Explore

Build a semantic feature index of the repo via clawpatch map (opt-in). Use when asked to map the repo.

Open a PR with a cognitive-aid body rendered from flow-next spec state via gh. Use whenever asked to make or open a PR in a flow-next repo.

Resolve feedback and CI for one named pull request, then merge when authorized and ready. Emits LAND_VERDICT. Use when asked to land a pull request.

Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.

In a project that uses Flow-Next, use first for a spec id to implement, change, bug, slow code or number to move, cleanup, design choice, issue, or what next. Skip for quick questions or direct work.

Seed or maintain the committed user-POV drive map at .flow/features/ so QA and drive reuse how a user reaches each feature.

Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to navigate sites, verify deployed UI, test web or desktop apps, capture baseline screenshots, drive a sign-in flow, scrape data, fill forms, run an e2e check, or inspect current page state. Triggers on "check the page", "verify UI", "test the site", "test this app", "drive the app", "automate this desktop app", "read docs at", "look up API", "visit URL", "browse", "screenshot", "scrape", "e2e test", "login flow", "capture baseline", "see how it looks", "inspect current", "before redesign", "Electron app", "native app".

Show spec dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should specs run', 'critical path', 'which specs can run in parallel'.

Decision-map discovery for one oversized unclear idea before capture. Resolve one decision per invocation, brief for capture. Use when asked to chart an idea or work a chart decision.

Save the current conversation as a source-tagged flow-next spec, then offer review or editing. Use when asked to capture this as a spec.

Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.

Manage .flow/ tasks and specs. Use for show or list tasks, task status, what is ready, show fn-N. NOT for planning or executing (use the plan and work skills).

Check that a microphone is usable for Horizon dictation and report which layer is at fault — no signal, bad level, or a genuine model/accent limit. Use when dictation produces wrong, unrelated, or empty text.

Manage Horizon native VNC Device panels and drive isolated local desktops for simulators and native application tests through device_panel and the horizon-device CLI/MCP. Device panels work on every platform; driving an isolated desktop works on Linux with X11 only. Browser pages use horizon-browser.

Inspect Horizon cloud offers and companions, read or act on the cloud list of your workspace, see or propose changes to its Upkeep of Dependabot pull requests, control explicitly authorized companion workers, use a worker Local Network Bridge, or ask for GitHub access from a cloud worker through public MCP tools.

Cast Horizon panels, workspaces, cloud cards, or its main window to Apple TV through the public cast MCP tool. Use for receiver discovery, pairing, casting status, and stopping casts.

Control, inspect, or audit Horizon browser panels through public browser_* MCP tools.

Run or inspect declared iOS and Android native app tests through Horizon device_test_run and app_* MCP tools. Use for App Automate sessions, native actions, evidence, and cleanup; desktop fixtures use horizon-device.

Sets up and runs skillgrade evaluation pipelines for AI agents and Agent Skills. Use when initializing eval configurations, running trials, reviewing results, exporting reports, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.

Authors deterministic, LLM rubric, and human graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, setting up human review workflows, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.

Guidelines for using modern Angular APIs (signals, inject, control flow)

SEO·AEO·GEO·LLMO·NEO(네이버) 다섯 레인을 진단하고 직접 구현하며, 인용되는 콘텐츠를 계속 생산하는 서브 블로그·콘텐츠 운영 파이프라인까지 세팅하는 스킬. 사이트를 검색엔진·답변엔진·생성 AI·네이버 AI 브리핑이 인용하는 1차 소스로 만든다. "SEO 해줘", "AI에 인용되게 해줘", "네이버 노출 늘려줘", "llms.txt 만들어줘", "블로그 만들어줘/글 써줘", "콘텐츠 백로그·캘린더 잡아줘", "낡은 글 갱신해줘" 류 요청에 사용. Use for "audit my site's SEO", "get my site cited by ChatGPT/Perplexity/AI Overviews", "improve search visibility", "create llms.txt", "answer engine / generative engine optimization", "set up a blog that gets cited", "content backlog / calendar / refresh", and any AI-search-visibility request.

Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.

Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council. Use when the user wants to design, build, or set up an agent loop, iterative agent workflow, self-review loop, LLM-as-judge loop, multi-model council, reviewer/judge gate, or /goal-style looping process. Start from a named pattern template (security-scan, code-review, bug-hunt, docs-sync, research-synthesis) or from a blank interview. Guide goal refinement, typed verification criteria, reviewer and judge selection, privacy boundaries, termination guards, no-progress stops, and lightweight observability, then emit a RUN_IN_SESSION.md handoff prompt plus portable loop.yaml, loop.resolved.json, LOOP.md, and run-loop.py.

Reviews completed implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved corrections.

Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow

Create work plan from design document and obtain plan approval

Orchestrate the complete implementation lifecycle from requirements to deployment

Orchestrate full-cycle implementation across backend and frontend layers

Execute materialized fullstack task files with layer-aware agent routing

Execute from codebase-scoped analysis through optional ADR decisions to complete Design Doc approval

Execute materialized task files in autonomous execution mode

Add integration/E2E tests to existing codebase using Design Docs

Guides subagent coordination through implementation workflows. Use when orchestrating multiple agents, managing workflow phases, or determining autonomous execution mode.

Update existing design documents (Design Doc / PRD / ADR) with review

Proposes repository-specific quality policy for implementation and review and, after confirmation, creates or updates docs/project-context/quality.yaml. Use when asked to create or update a repository quality profile.

Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.

Create frontend work plan from design document and obtain plan approval

Execute from repository evidence through applicable UI Spec and optional ADR decisions to complete frontend Design Doc approval

Execute materialized frontend task files in autonomous execution mode

Adjust an already-implemented UI in-session with verification against the design source

Investigate problem, verify findings, and derive solutions

React/TypeScript frontend development rules including type safety, component design, state management, and error handling. Use when implementing React components, TypeScript code, or frontend features.

Language-agnostic testing principles for choosing which tests a change needs, test quality, and proof ownership, with frontend and browser E2E implementation references. Use when writing tests, deciding test scope, or reviewing test quality.

Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure. Use when a requirement enters a workflow, before design begins.

Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.

Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria. Use when designing integration tests, E2E tests, or reviewing test quality.

Implementation strategy selection framework. Use when planning implementation strategy, selecting development approach, or defining verification criteria.

Applies React/TypeScript-specific technical decision criteria, anti-pattern detection, debugging, and frontend quality gates. Use when reviewing components, hooks, browser behavior, or frontend implementation completeness.

Records where resources outside the repository live (design source, design system, API schema, IaC source, secret store) and how design, implementation, and verification reach them. Use when work depends on an external resource, or when the user mentions design source, design system, API schema, IaC source, secret store, or canonical source.

Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.

Language-agnostic coding principles for maintainability, readability, and quality. Use when implementing features, refactoring code, or reviewing code quality.

Applies language-agnostic and backend technical decision criteria, anti-pattern detection, debugging, and quality gates. Use when reviewing general/backend implementation choices, code smells, failures, or implementation completeness.

Set up or tune .codemap/config.json so Codemap focuses on code-relevant parts of the repo. Use when config is missing, boilerplate, noisy, or mismatched to the stack.

Analyze codebase structure, dependencies, changes, cross-agent handoffs, and get code-aware intelligence. Use when user asks about project structure, where code is located, how files connect, what changed, how to resume work, before starting any coding task, when you need risk analysis and skill guidance, or when Codemap should tune project config before analysis.

Use when a Solo task or thread should become an interactive, reviewable, self-contained HTML artifact for progress/status, review/decision, or comparison/leaderboard work inside Solo.

Run the real fixed PM arithmetic case and retain submission evidence.

Turn a feature request into a minimal, file-level implementation plan before any code.

Evolve this harness with Darwin Mode — frozen model, evolving harness (real, sandboxed, safety-gated).

Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.