New Skills

Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

Create and edit file-based Warp software factory definitions, in a repository tree rooted at a factory.yaml. Use when authoring or changing that factory.yaml, Agent, Automation, Scorer, or Runner files under that root, or its factory and agent skill trees, and when fixing Factory file diagnostics. Do not use for agent-definition Markdown that belongs to another tool, for a tree with no factory.yaml, or to operate a live factory or hand work to one through Factory MCP.

Run a dependency graph of child agents in one call with the native dag tool. Use when the user asks for mass-ulw, a DAG of tasks, fan-out/fan-in work, or multi-agent execution where some tasks must wait on others.

Store a dag definition once and re-run it in one or two lines, instead of pasting the full definition JSON into every eval cell. MUST USE whenever the user wants to save a DAG for reuse, run a previously saved/named DAG, schedule the same graph repeatedly (nightly/weekly audits, recurring multi-agent pipelines), or asks where to put a dag definition file. Triggers: dag library, save this dag, reuse a dag, run the saved dag, stored dag definition, recurring dag, nightly dag, dag 정의 저장, 저장된 dag 실행, dag 반복 실행, DAG 만들어두고 여러 번.

QA the omo Senpi adapter (packages/omo-senpi, packages/senpi-task) against the REAL senpi binary in strict isolation, and write every artifact to the one canonical evidence path .omo/evidence/omo-senpi-adapter/<slug>/. The live drivers under packages/omo-senpi/scripts/qa/ create their own isolated SENPI_CODING_AGENT_DIR and ignore the caller's, so the real ~/.senpi/agent is never written. Ships scripts/resolve-evidence-dir.mjs, which is the ONLY sanctioned way to pick an evidence directory: it rejects traversal, separators, absolute paths, and stray roots such as local-ignore/qa-evidence. Use whenever someone changes anything under packages/omo-senpi or packages/senpi-task, or wants to QA, smoke-test, verify, or debug the Senpi adapter, the task/team engine, the DAG, task RPC, or skill delivery. Triggers: senpi qa, qa senpi, senpi-qa, test senpi adapter, verify senpi task, senpi task e2e, senpi team e2e, task dag qa, live senpi driver, senpi evidence path.

Use when a worker should claim the next schedulable item in one FS-GG repository and carry it through implementation, review, green merge, post-merge obligations, and a verified done stamp.

Draft or edit user-facing markdown in this repo. Use when writing or revising README, PROBLEM.md status, explainers, notes, or GitHub pull request titles and bodies.

Drafts an undergraduate textbook chapter -- learning objectives, motivation, worked examples, exercises -- for a student who is studying the topic, not yet doing it. Diataxis-wise this is explanation with worked application, not a tutorial; if the user wants a hands-on lesson the reader follows at a keyboard, use `tutorial-writer` instead. May cite grounding papers from the synced corpus (content/ledger.sqlite via chitragupta.retrieval.search()) for motivation/background, but is not citation-dense; most content is original worked examples and exercises. Triggers when the user asks to draft a textbook chapter, lecture notes, course reader, teaching material, or worked-examples handout for students. To change one that already exists in content/drafts/, use draft-reviser instead -- never re-run this skill to make a change. Any citations it does include must pass `python -m chitragupta.draft gate` before the draft is presented -- never a fabricated citekey.

User-invoked session preflight. Runs the repository's declared checks read-only and reports project state the human may not be aware of: open issues and pull requests, work left in flight, errors in recent logs, dependent services that are down, approaching expiries, and drift in the project's own documents. Use this skill when the human invokes it by name, or asks what the state of the project is, what they were in the middle of, what has changed since last session, or whether anything needs attention before they start. It maintains `project-checks.md`, the per-repository record of what is worth checking and what normal looks like for each check. It reports observations and never decides what to do about them; choosing the next task stays with the human.

Polish CLI user experience with @clack/prompts for interactive flows, update-notifier for version awareness, and enhanced Commander.js help text with examples and colors. Generic patterns for any Node.js CLI.

Use as the main entry point for installing, updating, or applying the repository-managed Oracle APEX 24.2 skill kit in a project. Route APEX development, project learning, cooperative database object locks, complete application exports, full/partial database releases, retention, and pending DDL/DML while preserving project-owned standards.

Go beyond a finished piece of work — surface what it would take to make it genuinely better, priced, ranked, and honest about what is not worth doing. Mines the compromises already made (trimmed scope, TODOs, skipped tests, "good enough for now") before inventing anything, and is allowed to conclude "ship it". Use when the user says "plus ultra", "/plus-ultra", "go beyond", "how could this be better", "what would you do to make this even better", "if we went further", "what did we leave on the table", "level this up", or asks what to do next on something just finished. Homophones "plus ultra", "plusultra", "plus alta" all mean plus-ultra. Fires AFTER work is declared done — it does not shape the plan (that is `grilling`) or test the decision (that is `steelman`).