All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 437,679 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Use when the user wants to work on a Claude Code skill file (SKILL.md): writing one from scratch, testing whether an existing one works well, running evals or benchmarks, improving its instructions, or fixing why it isn't triggering. Triggers on: 'make a skill for X', 'test this skill', 'run evals on my SKILL.md'…
A diagramming assistant for creating flowcharts, architecture diagrams, and other visual plans in Excalidraw, a browser-based drawing tool. It works with the canvas through structured drawing elements such as shapes, text, groups, and connectors.
★not rated 125▲
+2 3d agoASkillSpector: pass29 tokens
originalMIT
A skill for designing courses as sourced, checkable products that can be improved over time. It says that creating the course files alone does not mean the course is finished.
Read and annotate a wiff code-review session from the command line. Use when asked to review a diff and leave comments in wiff, or to read and address the comments already left in a wiff review.
Local-first observability and cost control for Claude Code agents: a zero-token statusline showing context re-read %, savings/optimize reports, and a health check. Runs 100% locally against your own telemetry, no signup or network account required.
★not rated 125
changed 1mo agoA
tokens not measured
originalMIT
Autonomous experiment loop for optimization research. Use when the user wants to: Optimize a metric through systematic experimentation (ML training loss, test speed, bundle size, build time, etc.) Run an automated research loop: try an idea, measure it, keep improvements, revert regressions, repeat Set up autoresearch…
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
Turn your agent into an SEO team: crawl any site, catch broken links, redirect chains, missing metadata, thin content, and AI-search (GEO) gaps — then get a prioritized fix list and diff crawls to prove the fixes landed. Runs on Crawlie Cloud: sign in and go, nothing to install.
A coordinated code-review workflow with four reviewers: one for static analysis, one for design, one for security, and one for refactoring. A pull request is a proposed set of code changes submitted for review.
Generate AI-illustrated comic-style educational guides from documentation, source code, or any technical content. Produces actual comic PNG images using AI image generation (not HTML). Supports 10+ anime styles: Doraemon, Naruto, One Piece, Dragon Ball, Spy x Family, Chibi, Chinese ink, Ghibli, Crayon Shin-chan…
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
Use when the user asks to quote an ayah/surah, translate a verse, explain meaning/context/tafsir, find verses about a theme, compare translations/tafsir, analyze Arabic word patterns, or view a mushaf page. Also use for any question the Qur'an might address, any Islamic question that might have an answer from tafsir…
Build multi-agent AI systems with the JarvisCore Python framework. Use when writing, reviewing, or debugging code that imports jarviscore, defines AutoAgent or CustomAgent classes, runs a Mesh, or configures agent memory (Athena), P2P, Nexus credentials, or tracing.
Build, assemble, inspect, reconstruct, and export parametric CAD models with the SimpleCADAPI Python SDK. Use for SimpleCAD geometry modeling, constrained sketches, parts and assemblies, standard gears and bearings, STEP/BREP inspection and reconstruction, vector-PDF drawing reconstruction, durable product packages…
What building realness taught us about the web platform - semantic HTML with microdata as one decision that serves SEO, CSS selectors, layout, the data model, state (no Pinia), file storage paths, and the NoSQL database. Plus baseline-grid spacing, fluid type scale, materials-and-roles color, OS dark mode, and cascade…
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, and expand or cut scope when that makes a better product — in one of four modes: scope expansion, selective expansion, hold scope, scope reduction. Then review the plan section by section: architecture, error and rescue…
Show the user's AI Engineering Fluency stats (token usage, cost, sessions, charts, fluency score) in the AI Engineering Fluency canvas. Use when the user asks about their AI or Copilot token usage, spend, recent sessions, or fluency score.
Build, develop, deploy, validate, or troubleshoot custom agents with the Agent Bricks CLI and AgentKit. Use for agentbricks commands, agent.toml bindings, and Agent Bricks project integration; not for unrelated agent frameworks or MLflow-only tasks.
★not rated 125 todayA58 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: