81,493 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.
Adaptive extractive text compression: shorten academic papers, chapters, reports and documentation without paraphrasing, using the author's words and order. Use for "compress this text", "shorten without rewriting", "condense this chapter", "comprimí este PDF", "acortá sin perder contenido" or a faithful study summary…
Scaffold, audit and migrate CLAUDE.md files from inside Claude Code: /claude-md-new builds one from battle-tested templates using your repo's real commands; /claude-md-audit grades an existing one and returns worst-first fixes; /claude-md-migrate rewrites a bloated file into the lean verified style.
★not rated 10 3mo agoA
tokens not measured
originalMIT
SAP project-delivery & operations automation for functional consultants, integration, security, release, and AMS/ops teams. Ships 40 skills covering functional/AMS operations across six lanes — incident root-cause, health checks, access & authorizations, release & transports, test data & regression (Business Partner…
★not rated 10▲
+1 2mo agoA
tokens not measured
GPL-3.0
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
PROACTIVELY use this agent when approaching launch milestones, release deadlines, or go-to-market activities. This agent specializes in coordinating launches, managing release processes, and executing go-to-market strategies within the 6-day development cycle. Should be triggered automatically when release dates are…
★not rated 10 1mo agoA
tokens not measured
originalApache-2.0
Méthodologie rigoureuse de recherche en droit français, distribuée comme plugin Claude Code : sources primaires Légifrance et Judilibre, vérification de vigueur, citations traçables.
A voice-reporting skill that turns a work summary into an offline-generated voice message and locally transcribes a user's voice reply. It sends and receives these messages through Telegram.
Deterministic finish-line gates for AI coding agents — define done once in .skillgate/done.yaml, then block commit, push and publish until it passes. Wires a fail-closed PreToolUse hook, evaluates agent patches in a network-off clone, and keeps CLAUDE.md/AGENTS.md from drifting apart.
★not rated 10▲
+1 2d agoA
tokens not measured
originalMIT
Manage AI coding skills and commands with the skm CLI: one local Git repo of skills/commands, installed into Claude Code, Codex, pi, dsh and any custom target. Use when asked to import/adopt a skill, install or uninstall one somewhere, update or verify the repo, inspect what is installed where, add an install target…
Ask Codex, Antigravity, OpenCode or GitHub Copilot for a second opinion, a code review or a phased workflow, through the CLIs already signed in on this machine.
★not rated 10
changed 1mo agoA
tokens not measured
originalMIT
Keeps an agent from using tex-mcp's tools, guide() aside, until this context has read the files guide() lists, again after each compaction, and listens for Call agent from the session's start to its end.
★not rated 10
changed 8d agoA
tokens not measured
originalMIT
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture.
A Chinese-language skill for checking the completeness and consistency of academic manuscripts. It traces claims to original papers, code, and experiment records, then checks related text, tables, scripts, figures, and stored memories.
Go development toolkit: 6 specialized subagents (go-structure-reviewer, go-developer, go-bug-reviewer, go-security-reviewer, go-perf-developer, go-test-developer) and a multi-phase optimization pipeline (go-optimize) for end-to-end Go code review and improvement.
A conversation tool that brings selected past chats into a new discussion as separate first-person advisers. It supports Reasonix and Codex session formats.
★not rated 9 4mo 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: