Skill Library
Every skill and deck in the catalog — search, filter, and open any card.
Afps Status
Summarize AFPS product-workflow progress from existing artifacts and recommend the next concrete skill command
Animation Design Planner
Plan interactive UI animations before implementation with visible motion contracts, lifecycle ownership, accessibility/performance guardrails, and proof gates
Autoresearch Prep
Scaffold a program.md for /autoresearch by auto-detecting codebase signals and interviewing for what can't be inferred
Autoresearch
Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)
Codebase Status
Report what a repository is, what recent conversation history says about it, current application status, and outstanding work
Create Alignment Page
Create or amend a portable HTML alignment review page in a target repo using bundled conventions and skillpacks alignment commands
Fork Idea Branch
Split an idea or active research path into two or more new research product-path stubs after alignment approval; preserves the source path by default and archives it only when --archive is passed
Idea Scope Brief
Shape a rough product or project idea into a scoped brief before customer discovery, market research, specifications, UX, UI, or implementation planning
Init Agentic Skills
Make the base agentic-skills available in a project by installing them project-local with npx skillpacks init, report and fix skill-install drift, clean up legacy user-home installs, and run guided setup for project-local domain packs. Use when Claude needs to enable base skills for a project, repair stale installs, confirm initialization status, remove old global installs, or set up and route domain packs.
Provision Agentic Config
Provision workflow orchestration and agent conventions into project CLAUDE.md and AGENTS.md
Skills
Browse and search all available skills, grouped by workflow stage or activity type
Delegate
Live in-session delegation from Claude to Codex via the approval/delegation packet contract
Plan Phase
Decompose a single roadmap phase into implementation steps, tests, and file-level detail
Roadmap
Scan task pipeline health, build or update the project roadmap, and maintain a priority task queue
Spec Drift
Audit specs against codebase — find unimplemented features, diverged implementations, and undocumented code
Benchmark Agent Review
Review persisted benchmark run outputs with one or more agent graders and report subjective ergonomic quality separately from deterministic benchmark scores
Benchmark Test Skill
Run verify and benchmark tests for one agentic-skills skill, producing pass-rate, latency, cost, and consistency metrics
Destination Doc
Serialize taste-calibration alignment into a lightweight destination document
Taste Calibration
One-question-at-a-time questioning to calibrate operator-agent alignment on intent, taste, and boundaries
Vertical Slice Splitter
Decompose a destination doc or spec into vertical-slice issue cards with a dependency DAG
Compile Central Alignment
Generate a central alignment/index.html table of contents for all alignment pages in the current repo
Upgrade Alignment Pages
Audit and explicitly upgrade generated alignment/*.html review pages to the current local alignment-page standard while preserving page-specific context
Experiment
Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules
Growth Model
Reforge-style growth loop design — acquisition, retention, and monetization loops
Gtm
Go-to-market planning — channel strategy, messaging, pricing, launch plan, and early traction tactics
Hook Model
Nir Eyal engagement loop design — trigger, action, variable reward, investment
Landing Copy
Generate or audit landing page copy grounded in upstream research — hero, benefits, social proof, pricing, FAQ, and CTAs
Metrics
Define success metrics framework — activation, engagement, retention, growth, and business metrics tied to journey stages
Monetization
Research-driven monetization strategy — revenue models, pricing architecture, unit economics, and packaging grounded in ICP and competitive data
Pmf Assessment
Sean Ellis PMF survey design + qualitative signal analysis for post-launch fit measurement
Assumption Tracker
Extract and risk-rank assumptions from research docs — living register of what to validate first
Burn Rate
Estimate monthly burn rate from infrastructure signals and calculate payback period against revenue projections
Cohort Review
Post-launch metrics & funnel analysis — cohort retention, channel performance, and progress against targets from /metrics
Investor Update
Generate structured monthly stakeholder update from current research state, metrics, roadmap, and feedback
Mvp Gap
Evaluate codebase against ICP to identify gaps blocking first sales and retention
Platform Strategy
Expand from a single product into a multi-product platform — map vertical and horizontal growth vectors, score candidates, design validation experiments, and sequence the portfolio
Product Line
Manage the portfolio of product paths — review, activate, archive, restore, promote, fork, and check revisit triggers across the product-path manifest
Reconcile Research
Cross-document consistency audit across research outputs — find contradictions, stale assumptions, and gaps
Repo Glossary
Audit and reconcile the shared project glossary — find stale terms, missing definitions, conflicts, shadows, inheritance gaps, and cross-path divergences across research docs
Retro
Strategic decision retrospective — review research decisions against actual outcomes, update confidence levels
Risk Register
Broad risk assessment — key-person, technical, regulatory, competitive, financial, and execution risks beyond product/market
Runway Model
Financial runway & unit economics tracker — burn rate, revenue trajectory, runway in months, scenario modeling
Scale Audit
Evaluate codebase against enterprise ICP for production readiness, compliance, and multi-stakeholder journey coverage
Feature Pricing Matrix
Feature and pricing matrix competitive analysis - compare capabilities, packages, proof points, and pricing models
Porter Five Forces
Porter's Five Forces competitive analysis - industry structure, rivalry, substitutes, entrants, buyer power, and supplier power
Strategic Group Map
Strategic group map competitive analysis - cluster competitors by market axes and identify segment whitespace
Swot
SWOT competitive analysis - strengths, weaknesses, opportunities, and threats grounded in market evidence
Competitive Analysis
Orchestrator — select competitive-analysis frameworks, run them inline one per session, and synthesize market landscape findings
Five Rings
Revella Five Rings of Buying Insight — map Priority Initiatives, Success Factors, Perceived Barriers, Decision Criteria, and Buyer's Journey per ICP candidate to understand B2B buyer decision psychology
Four Forces
Moesta Four Forces of Progress — map Push, Pull, Anxiety, and Habit forces per ICP candidate to identify switching catalysts and barriers
Jtbd Needs
Ulwick/Christensen JTBD — identify jobs, map desired outcomes, score importance vs satisfaction, and segment ICP candidates by unmet needs
Pmf Engine
Vohra/Supan PMF Engine - evaluate existing user data with Sean Ellis PMF signal, very-disappointed segmentation, retention/usage evidence, and High-Expectation Customer synthesis
Seven Dimensions
Lincoln Murphy 7 Dimensions of ICP — score ICP candidates on Readiness, Willingness, Ability, Success Potential, Acquisition Efficiency, Ascension Potential, and Advocacy Potential for composite fitness scoring
W3 Hypothesis
Schwartzfarb W3 — define WHO/WHAT/WHY for each ICP candidate, generate disproval hypotheses, and validate via targeted research
Customer Discovery
Orchestrator — detect pre-product vs product-exists mode, bootstrap ICP candidates, recommend customer-discovery frameworks, synthesize outputs into unified ICP research
Customer Feedback
Ingest and synthesize customer feedback — categorize findings against ICP and journey map, maintain a running log
Enterprise Icp
Enterprise multi-stakeholder discovery — map personas, deal-killers, and the evaluation-to-renewal lifecycle
Lean Canvas
One-page Lean Canvas business model synthesis (Ash Maurya)
Category Design
Play Bigger category creation — category diagnosis, naming, POV development, ecosystem mapping
Jtbd Positioning
Jobs-to-be-Done positioning analysis — identify primary job, map functional/social/emotional dimensions, position around job outcome
Moore Positioning
Geoffrey Moore positioning hypothesis — generate positioning statement using the Crossing the Chasm template
Obviously Awesome
April Dunford Obviously Awesome methodology — competitive alternatives, unique attributes, value mapping, target segment, market category
Strategic Canvas
Blue Ocean strategic canvas — extract competing factors, build value curves, identify eliminate/reduce/raise/create moves
Positioning
Orchestrator — detect market vs product mode, recommend positioning frameworks, synthesize outputs into unified positioning
Value Prop Canvas
Strategyzer-style jobs/pains/gains to features/relievers/creators fit validation
Debug
Investigate a problem, log it to the debug changelog, cross-check past issues, and suggest a non-duplicate fix
Investigate
Validate user claims against codebase and git history, trace to root cause, and propose a fix
Trace
Follow a request end-to-end through the stack from route to database
Migrate
Guide a structural migration or dependency upgrade with a step-by-step plan and verification
Update Packages
Update project dependencies to the latest version that is more than 8 days old, preferring pnpm over npm and enforcing installer age gates
Extract Shared Types
Extract shared type definitions into a dedicated types directory without runtime behavior changes
Quality Sweep
Audit and implement behavior-preserving cleanup across types, dead code, dependencies, errors, and comments
Dead Code
Scan for unused exports, unreachable code, orphaned files, and stale dependencies
Expert Review
Conduct a thorough project-wide code review as an expert panel, cross-referencing specs, changelogs, and design documents
Regression Check
Run a comprehensive health check across the monorepo after completing a phase or major change
Slim Audit
Audit codebase for opportunities to reduce lines of code while preserving functionality, performance, and quality
Handoff
Generate a project-level context snapshot for resuming work in a fresh session
Content Programming
Design an evidence-backed channel programming plan across pillars, formats, cadence, roles, and measurement without writing scripts
Creator Evidence Schema
Define normalized creator evidence records, raw evidence paths, confidence fields, privacy notes, and collection constraints for multi-platform audits
Creator Metrics Review
Review creator-media performance over time using raw YouTube evidence, portfolio metrics, programming goals, and explicit follow-up decisions
Creator Platform Capability Matrix
Map creator platforms to free/manual evidence sources, available fields, audit depth, operational risk, and recommended next skill
Creator Positioning
Define a creator or founder-media channel's audience promise, category, differentiated wedge, proof, and anti-positioning
Creator Presence Dossier
Build a repo-backed Markdown dossier of a creator's public professional presence, career arc, proof assets, platform roles, and next strategy route
Product Led Media Map
Map a product or company into founder-led YouTube media themes, proof assets, demos, trust moments, and content roles
Research Directory Conventions
Reference standard for creator-media research directory layout — platform-scoped nesting, handle-scoped data, dated snapshots, archive-before-replace, and README indexing
Series Spec
Specify a repeatable YouTube series format with audience job, episode shape, evidence requirements, packaging rules, and success metrics
Conversion Map
Plan evaluation, trial, pricing decision, objections, buyer roles, and conversion triggers
Expansion Map
Plan account expansion, upgrades, seat growth, referrals, advocacy, and land-and-expand paths
Customer Journey Canvas
Stickdorn customer journey canvas — stage×touchpoints×actions×emotion×backstage×pain×opportunities grid
Experience Map
Adaptive Path experience map — emotional arc with doing/thinking/feeling layers, pain/delight moments, and channel transitions
Jtbd Timeline
Moesta/Switch JTBD timeline — map first thought→passive→active→deciding→consuming→satisfaction with push/pull/anxiety/habit forces
Service Blueprint
Shostack service blueprint — map front-stage/backstage/support/evidence lines and identify operational gaps
User Story Map
Jeff Patton user story map — activity→task→story hierarchy with release slicing and walking skeleton identification
Journey Map
Orchestrator — detect pre-product vs product-exists mode, recommend journey-mapping frameworks, synthesize outputs into unified lifecycle overview
Lifecycle Metrics
Define stage metrics, instrumentation needs, and evidence gaps across onboarding, conversion, transaction, retention, and expansion
Onboarding Map
Plan signup, setup, activation, first success, onboarding drop-offs, and time-to-value for each lifecycle persona
Retention Map
Plan repeat-use loops, lifecycle triggers, churn risks, recovery paths, and retention signals
Transaction Map
Plan purchase, checkout, payment, fulfillment, receipt, refund, dispute, and trust-state flows
Devtool Adoption
Use only for developer-facing products; plan adoption loops, examples, templates, community, and proof artifacts
Devtool Docs Audit
Use only for developer-facing products; audit docs for quickstart clarity, examples, API reference, troubleshooting, and migration paths
Devtool Dx Journey
Use only for developer-facing products; analyze install, quickstart, first success, debugging, and production adoption journeys
Devtool Integration Map
Use only for developer-facing products; map integrations, ecosystems, setup surfaces, and compatibility constraints
Devtool Monetization
Use only for developer-facing products; design pricing, packaging, limits, open-source strategy, and team conversion
Devtool Positioning
Use only for developer-facing products; position against alternatives by workflow, ecosystem, trust, and switching cost
Devtool User Map
Use only for developer-facing products; map users, buyers, champions, contributors, and operational stakeholders
Devtool Workflow
Use only for developer-facing tools, libraries, SDKs, CLIs, APIs, and infrastructure products
Hygiene
Audit project structure for convention violations, missing files, template drift, and cross-platform sync gaps — optionally auto-fix
Reconcile Dev Docs
Reconcile development docs by auditing roadmap, todo, history, phase archives, specs, git history, and code reality
Exec
Plan the next incomplete step (or full phase with --phase flag) from the plan, then enter plan mode for user approval before executing
Ship End
Wrap up the current session — update docs, commit, and push
Ship
Ship current work (update docs, commit, push, deploy) and optionally plan the next step
Patch Exec Profile
Audit and fill missing lane metadata (Mode, Depends on, Owns, Branch) in agent-team and implementation-safe execution profiles in tasks/todo.md
Game Audience
Use only for video game projects; identify player segments by taste, behavior, platform, genre affinity, and motivation
Game Comparables
Use only for video game projects; research comparable titles, tags, prices, player signals, and positioning patterns
Game Core Loop
Use only for video game projects; analyze moment-to-moment, session, progression, and retention loops
Game Fantasy
Use only for video game projects; define the emotional promise, player fantasy, vibe references, and hook
Game Genre Map
Use only for video game projects; map genre conventions, player expectations, review complaints, and anti-patterns
Game Launch
Use only for video game projects; plan Steam launch, festivals, creator outreach, demo timing, community, and wishlist targets
Game Playtest Metrics
Use only for video game projects; define playtest metrics for time-to-fun, replay, confusion, quit points, sharing, and retention
Game Prototype Test
Use only for video game projects; design playable prototype tests and success criteria for fun, clarity, and replay
Game Roadmap
Use only for video game projects; sequence prototype, vertical slice, demo, store page, festival, launch, and post-launch milestones
Game Store Page Test
Use only for video game projects; plan Steam/store page, capsule, trailer, screenshot, tag, and wishlist validation
Game Workflow
Use only for video game projects; route research, validation, roadmap, metrics, and launch work through the game pack
Commit And Push By Feature
Commit and push all changes to GitHub grouped by logical feature/function buckets with conventional commit messages
Sync
Pull latest changes from remote and report status
Guide
Click-by-click instructions for manual blockers — DNS, OAuth, signups, and other GUI-dependent tasks
Uat Guide
Expand a UAT journey into click-by-click tester instructions, then update the result log on completion
Upgrade Interrogation Pages
Audit and explicitly upgrade generated interrogation/*.html round pages to the current local interrogation-page standard while preserving page-specific context
Quiz Me
Adversarial one-question-at-a-time questioning to verify deep reading comprehension of alignment pages, specs, or any document
Affected
Analyze which monorepo packages and apps are affected by current changes
Mono Detect
Detect pnpm workspace structure, optional Turborepo overlay, package metadata, and internal dependency graph for monorepo-aware skills
Mono Exec
Augment the standard exec lifecycle with monorepo detection, lane-spec generation, guard validation, and package-scoped dispatch
Mono Guard
Validate monorepo lane specs before dispatch and verify integrated changes stay inside declared lane boundaries
Mono Plan
Detect monorepo structure, identify shared chokepoints, and generate safe parallel lane specs aligned to package boundaries
Mono Ship
Augment the standard ship lifecycle with monorepo package-scoped and transitive-dependent validation
Scaffold
Generate a new package or app in the monorepo following established project conventions
Ord Align
Validate whether an OSS tool is worth building through staged namespace, existing-solution, and feasibility review
Ord Scan
Scan for OSS tool opportunities from npm gaps, GitHub trends, and developer pain points
Ord Ship
Publish to npm, create README, set up repo, and log the shipment
Ord Traction
Check post-launch adoption for a published ORD package and recommend iterate, graduate, or archive
Brainstorm
Evaluate the codebase and suggest ideas to explore with /feature-interview
Build Ui Screens
Build the visual UI screens for one approved UI branch as an ordered element-batch loop — one flow step at a time, with a per-batch visual checkpoint and a minimum-UI stop — using fake, fixture, local, or in-memory data, then hand the screens to logic-wiring to make them clickable.
Consolidate Prototypes
Converge evaluated prototype branches into one approved MVP, resolve UAT findings, hand off to post-prototype research, and let spec-interview own production-ready approval
Consolidate Variations
Deprecated compatibility alias for consolidate-prototypes; use the primary prototype-consolidation skill instead
Create Ui Experiment
Deprecated compatibility alias for build-ui-screens; use the primary visual UI screen builder instead
Design Inspirations
Gather UI/UX design inspiration once via web research — named patterns, interaction/layout conventions, component-library references, and annotated links — into a durable cited brief that feeds the prototype-phase design skills
Design System
Extract or scan design tokens from a consolidated UI spec or existing codebase and produce a DESIGN.md file following the Google Labs Stitch format — machine-readable YAML frontmatter with prose rationale sections
Eval Ideas
Loop feature-interviews over a brainstorm idea set and consolidate survivors into the roadmap
Feature Interview
Interview a feature idea with evidence-backed alignment, then decide whether to create/update docs, specs, roadmap, or tasks
Key Moments
Rank a topic's user-flow branches by proof priority (value × risk × frequency) right after user-flow-map, ordering the branches, gating variation breadth, and promoting or pruning flows so state-model and ux-variations grow the tree in proof order — writes only existing flow-tree ordering fields, no schema change.
Logic Wiring
Wire approved UI screens into a clickable, state-backed prototype — make the visual screens from build-ui-screens reachable and interactive, plus runnable logic for CLI/API/infra projects, so each variation's flow can be walked end-to-end before consolidation
Prototype
Deprecated compatibility alias for logic-wiring; use the primary clickable/state-backed wiring skill instead
Spec Interview
Post-prototype production deep dive — walks through consolidated prototype screen by screen to extract production specifications
State Model
Orchestrator — author the flow-anchored logical domain model (entities, state machines, events/commands, read models, policies, logical contracts) from an approved user-flow map, running one domain-modeling framework per session, before UX variation work
Ui Interview
Interview page by page to define a complete UI specification, including layout, hierarchy, controls, links, spacing, sizing, responsive behavior, visual states, and implementation-ready interface details — supports a requirements-only mode that establishes data, actions, and states without locking layout or component decisions
User Flow Map
Turn a high-level product concept, positioned goal, or goal sequence into screen flow structure with entry points, decisions/actions/states, branches, failure paths, and low-fidelity wireframe guidance before UI/spec/prototype work
Ux Variations
Interview and plan multiple UX and UI variations for a product, page, or flow, including onboarding, typical workflows, sharing, collaboration, return use, and interface alternatives users can compare before locking a direction — and concrete visual/layout UI variations (component choices, spatial arrangements, information density)
Dogfood
Derive owner/operator dogfood scenarios from product evidence and active-use cadence, then produce adoption instructions and manual evaluation checks
Uat
Create user acceptance test journeys from a target user's perspective, with role-based scenarios, acceptance criteria, and evidence capture
Clone Spec Store
Build a canonical lawful-functional-parity spec store for N software ideas in any domain, then use portfolio gates to seed only implementation-ready or explicit scaffold-only downstream repos.
Skill Inventory
Inventory downstream repository Claude and Codex skill installs from a control-repo manifest, classify managed local skill-copy drift against canonical agentic-skills sources, and produce report-only Markdown or JSON guidance without refreshing, deleting, or mutating downstream repos.
Project Fleet
Orchestrate a central control repository that plans, provisions, tracks, and advances many related downstream repositories or work items with guarded batches, blocker handling, and productive fallback work.
Spin Off
Extract a bounded part of the invoking codebase into a new GitHub repository with private and public-OSS readiness gates
Spinoff Idea
Derive a portable product-idea kickoff prompt from the invoking repository for use with $idea-scope-brief in a different repository. Use when a repo suggests an adjacent product, SaaS, devtool, library, workflow, or experiment worth briefing elsewhere, but the user wants an idea prompt rather than code extraction or repo creation.
Branch Lifecycle
Evaluate feature branches and decide whether to merge, salvage, keep open, or delete based on branch health, PR status, and stale-branch heuristics
Deploy
Deploy the project to a target environment (defaults to staging) with deployment history tracking
Release
Version bump, generate changelog, tag, and prepare a release
Video Build
Transform an approved video script into a Remotion build specification with scaffolded project directory, compositions, scene components, and render config
Video Script
Draft a scene-by-scene video script with timing, visual direction, narration, and source attribution from upstream creator-media artifacts
Youtube Format Research
Break down a YouTube video's format, visual system, pacing, editing grammar, motion, audio, and Remotion-ready production patterns
Bootstrap Repo
Initialize or reset a repository README and agent workflow docs from a short project brief
Env Setup
Scaffold the local env file with required variable stubs from .env.example and code, open it for the user to fill, and verify completeness by key names only — never reading secret values
Report Website
Convert one Markdown report or a collection of documented Markdown outputs into clean JSX routes for a polished, readable frontend website
Research Roadmap
Scan research and documentation health, then maintain a priority documentation queue
Analyze Sessions
Analyze Claude Code and Codex session history for cross-session trends, recurring patterns, and automation opportunities
Prompt History Backfill
Scan Claude and Codex conversation history for skill invocation prompts missing from repo prompt history and report or backfill them safely
Session Triage
Investigate one immediate session, correction, repo incident, or skill failure and recommend a verified fix
Create Agentic Skill
Create or update a repo-managed skill inside this agentic-skills checkout under base/claude and optionally base/codex, then validate, commit, and push it
Create Local Skill
Scaffold a new user-local skill in ~/.claude/skills (and optionally ~/.codex/skills), then offer to promote it to a personal fork of agentic-skills
Skill Interview
Interview the user to define the characteristics of a skill they want created
Targeted Skill Builder
Build or update one specific skill from a concrete workflow gap, correction, or repeated bad recommendation
Decommission
Systematically tear down and remove a service, package, or infrastructure component
Desk Flip
Autopsy a stuck project, extract salvageable artifacts, and route to a fresh start via /bootstrap-repo reset or new-repo bootstrap
Vard Align
Quick feasibility and novelty check — go/no-go decision for this week's build
Vard Scan
Scan for viral app opportunities from trends, gaps, and user pain points
Vard Ship
Deploy the app, create landing page, set up analytics, and log the shipment
Vard Traction
Check post-launch traction for a shipped VARD app and recommend iterate, graduate, or archive
Icon Handler
Audit and apply project-root icon assets to favicon, app icon, Apple touch icon, and manifest surfaces
Youtube Audit
Analyze a YouTube channel with evidence-first metadata, transcripts, performance fields, portfolio shape, and repeated content-quality patterns
Youtube Cadence Diagnosis
Diagnose YouTube publishing cadence, gaps, streaks, and post-gap performance effects against channel and peer evidence
Youtube Channel Audit
Run an evidence-first YouTube channel audit that captures raw metadata/transcripts, performance fields, portfolio roles, and repeated content patterns
Youtube Competitive Research
Analyze why an external YouTube video performed well and extract evidence-backed competitive lessons, positioning gaps, and adaptation opportunities
Youtube Concept Research
Research a proposed YouTube video concept against successful direct and adjacent content, then extract evidence-backed lessons, concept variants, packaging directions, and differentiated execution guidance
Youtube Derivative Cuts
Plan a prioritized derivative content slate from one long YouTube source video using metadata, transcript, chapters, audits, portfolio evidence, and available metrics
Youtube Description Optimizer
Audit, draft, or template YouTube descriptions and metadata for promise-match, search clarity, CTA hierarchy, links, chapters, hashtags, and upload readiness
Youtube Peer Benchmark
Benchmark a YouTube channel against peers — discover comparable creators, pull real metrics via yt-dlp, compare performance at equivalent stages, and diagnose whether the gap is quality, volume, format, or conversion
Youtube Portfolio
Map a YouTube channel's video portfolio by archetype, strategic role, performance concentration, and cleanup or refresh opportunities
Youtube Search Positioning
Find YouTube search opportunities by comparing channel topics against query demand, ranking competition, and underserved results
Youtube Title Thumbnail Audit
Audit YouTube titles and thumbnails against channel performance and peer packaging patterns
Youtube Vid Research
Research one or more external YouTube videos for context, claims, structure, examples, terminology, and transferable takeaways
Youtube Video Audit
Audit one YouTube video in depth using public metadata, transcript/content evidence, release timing, comments, and optional owner analytics
Youtube Video Prelaunch Audit
Audit unlisted or pre-release YouTube videos before public launch for edit readiness, polish, packaging, title, description, chapters, publish settings, launch timing, and social cross-sharing strategy
Youtube
Intent-based router and play composer for youtube-ops skills — classifies what the user needs and recommends a single skill or queues a multi-step play for /exec