Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.
Drive CodeBurn, a free open-source local-first CLI/TUI/web/menubar tool that reads the session files already on disk from 40 AI coding tools (Claude Code, Codex, Cursor, Gemini CLI, Grok, OpenCode, and more) and breaks down token usage and dollar cost by task, model, tool, and project. Use when the user wants to see where their AI coding spend went, find and fix token waste in a Claude Code / agent setup, cap a session's budget before it runs away, compare which model is actually worth its price, check whether AI spend shipped or was reverted, or wire live usage/savings data into an agent over MCP. Triggers on: "codeburn", "npx codeburn", "AI token usage", "AI coding cost", "where did my Claude spend go", "codeburn optimize", "codeburn guard", "codeburn compare models", "codeburn yield", "token waste in CLAUDE.md", "AI spend dashboard".
Automate code review remediation loops with the codex CLI. Requests reviews from codex, classifies findings by severity (P0-P4), fixes critical issues (P0/P1) through iterative cycles, defers quality improvements to backlog, and escalates after 3 review cycles. Use when working with code that needs structured remediation: ''codex review'' in a request triggers this workflow.
Submit a packaged .codex-theme file or a linked theme showcase (skin) to CodexThemes through the authenticated codexthemes.ai submit API. Use when a user asks to submit, publish, upload, or share a Codex theme on codexthemes.ai, shares a URL of a theme to list in the directory, asks to configure or check a CodexThemes API key, or has an exported .codex-theme package ready for submission.
Use when building data integration pipelines, querying industrial data, deploying data models, managing access control, or developing applications that connect to industrial assets, time series, events, and files. Reach for this skill when working with REST APIs, SDKs (Python/JavaScript), data modeling, extractors, transformations, or infrastructure-as-code deployments. Use for **Cognite Flows** custom web apps hosted in CDF (React, `@cognite/cli`, Aura design-system UI with `@cognite/aura`, app hosting, local dev with Vite, deploy, and certification). Core data modelling (CDM)—use when working with CogniteAsset, CogniteTimeSeries, CogniteFile—the CDM concepts for assets, time series, and files. Reach for this skill when building asset hierarchies, populating time series, creating and linking files, or when searching for "Asset" in the API reference (CDM assets are in the Instances API. The legacy /assets endpoint is deprecated as of 2026-10-15 and retires on December 31, 2027)
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client, workflow JSON format, model patterns, dual/multi-GPU placement, the MCP driver, in-graph Claude nodes, and VRAM coordination.
Kaggle competition notebook workflows and submissions. PROACTIVELY activate for: (1) submitting notebook outputs to competitions, (2) `kaggle competitions submit -k`, (3) downloading competition data, (4) validating submission.csv format, (5) leakage review, (6) cross-validation split design, (7) public leaderboard overfitting concerns, (8) competition rule compliance, (9) reproducible top-to-bottom notebook execution, (10) fold-aware preprocessing for ML pipelines. Provides: submission commands, validation checklist, leakage controls, and competition-ready notebook guidance.
Based on an already-reached design consensus, research and compare suitable technical libraries, packages, or frameworks, and output an evidence-backed technology selection report with recommendations. Use after consensus is reached in grilling, grill-me, or grill-with-docs when you need technical research, framework comparison, dependency selection, or to prepare technical decisions for to-spec.
Content extraction and analysis for video, podcast, article, and YouTube content. Extracts structured insights, key takeaways, and wisdom. USE WHEN extract wisdom, content analysis, analyze content, insight report, analyze video, analyze podcast, extract insights, key takeaways, what did I miss, extract from YouTube.
End-to-end open source contribution workflow: from scanning issues to submitting PRs. Use this skill whenever the user wants to contribute to an open source project, find issues to fix, submit a pull request, fork a repo to contribute, fix a GitHub issue, or mentions 'open source contribution'. Also trigger when they provide a GitHub repo URL and ask about contributing, say things like 'help me submit a PR', 'find good first issues', 'I want to contribute to X', or mention fixing bugs in someone else's project.
Create dimensioned 3D CAD parts from natural-language requirements and export validated STEP, STP, or STL files with OpenCAD. Use when a user asks an AI agent to model a mechanical part, make a printable STL, create an editable STEP file, convert a dimensional description into CAD, or revise a previously generated OpenCAD model.
Generate a ready-to-send FAQ document that anticipates and answers the most common creator questions about a campaign brief, reducing back-and-forth messages and delays. This skill should be used when creating a campaign brief FAQ, writing answers to common creator questions about a brief, building an FAQ attachment for an influencer brief, reducing back-and-forth with creators after sending a brief, anticipating creator questions before launch, preempting influencer confusion about deliverables or timelines, generating a brief companion FAQ, writing a creator-facing Q&A for a campaign, drafting briefing clarifications for influencers, or creating a FAQ sheet to send alongside a content brief. For writing the campaign brief itself, see campaign-brief-generator. For writing individual content briefs, see content-brief-builder. For chasing creators who have not responded to a brief, see universal-creator-follow-up-chaser.
Input contracted creators with their required vs. actual post counts and receive a compliance table with status classifications and escalation notes for non-compliant creators. This skill should be used when checking which creators have fulfilled their posting obligations, auditing deliverable completion across a campaign, tracking contracted vs. actual posts for an influencer program, identifying which creators are behind on deliverables, building a compliance report for campaign creators, flagging overdue or missing creator posts, reviewing posting status across all creators in a campaign, generating escalation notes for non-compliant influencers, or producing a deliverable tracker for a creator campaign. For checking whether a specific piece of content matches the brief requirements, see content-to-brief-compliance-checker. For chasing a specific creator about a late deliverable, see universal-creator-follow-up-chaser. For building a full campaign report with ROI metrics, see campaign-roi-calculator.
This skill should be used when the user asks to "show me the changes", "what did you change", "let me see the diff", "review the code", "open web preview of changes", "show me what you worked on", "compare branches", "explain what changed", or wants to view git diffs in a terminal UI, web browser, or get AI-powered code review explanations.
Find ALL the arXiv papers that answer a research question, using fastCRW's Firecrawl-compatible Research API. Use when the ask is to survey a literature, enumerate papers on a topic, find what a paper compares against or builds on, list the best models on a benchmark, or recover a paper from a vague description — "papers that do X", "what does X benchmark against", "best open model on Y", "find the paper that ...". Reaches 61.0% recall on the ArXivQA benchmark vs Firecrawl's Research Index 53.3%.
Collect, analyze, and act on customer feedback to improve your product and business. Use when building feedback systems, running customer interviews, analyzing feature requests, measuring satisfaction (NPS, CSAT), or closing the feedback loop. Covers feedback collection methods, interview techniques, analysis frameworks, and how to decide what feedback to act on. Trigger on "customer feedback", "collect feedback", "user research", "customer interviews", "NPS", "feature requests", "feedback system".
Vercel Daemons guidance — long-running background workers built from a Dockerfile and declared under the `daemons` key in vercel.json. Use when running queue consumers, Celery/Sidekiq/BullMQ workers, workflow workers, or job runners next to an app on Vercel; configuring daemon instances per region, memory, or command; handling SIGTERM; or choosing between Daemons, Functions, Queues, and Workflows.
Set up the Datadog Google Cloud integration with Terraform: creates a service account in the host project, lets Datadog's delegate principal impersonate it via roles/iam.serviceAccountTokenCreator (no service-account keys), enables the required APIs, grants the monitoring roles across the chosen projects and folders, and registers the account through datadog_integration_gcp_sts. Use when the user wants to monitor GCP resources such as Compute Engine, Cloud SQL, GKE, Cloud Run, or Pub/Sub, wants to connect a GCP project or folder or organization to Datadog, or asks to set up or repair the GCP integration. Does not set up log forwarding.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
