81,468 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.
The reflex layer on top of superpowers. Tunes an agent's working instincts — verify against the source, instrument for remote diagnosis, write for humans, test with teeth.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Generate a unique themed Super Claudio Brothers platformer. Creates a custom level, colour palette, enemy look, and Claudio costume. Every run produces a different game.
A Korean job-search and company-finance research agent. It uses a résumé to define search criteria, collects currently active job postings, checks public financial filings, and produces an HTML report.
★not rated 2 3mo agoA
tokens not measured
AGPL-3.0
A collection of skills for working with BaseMachina, including researching its official documentation, managing code, and building clients for its public APIs.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Senior implementation lead — orchestrates the full feature lifecycle from problem exploration to commit. Enforces gated approval before writing code, incremental quality checks during implementation, and handoff to code-review for final validation. Stack-agnostic by default; loads stack-specific references when a…
A brainstorming workflow that asks several different roles or subagents to analyze a topic independently, then combines their views into a structured report.
Learn from prior mistakes and repeated patterns - review what failed, extract a reusable lesson, apply it to the next attempt. Activate when the user corrects your output, when an approach fails and needs a retry, when you notice the same friction recurring across tasks, and at the end of significant multi-step work.…
Control Claude Code from your phone via Discord. Full session mirroring, bidirectional messaging, permission approval. Auto-discovers all running instances.
★not rated 2 2mo agoA
tokens not measured
originalApache-2.0
Transform any learning resource OR bare concept/topic into a personalized, example-driven study session — like a smart friend teaching you the content. Use this skill whenever the user wants to learn from or understand content from any external source (YouTube videos/lectures, GitHub repos or READMEs, research papers…
AI patent writing skills: from idea to submission-ready patent disclosure (docx) with anti-hallucination checks and claim-format validation. Works for any technical domain.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Orient a multi-turn “help me think this through” deliberation with a Rumsfeld matrix. Use when the user owns an open decision or judgment and wants a thinking partner — articulating a tacit judgment, surfacing an unrecognized assumption or pattern, or touring options around the choice they are weighing. A question…
Parallel multi-agent code review using Agent Teams with 4 specialized reviewers. Spawns a coordinated team of security, performance, test coverage, and code quality agents. Teammates can share findings with each other for cross-domain insights. Produces unified report with severity-ranked findings saved to /output/.…
Priority-ordered rulebook of core UX/UI laws, cognitive-psychology principles, Nielsen's usability heuristics, and accessibility requirements that Claude must actively apply (not just cite) whenever it designs, builds, redesigns, reviews, or critiques any user interface — websites, web/mobile apps, dashboards, forms…
★not rated 2
changed 4d agoA
tokens not measured
original
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: