All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 437,079 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.
Full-featured CLI for Zotero reference management. Search, import by DOI/PMID, export BibTeX, attach PDFs, semantic search, manage tags/collections, and more. Use this tool whenever you need to interact with a Zotero library programmatically.
AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — grounded in Microsoft's Eval Scenario Library and Triage & Improvement Playbook.
★not rated 142▲
+1 4mo agoA
tokens not measured
originalMIT
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
Generate single-file HTML presentations with 10 professional themes and speaker notes. Use this skill whenever the user mentions presentations, slides, deck, talk, keynote, pitch, slideshow, or wants to turn any content into a visual presentation — even if they don't explicitly say 'slide'. Also triggers for requests…
A professional audit-consulting framework based on the reasoning and communication style of Shaoniannu, an audit commentator. It includes decision models and advice for analyzing audit issues and practical choices.
Build and audit WordPress layouts with GenerateBlocks V2, including CSS Mode, responsive at-rules, dynamic data, Pro components, and recovery-safe block serialization. Use for new GB layouts, conversions, repairs, and hand-authored block markup.
Delegate coding, code review, analysis, and research jobs to Google Antigravity CLI (agy) sub-agents that run alongside your own work. Use this whenever the user asks to spin off, offload, or delegate a task to Antigravity, agy, Gemini, or an "external agent"; wants a second opinion or independent review from a…
Totem — talk to your wearables with AI. Today: full Whoop access (48 tools). Runs locally from the @thebriangao/totem npm package. Needs 5 environment variables to run.
The AI Counsel — MCP-first (10 action-based tools) when The AI Counsel MCP server is connected; REST/curl fallback when MCP is unavailable, for cron scripts, or raw SSE. Triggers on "ask the council", "run a debate", "configure models", "run a deliberation", "check council health", "import relay-ai keys", "disconnect…
Audit and improve recording and alerting rules. Use when reviewing alert coverage or rule health, drafting new alerts or recording rules, investigating flapping or noisy alerts, or speeding up slow dashboards with pre-computed expressions; produces complete rule-group YAML.
A builder for an offline personal fitness dashboard that combines a structured training plan, workout records, reviews, documents, and interface assets.
Designs high-performing ad creatives across Instagram, Facebook, TikTok, LinkedIn, Google (Display / Demand Gen), YouTube, Pinterest, and X/Twitter — locking platform dimensions, safe zones, text overlay policy, character limits, industry visual DNA, ad objective hierarchy, composition patterns, CTA strategy, and…
Drive a macOS app through the computer tool — read its accessibility tree, act on elements, and use real input only when the tree cannot reach the target.
Intent-to-implementation: from a goal, design docs, notes, or a mix, elicit and validate intent into a grounded 3-doc, then orchestrate dependency-aware parallel execution with right-sized review.
★not rated 141 2mo agoA
tokens not measured
originalMIT
Analyze, benchmark, diagnose, and optimize large-model inference deployments from hardware inventory, model details, workload traces, and latency or throughput SLOs. Use when Codex needs to tune SGLang launch parameters, run bounded single-host GPU experiments, plan deployment topology, inspect GPU or CPU profiles…
Turn one topic into one finished video — research, script, an agent debate over the punchline, voiceover, footage, timeline, delivery folder. Ships a 16-agent production team.
★not rated 141 4mo agoA
tokens not measured
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: