Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget. Orchestrates the other four DSPy skills (dspy-fundamentals, dspy-evaluation-harness, dspy-gepa-optimizer, dspy-rlm-module) in the correct order. Use for greenfield DSPy builds; prototypes may stop at a validated baseline.
Orchestrate dozens-to-hundreds of subagents from a script Claude writes (Claude Code Dynamic Workflows, trigger `ultracode`). Use when a task exceeds a single agent's context or needs more than ~4 concurrent workers — large audits, migrations, multi-source research, fan-out reviews. Distinct from Agent Teams (synchronous, ≤4 workers) and ralph-run (sequential single-context loop).
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Fetch upcoming economic events and data releases using FMP API. Retrieve scheduled central bank decisions, employment reports, inflation data, GDP releases, and other market-moving economic indicators for specified date ranges (default: next 7 days). The script outputs raw JSON or text; the assistant filters, assesses impact, and generates the Markdown report.
Guidance for Microsoft Entra ID (formerly Azure AD) — cloud identity and access management and the control plane for Zero Trust. Covers tenant and identity model, authentication methods (passkeys, FIDO2, certificate-based), hybrid identity with Entra Connect or Cloud Sync, app registrations and consent governance, groups and administrative units, break-glass accounts, and Zero Trust identity foundations. WHEN: Microsoft Entra ID, Azure AD, identity provider setup, SSO, hybrid identity, Entra Connect, Cloud Sync, authentication methods, passwordless, passkey, FIDO2, certificate-based auth, app registration, enterprise application, illicit consent grant, break-glass account, emergency access, administrative units, SSPR, password writeback. DO NOT USE for risk-based detection (use entra-id-protection), Conditional Access design (use conditional-access-mfa), PIM (use azure-pim), or identity governance lifecycle (use entra-id-governance).
Turn AI coding conversations and project delivery materials into a verifiable nine-part evidence chain, distinguishing problems, decisions, individual actions, delivery stages, outcome evidence and responsibility boundaries. Use when the user runs /evidence-recap, $evidence-recap, or explicitly asks to review an AI coding process, delivery records, rollout status and evidence gaps; not for resume rewriting, source-code walkthroughs or mock interviews.
Provides structured formats and techniques for running productive group sessions, from standups to multi-day workshops. Covers format selection, agenda design, participation management, decision methods, and handling difficult dynamics. Use when running meetings, workshops, brainstorms, design sprints, retrospectives, or team decision-making sessions, or when user mentions facilitation, workshop design, meeting patterns, session planning, or effective collaboration.
Designs service objectives for a Salesforce Field Service scheduling policy via a structured trade-off interview. Guides the user through objective selection and derives weights by establishing crossover equivalences against Minimize Travel (the anchor). Produces a finalized weight table with penalty-rate interpretation and a plain-English policy summary. Use this skill when a user wants to design or weight Field Service scheduling service objectives; called after work rule design and delegates to sfs-sobject-create for record creation.
Search, install, update, and remove third-party Agent Skills from skills.sh or any GitHub/GitLab repo via the `npx skills` CLI. Use when the user wants to "find a skill", "install a skill from github", "search skills.sh", or add third-party capabilities to Claude Code/Cursor/other agents. Not for authoring new skills (see create-skill).
Query Firecrawl Research Index paper endpoints for topic discovery, source metadata, question-matched passages, and citation-neighbor expansion. Use when a researcher explicitly asks for Firecrawl Research or its hosted arXiv and biomedical paper records.
Query Fireflies.ai meeting transcripts, meeting notes, summaries, contacts, channels, AI meeting analytics, AskFred, audio uploads, and webhook signatures through its GraphQL API. Use when a user mentions Fireflies, Fireflies.ai, meeting transcripts or notes stored in Fireflies, AskFred, or Fireflies webhooks. Do not use for local audio transcription, calendar management, or meetings that are not Fireflies data.
Plan, execute, or review Flutter and Dart SDK upgrades, dependency resolution, lockfile changes, package breaking changes, and compatible native toolchain migrations. Use when versions or compatibility are the task; route ordinary Dart refactoring to dart-language, security audits to flutter-security, and release artifacts to flutter-build-release
An intelligent formula normalization skill for standardizing mathematical formula formatting, checking symbol consistency, and converting formula styles. It also generates general templates for describing comparisons of classic algorithms in academic theses. Use for normalizing formulas in Markdown documents, checking symbol consistency throughout a document, and academic writing such as algorithm comparisons.
Best practices for modern Fortran (2003/2008+) scientific and numerical computing, covering modules, explicit interfaces, kind parameters, memory safety, and testing. Use when writing or reviewing Fortran source (.f90/.f95/.f03/.f08), defining modules and derived types, choosing numeric kind parameters, working with allocatable arrays, setting up a Fortran build with CMake or fpm, or writing unit tests for numerical code.
Scaffold, adapt, validate, and maintain example-rich full-stack product documentation: 10 product-level documents, 7 version documents, optional module PRD/Stitch/UI triplets, 5 delivery documents, and a detailed project README template family. Use when users ask to initialize a documentation repository, create product or version plans, write PRDs and architecture/UI documents, preserve and adapt detailed examples, audit document structure, or improve an existing product-docs tree, including Chinese requests such as 初始化文档、产品文档、写规划文档.
New listing DD and event radar via gate-cli (info/news/cex): listings, fundamentals, risk, sentiment, tape, LaunchPool calendar; optional first spot/Alpha order after Action Draft + Y/N. Use this skill whenever the user asks about new listings, pre-listing research, launchpool, rug checks, or a first buy on a new asset. Trigger phrases include 'new listing', 'due diligence new coin', 'launchpool calendar', 'listing announcement', 'is it a rug', 'first buy spot'.
Expert Godot 4 game developer specializing in GDScript, the node/scene system, signals, resources, and engine-native patterns. Provides deep knowledge of Godot's unique architecture, performance optimization, and best practices for building games from simple prototypes to production-ready releases. Use when "godot, gdscript, godot 4, godot engine, build a game with godot, godot scene, godot node, godot signal, godot resource, godot tilemap, godot physics, godot animation, godot ui, godot multiplayer, godot, gdscript, game-engine, game-development, 2d-games, 3d-games, open-source" mentioned.
Use when working with Halo CLI authentication, login, bearer token or basic auth, profile setup, profile switching, current profile inspection, or fixing missing keyring credentials. Trigger this skill whenever the user needs to log into Halo, manage Halo CLI profiles, switch profiles, or diagnose authentication issues.
Use when moderating Halo comments or replies, creating official replies, managing notifications, listing unread notifications, deleting notifications, or marking notifications as read. Trigger this skill whenever the user mentions Halo comments, comment replies, or notifications in a terminal context.
Use when operating Halo themes, plugins, attachments, backups, or moments from the terminal. This includes install, upgrade, activate, enable, disable, upload, download, create, delete, reload, and batch maintenance flows. Trigger this skill whenever the user mentions Halo themes, plugins, attachments, backups, moments, or any Halo CMS maintenance operation in a CLI context.
Use when searching public content on a Halo site with Halo CLI. This includes keyword search, site URL based search, result limits, or any search that does not require authenticated console access. Trigger this skill whenever the user wants to search a Halo site from the terminal, even if they do not explicitly mention 'search'.
Use when authoring a NEW Datex Studio hub configuration (configurationTypeId=2) on a branch — filter-driven container with tab grids, role-gated tabs, toolbar buttons. Owns the dead-wiring trap (hub filter -> tab configParameters -> grid inParams must stay in sync), filter-driven-tab pattern, and toolbar button wiring. Triggers: "create a hub", "add a tab to xxx_hub", "add a filter", "add a toolbar button to the hub", "role-gate a hub tab", "filter-driven tabs", "tab grid ignores filter value", "hub won't open", "dead wiring between hub filter and grid". For modifying an existing hub, see hub-editor.
Edit, audit, or draft writing to remove recognizable AI phrasing and structural habits while preserving the writer's meaning and personal voice. Use when the user asks to humanize writing, remove AI slop, make copy sound natural, audit a draft for AI patterns, or invokes human-speak
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Reviews generated implementation plans against best practices including task sizing (30m-2.5h), style anchors, TDD requirements (AI audience), drift prevention (AI audience), and quality constraints. Validates milestones.yaml and task files for completeness, alignment, and development readiness. Adjusts review criteria based on target audience (AI, human, or hybrid).
Guides implementing AES-256 encryption in GCM mode (FIPS 197) for files and data stores at rest, covering key derivation, IV/nonce management, and authenticated encryption. Use when deploying or configuring encryption for data at rest, establishing controls to meet compliance requirements, or reviewing an implementation during a security assessment.
Ability to analyse, design, optimise, and improve systems that integrate people, processes, technology, and resources to meet defined performance, quality, cost, and safety requirements. Includes applying engineering, statistical, and systems methods to model workflows, identify inefficiencies, evaluate trade-offs, and implement improvements across operations and supply chains. Applies across manufacturing, services, logistics, healthcare, and infrastructure contexts and is independent of specific tools or industries, with human accountability retained for decisions, outcomes, and impacts.
Use when the user says 'build internal links', 'improve internal linking', 'fix orphaned pages', or 'create topic clusters'. Analyzes all published content, maps topic relationships, and presents a linking plan for approval before changing anything.
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.