used when integrating NextDNS with routers, home automation systems, network management platforms, or other third-party services. It also guides transport selection across DoH, DoT, DoQ, DoH3, IPv6, and legacy DNS. Triggers on…
Skill Claude CodeCodex
Search and read academic papers from arxiv via Semantic Scholar API + ar5iv HTML. No OAuth, no PDF parsing. Use when the user wants to find research papers, read a specific paper, look up citations, or explore academic literature. Trigger on "find papers on", "arxiv", "research on", "look up the paper", "academic…
Skill Claude CodeCodex
How an agent should reason about what it has, what it can do, what to delegate, and how to verify without assumptions. Read before starting any non-trivial autonomous task. Covers self-inventory, verification levels, assumption audit, and when to stop and escalate.
dovoanhtruong/abap-agent-antigravity-workspace
Skill Claude CodeCodex
Generate SAP BTP (Business Technology Platform) solution architecture diagrams as native draw.io (.drawio) files following the official SAP BTP Solution Diagram guidelines (Fiori Horizon design system) and open them via a configured draw.io MCP server. USE WHEN: user asks to create/draw/design/sketch a BTP diagram…
Skill Claude CodeCodex
Read and act on the user's messages, email, calendar, meeting notes, and files (Slack, Discord, Telegram, Gmail, Google Calendar/Meet/Drive, Twitter/X, Notion, Obsidian, SMB) through their Conduit hub — all writes queue in a human-approval outbox.
Skill Claude CodeCodex
Use when operating LINZA MCP as a local-first agent workspace. Guides agents through doctor checks, guidenextsteps, agentworkspace actions, teach/grow review loops, dry-run apply gates, artifact safety, calibr trace review, and context export without exposing raw tool lists to users.
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: