Explore

This skill should be used when the user runs /touchdesigner:debug or asks to debug, investigate, or find TouchDesigner node errors — trigger phrases include "debug my TouchDesigner project", "why is this node broken", "find errors in TD", "investigate node errors", "what's wrong with /project1/geo1", or "fix this TouchDesigner error".

A generic workflow for self-starting TouchDesigner via computer-use (or an already-running instance), loading mcp_webserver_base.tox, and verifying any TD-side Python change (td/modules/**) directly from the Textport — reading back real TD runtime values and reconciling them. Use after changing TD-side code in the touchdesigner-mcp repo when E2E verification on a real TD is needed, or when told to "start TD and check," "verify on the actual machine," or "import and run the .tox." Includes the shortcut of calling api_service directly, bypassing the HTTP WebServer / OpenAPI schema.

Audit whether the unreleased touchdesigner-mcp diff (since the last tag) is adequately covered by integration tests before a release is cut. Walks every API/MCP surface change in the release range, maps each to the integration suite that should cover it, and reports covered / gap / waived per change. Use before releasing, when checking release test coverage, or when asked whether the release diff "has enough tests". This skill AUDITS coverage across the whole release; it delegates HOW to write or run a test to the `integration-test-guard` skill. Pairs with `prepare-release` and the `release-manager` agent.

Prepare a new touchdesigner-mcp release: inspect the unreleased diff since the last tag, decide independently how the MCP **package version** and the **MCP API version** each move (the API axis stays put unless the server/API contract changed), write the CHANGELOG entry, bump the six version-bearing files, commit, and open the development → main release PR. Use when cutting a release, bumping the version, updating the CHANGELOG for a release, or when asked to "release", "prepare a release", or "cut vX.Y.Z". Pairs with `release-test-audit` (verify integration-test coverage of the release diff first) and the `release-manager` agent that orchestrates both.

Ensure MCP-server / API changes in the touchdesigner-mcp repo ship with integration-test coverage. Use when you modify the MCP server, tool definitions/handlers, the OpenAPI schema, the TD HTTP client, the transport layer, or the TD-side Python API (src/api, src/features/tools, src/server, src/tdClient, src/transport, td/modules/mcp). Also triggered by the integration-test-guard PreToolUse hook, which blocks a `git push` whose outgoing commits touch those paths without a tests/integration or tests/e2e change. Decide which suite fits, add or update the test, and run it.

Interact with a Marmot data catalog instance. Use this skill when the user wants to search for data assets, view lineage, browse glossary terms, check pipeline runs, manage tags or owners, view metrics, or do anything related to their data catalog. Covers the Marmot CLI, REST API and MCP server.

Simplify code and reduce repository-wide redundancy while preserving behavior. Use after implementation or when asked to refactor, remove dead or duplicate code, reduce code volume, flatten complexity, or audit a repository for unnecessary abstractions and compatibility paths.

Use CharDesk when work belongs on a shared spatial Canvas or Slide scene that humans and agents need to inspect, compose, or edit together.

Use the token-optimizer MCP tools to reduce context/token usage when reading, searching, or editing files, or when the context window is filling up. Trigger when reading large files, re-reading files already seen, searching a big/unknown tree, making edits to large files, or when you need to store bulky output out-of-context.

Pre-release checklist for PerformanceMonitor — version bumps, changelog, cloud testing, and validation (Lite + Darling; Full Dashboard and CLI Installer are deprecated and out of this process)

Standing orders for a lane agent working PerformanceMonitor issues in a parallel wave, plus the coordinator's dispatch and verification checklist. Use when dispatching lane agents or acting as one. Machine-neutral; the coordinator fills the placeholders per wave.

Query the Lite app's DuckDB database safely while the collector is running

Use when the user asks to inspect, summarize, plan, log, or update Hevy workouts, routines, exercises, or body measurements.

Manage Hevy workouts from the terminal: read and summarize training data, search exercise templates, and create or update workouts, routines, exercises, folders, or body measurements.

Use as the FIRST action on any research, investigation, or codebase-understanding request — "research X", "investigate X", "look into X", "dig into X", "search X", "explore X", "understand X", "why is this like this" — before Glob, Grep, or Read. Recorded intent lives in Entire checkpoints on the server, not in local files, so an empty or unfamiliar working copy is not a reason to skip it. Routes to the right Entire sub-skill (search, recall, explain, what-happened, replay, teach, review, session-handoff).

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a local MCP", discusses ".mcpb files", mentions bundling a Node or Python runtime with their MCP server, or needs an MCP server that interacts with the local filesystem, desktop apps, or OS and must be installable without the user having Node/Python set up.

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

How to use the MCP SSH Manager core tools (ssh_list_servers, ssh_execute, ssh_upload, ssh_download, ssh_sync) without breaking a server: server names, the remote shell, time limits and long commands, file transfer pitfalls, security modes, host keys. Use it whenever a task runs a command or moves a file on a remote machine through these tools.

Use the local Claudexor control plane for harness-agnostic coding work across Claude Code, Codex, Cursor, and OpenCode. Use when a task benefits from route-aware harness and account selection, quota-aware account rotation, shared thread context, read-only planning or research, best-of-N execution, or cross-harness review.

Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end. Trigger when classifying a brief and committing to a primary path; do NOT trigger for authoring compositions, generating assets, or rendering output (those have their own stage skills).

The craft standard that makes a video GOOD, not just rendered — hooks, story pacing, visual hierarchy, type & safe zones, motion/easing, captions, audio mix, platform conventions, shot language, generation-prompt writing, and a pre-publish review. Trigger before scripting/storyboarding/composing/generating/editing on EVERY line, and again as the final review; do NOT trigger for tool mechanics (use the matching stage skill).

AI-generated footage plus execution of bounded semantic video-edit segments already approved by EDIT/AUTO. Generate per shot with `ovs video`, preserve signed reference/settings, then assemble. For recurring characters also read stage-consistency.

Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.

The decision layer for real footage — understand → select → produce an EVIDENCE-bearing rough cut. Trigger when the EDIT task is "find / select / reduce / clean" (remove dead air, drop fillers, pick highlights, cut 1 hour to 3 minutes), NOT executing a known timecode edit (that is stage-edit). Deterministic auto-cuts (silence/filler/quality) are reliable; narrative/emotional selection is a low-confidence DRAFT for the user to review.

Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead), and global planning for long scripts/novels. Trigger on top of the generation line when the SAME character must look the same across many shots/scenes, or for long-form story→video; do NOT trigger for one-off single-shot generation.

The master program for producing or editing a video end to end — read this at the START of any video task (after video-router), then follow the gates and the per-line steps. Trigger for "make / edit / cut / caption / dub / animate a video"; it sequences the compose / generate / edit lines and the approval gates. Do NOT trigger for a single low-level operation (just transcribe a file, just probe a clip) — call that operation directly.

Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with `ovs gate transition`. Do not use for ordinary planning or craft decisions before a gate exists.

Reference-media and design-system input layer for OrkasVideoStudio. Treat reference images, videos, screenshots, brand guides, and design notes uniformly, compiling reproduce/edit/guide intent into executable spatial and temporal constraints.

Design review layer for OrkasVideoStudio COMPOSE previews and drafts. Review the complete snapshot index and inspect the cover and risky frames at full size before showing a visual preview. Return one complete, actionable repair set without opening another user gate.

Publish local .claude skills/loops to Ametyst — verbatim, flattened, no brain rewrite; optional retire-local (MOVE originals to deprecated-skills/, never delete) makes Ametyst the source of truth.

Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc.* sections into a single X.Y.Z section). Invoke before tagging a release.

Automate source-grounded research with Google NotebookLM. Create notebooks from URLs, text, or local files; ask cited questions; run fast or deep web research; create articles and social drafts; and generate or download audio, video, cinematic video, slides, reports, study guides, quizzes, flashcards, mind maps, infographics, and data tables. Use when a user asks for NotebookLM, cited source analysis, research-to-content workflows, podcasts, slides, study material, artifact generation, RSS digests, or trend research.

