craigm26

Use when designing and implementing a new software feature from scratch — triggers the Fable-plan → implement → review pipeline.

Use when declaring or checking the token budget / model tier for this session. Triggers on: "set effort", "how much budget do we have", "low on tokens", "use opus", "use sonnet", "constrained this week", or any explicit model-tier selection. Can also be called mid-session to downgrade tier when tokens run low.

Generate an implementation-ready Product Requirements Document for a feature: self-clarify the open questions (no user interview), then write a structured PRD — goals, one-session tasks with verifiable acceptance criteria, numbered functional requirements, non-goals — saved to /tasks/prd-<feature-name>.md, ready for the `tasks` skill to convert into an executable plan. Use when the user asks "create a prd", "write a prd for X", "plan this feature", "spec out X", "requirements for X", or after running `build-options` (its Phase 4 hands the winning option here).

Convert a PRD markdown file (typically `/tasks/prd-<feature>.md` from the `prd` skill) into `prd.json` — an ordered, dependency-sorted execution plan where every acceptance criterion is a boolean check an agent can pass or fail without a human. Use when the user asks "convert prd", "create tasks", "prd to json", "generate tasks from prd", or after running `/prd` at the end of the `/market-validation → /build-options → /prd → /tasks` chain.

Map and maintain the founder-skills <-> PlatAtlas integration surface: the fable-org-audit endpoint map (with its known drift against the live worker), the market-validation market-map sink (nodes.json + flows.json into workflow-atlas, shape-valid but load-untested), adoption guidance for PlatAtlas rail agent seats, and the documented-not-executed mirror plan into workflow-atlas's own plugin convention. Use when a maintainer says "how does founder-skills connect to PlatAtlas", "is the org-audit endpoint map still current", "prove the market-map sink", "load the market map into PlatAtlas", "can the rail agents use these skills", "mirror founder-skills into workflow-atlas", or "what drifted on the PlatAtlas side".

Decide WHAT to build after a market is validated: generate divergent build options, score them with an independent judge panel into a weighted decision matrix, adversarially stress-test the top, recommend one (with kill criteria), render a Tufte decision matrix, and hand the winner to the `prd` skill. Use when the user asks "what should I build", "what are my build options", "which option should we build", "decide what to build", or after running `market-validation`.

Use when you need to verify that a customer organization on your platform is healthy and getting full value — a live integration audit that probes real API signals across eight dimensions, not a code review. Triggers on: "audit this org", "is <org> healthy", "health-check the integration", "why does this org feel off", or a scheduled pre-demo / weekly org check.

Validate whether there is a real market for a product idea, end to end: scope questions → a multi-angle web-research workflow with mandatory live-URL verification → a cited evidence pack → a Tufte HTML deck + PDF + PPTX → a build/integrate brief and an emitted market-map graph. Use when the user asks "is there a market for X", "validate demand for", "prove the market for", "should I build X", "market research / competitor + willingness-to-pay evidence for X", or wants a fundable evidence pack.

Review a proposed code change, docstring, RCAN config, or SKILL.md for the OpenCastor robot runtime. Called by autoresearch Bob when peer review is needed. Reply in exactly one line: PASS or FAIL with a brief reason.

Use when the user asks the robot to pick up, grab, grasp, place, move, hand over, or manipulate a physical object using the robotic arm or gripper. Triggers on "pick up", "grab", "pick", "place", "put X on Y", "hand me", "move the X", "get the X", "assemble", "sort", "stack", "lift", "drop", "set down", "give me", "bring me".

Use when the user asks what the robot sees, requests a photo or snapshot, wants a description of the surroundings, asks about objects in view, or says "look at X", "what's in front of you", "describe your environment", "take a picture", "scan the area", "can you see X", "show me what you see".

Use when the user asks the robot to move, go somewhere, drive to a location, come closer, back up, or navigate to a named place or person. Triggers on "go to", "move to", "drive to", "navigate to", "come here", "back up", "turn around", "follow me", "move forward", "turn left", "turn right", "move back", "approach the", "get closer to".

Use when the user asks to consult, communicate with, or delegate to another robot in the fleet. Triggers on "ask Alex", "ask Bob", "check with [robot]", "what does [robot name] think", "coordinate with", "tell [robot] to", "split the task with", "collaborate with", "get Bob's opinion", "loop in Alex", "let Alex handle", "what can Bob do", "relay this to".

Use when the user asks about something the robot doesn't know from its local knowledge — facts, current events, how-to questions, product specs, news, definitions, or anything requiring up-to-date information from the internet. Also triggers on "search for", "look up", "find information about", "research", "what is the latest on", "google", "what does X mean", "how do I", "specs for".

Safe-edit playbook for changes requested through PTA Studio by a non-technical parent volunteer. Use for ANY content/copy/image/styling change to the Schweitzer PTA site. Defines the smallest-safe-change rule, the hard do-not-touch list (auth, Supabase, API routes, payments, config, dependencies, migrations, file deletion), and how to politely refuse anything that needs a developer.

A trivial test skill that confirms the Antigravity plugin loader is wired correctly. Use only when explicitly asked to verify the plugin system itself.