Explore

Generates a project dashboard from MCP work items. Default is a lean, attention-first view: what's in flight, what's blocked, what to do next, what's queued. Use when the user says: project status, what's active, show me the dashboard, work summary, what should I work on, project health, what's blocked, where did I leave off, show items, what's in the backlog, overview, or any request to see or review the current state of work items. Also use at session start when gathering current project context.

Navigates role transitions for MCP work items using advance_item. Shows current role, gate status, required notes, and the correct trigger to use. Use when a user says: advance this item, move to work, start this task, complete this item, what's the next status, why can't I advance, unblock this, cancel this item, or check gate status.

Analyzes the current implementation run — evaluates schema effectiveness, delegation alignment, note quality, and plan-to-execution fit. Captures cross-session trends and proposes improvements when patterns repeat. Use after implementation runs, or when user says 'retrospective', 'session review', 'what did we learn', 'analyze this run', 'how did that go', 'evaluate our process', 'wrap up', 'end of session review'. Also use when the retrospective nudge fires after complete_tree.

Internal, invoked from the orchestration context: drives a schema-typed MCP item through its gate-enforced phases, filling required notes.

Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a tracked GitHub issue (or dwell in review for the maintainer); rejections are recorded and cancelled; deferrals are recorded and left in queue. Use when a user says: review proposals, triage proposals, pending proposals, what proposals are open, adopt proposals, process improvement proposals, accept or reject proposals.

Launcher for the Ralph-style queue drain script — emits the right `node ralph-loop.mjs` invocation based on the user's filter and bounds. The actual loop runs as a Node script that spawns one `claude -p --worktree` per iteration; this skill is the configurator, not the loop. Use when a user says: drain the backlog, ralph the queue, run Ralph loop, work the queue, batch through queue items, autonomous queue worker.

Interactive onboarding for the MCP Task Orchestrator. Detects empty or populated workspaces and walks through how plan mode, persistent tracking, and the MCP work together. Use when a user says "get started", "how do I use this", "quick start", "first time setup", "onboard me", "what can this MCP do", or "help me learn task orchestrator".

Internal, hook-triggered: gathers existing MCP items and schema gate requirements to set the definition floor before planning.

Internal, hook-triggered: materializes MCP items from the approved plan and dispatches implementation.

Internal, invoked from the orchestration context: tier classification, delegation model table, and phase-owner dispatch rules for sizing and dispatching implementation work.

Sets up Task Orchestrator for a project or for the user: creates (or finds) the project anchor root, writes the project: block into .taskorchestrator/config.yaml at the main checkout root, pushes it to the server, and seeds the bundled process rules. In project mode it also writes a project-level client.json when the server is a loopback HTTP server. With --user it creates a personal root and writes the user-level config.yaml and client.json instead. Use when a user says: initialize task orchestrator, task-orchestrator init, set up task orchestrator for this project, set up a personal root, init --user, or when the SessionStart notice says to run /task-orchestrator:init. NOT Claude Code's built-in /init (that writes CLAUDE.md), NOT tutorial onboarding (quick-start), NOT migrating an already-populated unscoped database (adopt-project-scope), and NOT launching or reconfiguring the server (configure-server).

Visualizes, creates, and diagnoses dependencies between MCP work items. Use when a user says: what blocks this, add a dependency, show dependency graph, why can't this start, link these items, unblock this, remove dependency, or show blockers.

Creates an MCP work item from conversation context. Scans existing containers to anchor the item in the right place (Bugs, Features, Tech Debt, Observations, etc.), infers type and priority, creates single items or work trees, and pre-fills required notes. Use when the conversation surfaces a bug, feature idea, tech debt item, or observation worth tracking persistently. Also use when user says: track this, log this bug, create a task for, or add this to the backlog.

Configures how the MCP Task Orchestrator SERVER runs and is reached — transport (HTTP vs STDIO), the REST API, port publishing, config mounts, and config-sync. Use when a user says: run the server, register the image, set up the Docker container, enable the REST API, set up config-sync, reconfigure the server, change transport, expose the API, reconnect to a different endpoint, or allow a hostname. NOT for first-time onboarding (that's quick-start), NOT for project/personal setup (that's init), and NOT for note schemas / gates / traits / actor_authentication policy (that's manage-schemas) — this skill only decides how the container is launched and reached.

Completes or cancels multiple items at once — closes out features, cleans up old work, and archives completed workstreams. Use when a user says: close out this feature, complete everything under X, cancel this workstream, clean up old items, bulk complete, finish this feature, or archive completed work.

Migrates an already-populated, unscoped Task Orchestrator database in place to the project-scoping convention — creates a project anchor root, re-parents existing work trees under it, and writes rootId back to config.yaml. Use when a user says: adopt project scope, migrate this database to project scoping, make this DB multi-project, project-scope this workspace, adopt existing database, or set up project scoping for an existing DB.

Test authoring framework for items carrying the needs-test-author trait. Defines scenario derivation from acceptance criteria, the oracle-derivation and blindness rules that keep test authorship independent of implementation, the adversarial probe catalog, forbidden patterns, and the test-plan/test-manifest note formats. Referenced by trait note guidance during queue-phase test-plan and work-phase test-manifest filling. Use when filling test-plan or test-manifest notes, or when asked to author or review tests independently of an implementation.

Specification quality framework for planning. Defines the minimum bar for what a plan must address — alternatives, non-goals, blast radius, risk flags, and test strategy. Referenced by schema guidance fields during queue-phase note filling. Use when filling feature-summary, task-scope, diagnosis, or other queue-phase specification notes for any MCP work item.

Review quality framework for the work-to-review transition gate. Guides verification of plan alignment, test quality, and code simplification before marking implementation complete. Referenced by schema guidance fields during review-phase note filling. Use when filling review-checklist notes or when asked to review completed implementation work.

End-to-end release automation — reads commits since last tag, infers semver bump, drafts changelog, creates release PR, merges it, waits for CI green, tags, and monitors the Docker build to completion. Use when the user says: prepare release, cut a release, bump version, create release PR, ship a new version, tag a release, deploy new version, or when all feature PRs are merged and it is time to release.

Assessment of plugin skill and hook changes needed after MCP or config changes. Evaluates skill references, hook context, config-format docs, and orchestration context references. Invoked via skillPointer when filling plugin-impact notes.

SQLite migration assessment for items with the needs-migration-review trait. Evaluates schema changes, table recreation patterns, data migration strategy, and Flyway migration correctness. Invoked via skillPointer when filling migration-assessment notes.

Guides the full lifecycle of a feature-implementation tagged MCP item (the feature container) — from queue through review. Creates or resumes the feature container, fills gate-enforced notes at each phase (feature-summary, implementation-notes, session-tracking, review-checklist), dispatches implementation subagents, and advances through queue, work, and review to terminal. Use when the user says: implement a feature, start a new feature, feature workflow, resume feature work, guide feature lifecycle, or references a feature-implementation item UUID.

Compatibility assessment for items with the needs-api-compat-review trait. Evaluates the MCP tool surface and the REST surface separately, since their compatibility models differ. Invoked via skillPointer when filling api-compatibility notes.

Checklists for adding a new MCP tool, a new Flyway database migration, or a new Gradle dependency to the Task Orchestrator server, including the tool-documentation single-source policy (parameterSchema field descriptions vs the prose description string vs api-reference.md). Use when adding or changing an MCP tool or its parameters, creating a migration, or adding a dependency to the version catalog.

ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intent_search), composite scoring, and memory lifecycle (pin/snooze/forget). Use when tuning retrieval, troubleshooting recall quality, or any ClawMem operation beyond the routing already in your global CLAUDE.md / this repo's AGENTS.md. NOT for setup — install / inference-server config / env vars / systemd / indexing config / internals live in AGENTS.md + docs/.

Code review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /ponytail-review. Complements correctness-focused review, this one only hunts complexity.

Quick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /ponytail-help, "ponytail help", "what ponytail commands", "how do I use ponytail".

Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of what to delete, simplify, or replace with stdlib/native equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat", "ponytail-audit", or "/ponytail-audit". One-shot report, does not apply fixes.

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

Use when one durable lnwjud goal must continue autonomously across ChatGPT turns until verified terminal completion.

Embedded hardware debugging workflow for probe-rs targets using embedded-debugger-mcp. Use when Codex or Claude Code needs to inspect debug probes, validate embedded debugger setup, start the MCP server, guide a user through ARM Cortex-M/RISC-V flashing/debugging/RTT workflows, or operate without installing an MCP client by using the CLI plus prompts.

MUST READ before building or refining rendered visual output in TouchDesigner: generative art, VJ visuals, shaders, scenes, renders, projections, or anything shown on screen. Principles, verified TD recipes, and named looks for composition, camera, lighting, value, color, contrast, motion, materials, and finishing.

MUST READ before declaring any TouchDesigner build, fix or show done, and before any soak or performance test: the verification ladder (structure, errors, frame, motion, data, performance, soak, end to end), run_soak_test and the observer-effect rules that keep measuring from perturbing the show, the iterate-by-capture loop, and what done means.

MUST READ when Envoy/TD connectivity is broken and has not self-healed: bridge internals, manual recovery, stale instances, broken venv.

MUST READ before writing TD Python via execute_python, set_dat_content, or edit_dat_content, and before any heavy build. Parameters, storage, operators, referencing, threading, cook model, heavy-build safety caps.

Workflow and hard-won TD patterns for authoring Embody Specimens (the transparent TDXN gallery networks). Load before building or persisting a Specimen.

Run Embody's test suite and write new tests (Embody development)

MUST READ before building or editing POP networks, particle systems, GPU point/geometry work, glslPOP compute, or converting SOP chains to POPs in TouchDesigner 2025+.

MUST READ before creating or designing custom parameters on any COMP: pages, styles, ranges, help text, naming, ParGroup gotchas.

MUST READ before wiring a TOP, CHOP, MAT, DAT, light, camera or instancing chain you have not built before: the parameter names TD abbreviates, the defaults that silently do the wrong thing, and the input-order rules, per operator, verified on TD 2025.33230. Pair with describe_op_type.

MUST READ when a _peers advisory appears or multiple AI sessions are active in the same TouchDesigner project: advisory contract, claim leases, destructive gates, raw-file-edit visibility, division of labor.

Workflow for running multiple TD instances with Envoy, switching between them, and understanding the instance registry.

MUST READ before recording, exporting, or batch-encoding any movie or image sequence from TouchDesigner: the Realtime trap, zero-drop verification, deterministic per-frame export, async file-reader staleness.

Merge or compare two divergent TouchDesigner .tox/.toe binaries that git cannot three-way-merge. Load when a merge/rebase conflicts on a .tox or .toe, when asked to merge, port, reconcile, or diff two versions of a TD component, or when comparing a component across branches, machines, or TD builds.

MUST READ before first MCP tool call in a session. Complete Envoy tool catalog with parameters and usage.

MUST READ before creating, modifying, or querying annotations. Contains parameter names, coordinate model, and API quirks.

MUST READ before writing GLSL or creating a glslTOP, glslmultiTOP, glslMAT or glslPOP: docked DATs, uniforms and the Colors page, TD's built-in functions and samplers, feedback and multi-pass, reading compile errors. Every built-in named here compiled on TD 2025.33230.

MUST READ before calling externalize_op or save_externalization. Required workflow steps.

TRIGGER when operator errors appear or user reports broken behavior. Systematic diagnosis workflow.

MUST READ before creating or moving any operator (create_op, copy_op, set_op_position, or execute_python builds). Required verification, canonical positioning recipe, and error-checking steps.

MUST READ before calling create_extension. Required parameters, lifecycle methods, and wiring steps.

Switch this session into thinking-partner mode for TouchDesigner: discuss, read the docs, build one small step at a time in the visible output, and hand the next decision back instead of finishing the network autonomously. User-invoked via /collab; /brief or 'just build it' restores the autonomous contract.

MUST READ before building or styling any TouchDesigner panel UI (dialog, wizard, HUD, control panel, buttons, text): design tokens, layout rules, component recipes, and the OP Viewer TOP verification loop. Mechanics (which panel COMP, single-window, click handling) are in td-ui-mechanics.md beside it.

Compile a conversational request into an Embody task brief (briefs/*.md): skills to load, discovered anchors, verifiable success criteria, and gates -- then execute the work from that contract. User-invoked via /brief.

MUST READ before calling RunAgentTests or touching agent-tier test infrastructure -- these tests spawn real AI clients (Claude Code, Codex) and SPEND SUBSCRIPTION USAGE; never run casually. Tier model, async runner rationale, auth/isolation rules.

Diagnoses and resolves MCP server registration failures, GPU detection, BigQuery authentication, index build failures, import errors, search quality issues, and performance problems.

Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.