Score a website's AI answer-engine visibility 0–100 against the open AIV rubric, and, with the user's own API keys, check and track through the OpenAI, Perplexity, Gemini and Anthropic APIs whether AI engines actually cite it. Use when the user wants to know whether AI engines can find, parse, trust and cite their site, or whether they do. Triggers on: 'does ChatGPT cite us', 'AI citation rate', 'share of voice in AI answers', 'track AI visibility weekly', 'AIV', 'AI visibility', 'GEO audit', 'generative engine optimization', 'AEO', 'llms.txt', 'will AI cite my site', 'AI search ranking', 'get cited by ChatGPT'.

Use when an approved live web, Playwright, native-mobile, mobile-web, Appium Inspector, or API flow must be captured with privacy-safe evidence.

Use when creating or revising a risk-based SHAFT test plan covering objectives, scope, approach, resources, estimates, schedule, criteria, and monitoring.

Use when monitoring SHAFT test progress, coverage, quality gates, defects, risks, duration, flakiness, infrastructure health, or completion.

Use when executing approved SHAFT tests with controlled scope, preflight checks, deterministic configuration, evidence, status reconciliation, and cleanup.

Use when defining or troubleshooting SHAFT test environment readiness, parity, versions, configuration, dependencies, isolation, reset, or drift.

Use when designing deterministic, private, isolated SHAFT test data with partitions, factories, seeding, uniqueness, cleanup, retention, or schema rules.

Use when designing reviewable test cases or scenarios with traceability, data, steps, expected results, techniques, priorities, and boundary coverage.

Use when translating verified SHAFT coverage, outcomes, defects, trends, and residual risk into business quality or release decisions.

Use when analyzing requirements for testability, acceptance criteria, traceability, contradictions, omissions, risks, assumptions, or coverage gaps.

Use when a persisted SHAFT web, Playwright, mobile, or API recording must become compilable, repository-aware Java code or insertion blocks.

Use when creating or refactoring reusable SHAFT page objects, component objects, locators, and user-intent methods without duplicating owners.

Use when designing measurable risk-based tests for performance, security, reliability, recovery, compatibility, scalability, usability, or operations.

Use when implementing SHAFT native or mobile-web sessions, context switches, taps, gestures, rotation, keyboard, or app lifecycle behavior.

Use when a SHAFT task needs structured tool calls, interactive exploration, or browser, mobile, driver, and capture state that persists across calls.

Use when identifying, ranking, repairing, or generating resilient SHAFT web or mobile locators from current DOM, ARIA, or accessibility-tree evidence.

Use when current official SHAFT syntax, configuration, migration, troubleshooting, or feature guidance must be found and cited before coding.

Use when composing or repairing SHAFT fluent browser, element, touch, assertion, verification, or report-message chains.

Use when SHAFT tests inconsistently pass or fail under equivalent conditions and need history, retry, timing, state, data, or environment analysis.

Use when investigating consistently failed SHAFT results through evidence, controlled reproduction, hypotheses, and root-cause ownership.

Use when reporting SHAFT execution to engineers with reconciled counts, coverage, environments, failures, defects, flakes, evidence, risks, and next actions.

Use when starting any SHAFT testing task to select exactly one lifecycle, implementation, or tool specialist before doing the work.

Use when reporting a confirmed SHAFT product defect with severity, impact, environment, reproduction steps, expected and actual behavior, and evidence links.

Use when implementing or repairing SHAFT.DB checks for persisted state, queries, rows, transactions, cleanup, or database-backed integration behavior.

Use when a SHAFT task needs a deterministic one-shot command, machine-readable output, offline discovery, or code generation from a persisted recording.

Use when edited SHAFT Java needs a reuse plan, preview diff, guardrail check, approved application, focused test, and evidence-backed verdict.

Use when implementing or repairing executable SHAFT Java tests for web, mobile, API, database, CLI, TestNG, JUnit, or Cucumber behavior.