Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
artemnovitckii/notebooklm-coach
Skill Claude CodeCodex
Turn expert podcasts into personalized protocols with cited experiments. Load 300 episodes from terminal, run an expert-informed interview, build experiments in your Obsidian morning routine. Use when user says "notebooklm", "load channel", "expert interview", "notebooklm ask", "health protocol", or wants to turn…
Skill Claude Code
Review a change in the EvalBench repo for (a) does it actually work — verified by running the tests and style checks, (b) does it follow EvalBench architecture — base-class contracts, config-key registration, PYTHONPATH-relative imports, sandbox isolation, concurrency safety, docs, (c) does it still build and deploy …
Skill Claude CodeCodex
A reference guide based on the thinking frameworks and examples of 梵公子, also known by similar Chinese names. It covers relationships, social strategy, personal development, conversation, and dating situations.
Xiaoyuan-Liu/national-team-position
Skill Claude CodeCodex
A Chinese-language analysis tool that estimates changes in China’s government-backed ETF holdings by tracking ETF share counts and related index prices. ETFs are funds traded on stock exchanges, and the “national team” refers here to Central Huijin, a state investment company.
Skill Claude Code
Activate, upgrade, test, and benchmark the 7-tool token-saving stack (context-mode, claude-mem, RTK, pxpipe, graphify, caveman, ponytail). Reports per-tool + per-provider (Codex, Gemini, Kimi, opencode, GitHub Copilot CLI) token savings, wires the stack into Copilot, and detects conflicts that would erase the gains.
Skill Claude CodeCodex
Screens for preventive care gaps per USPSTF A and B recommendations by checking existing Procedures, Observations, and Immunizations against age/sex-appropriate due dates. Use when user asks to "check care gaps", "preventive care due", "screenings overdue", "what is this patient due for", "wellness check", "annual…
Skill Claude CodeCodex
Generate or edit images with GPT Image through Codex/ChatGPT subscription authentication instead of OPENAIAPIKEY. Use for text-to-image, reference-image editing, or visual assets when the user wants local Codex auth, especially when no native image tool is available. Do not use for official OpenAI API-key billing or…
Skill Claude Code
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
Skill Claude CodeCodex
Create, repair, validate, and package SVG, APNG, or hybrid desktop pets from a concept, generated or provided images, and state mappings. Use when the user asks to make a desktop pet, start a character from image generation, create or edit character keyframes, animate idle or agent states, choose an asset route…
Skill Claude CodeCodex
AI presentation generator. Create professional HTML slides through conversation. Triggers: create/edit PPT, presentation, slides, deck, keynote, pitch deck, quarterly report, product intro, training materials, roadshow, work report. Core: requirement analysis, outline generation, theme selection, HTML slide…
Skill Claude CodeCodex ✓ vendor
Generate CI/CD configuration for Linear Release. Use when setting up release tracking, configuring CI pipelines for Linear, or integrating deployments with Linear releases. Supports GitHub Actions, GitLab CI, CircleCI, and other platforms.
Skill Claude CodeCodex
AMBIENT BACKGROUND TASK — FIRE ON EVERY SUBSTANTIVE TURN. The user does NOT need to ask. When the user mentions ANY domain (drafting, building, writing, composing, researching, planning, comparing options, exploring, deciding, learning, debugging, designing, refactoring, configuring — ANY domain engagement), you MUST…
91fapiao-cn/playwright-browser-skill
Skill Claude CodeCodex
A browser-automation skill for controlling web pages, including opening sites, clicking elements, filling forms, reading text, taking screenshots, and monitoring page behavior. The instructions are written in Chinese and describe 101 browser tools.
Skill Claude CodeCodex
A collection of skills for architecting and implementing production-ready code using Google Maps Platform APIs and SDKs for any map, place, address, geocoding, routing/ETA (including eco-friendly routing), nearby search, 3D / Street View / static map, marker clustering, custom styling, drawing, geofencing, heatmap, or…
coolowl2991-4kgvw/subtitle-hooks
Skill Claude CodeCodex
A skill for writing short on-screen text that opens technology, artificial-intelligence, coding, productivity, or gadget videos. It produces multiple hook styles and can include a reason, visual format, and language or length limits.
Skill Claude CodeCodex
Systematic departures from rational choice theory and their implications for economic analysis and policy. Covers cognitive heuristics (anchoring, availability, representativeness), biases (loss aversion, status quo, overconfidence), prospect theory (reference dependence, probability weighting, diminishing…
Skill Codex
Generate AI-friendly repository documentation with the SourceSage CLI. Use when Codex needs to run sage or sourcesage to create .SourceSageAssets/Repositorysummary.md, analyze the current repository or another local repository, switch the output language between English and Japanese, use --lite to keep the summary…
Skill Claude CodeCodex
Use the complete Godot development loop from the swallowtail CLI: discover the live engine API, build and edit in the open editor, run and play the game, observe state, debug failures, fix them in place, and verify the result. Use when the task involves creating or modifying a Godot project, testing game behavior…
aws-neuron/neuron-agentic-development
Skill Claude CodeCodex
Ingests vllm-neuron model execution artifacts into parquet using neuron-explorer and guides profile analysis: identifies prefill/decode NEFFs, segments by collective boundaries, computes per-engine bounds and DMA efficiency, and produces structured workload reports. Use when encountering "analyze profile", "ingest…
Skill Claude CodeCodex
Patsnap Patent Research MCP for AI agents. Performs novelty searches, invention freedom-to-operate reviews, and design-patent FTO reviews from technical text, claims, disclosures, or product images. Use for defined novelty and infringement-risk research workflows, including asynchronous task retrieval; do not use it…
Skill Claude CodeCodex
Rules for communicating with humans as an AI agent. Read in full BEFORE composing any text another person will read: PR titles and descriptions, issues, code review replies, comments, discussion summaries, emails, chat and forum posts, commit messages, changelogs. Also before replying when someone responds to you, and…
Skill Claude CodeCodex
Create detailed markdown walkthroughs of code changes. Use when the user asks to "create a walkthrough", "explain the changes", "review recent commits", "document what changed", "walk me through the diff", "summarize my changes", or similar requests for change documentation.
ricmmartins/azure-sre-agent-skills
Skill Claude CodeCodex
Assess security, reliability, and cost posture of Azure OpenAI and Microsoft Foundry deployments. Detects critical anti-patterns: API keys instead of Managed Identity, public endpoints without firewall, disabled content filtering, missing diagnostic settings, deprecated model versions, over-provisioned PTU, absence of…
Skill Claude CodeCodex
Dynamic access to medusa-mcp MCP server (299 tools).
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: