anvil

Author, parse, and review a project PRD in anvil — capture the requirements that everything downstream (features, tasks, claims, evidence) gets generated from. Use this skill when starting a new project or revising requirements before any planning work happens.

Decide what to do with an anvil task that has submitted evidence and is awaiting human review — accept and ship, reject and reopen, or hold for further investigation. Use this skill when one or more tasks are in needs_review and need a final disposition.

Turn a reviewed PRD into a ready-to-execute task graph — generate features and tasks, score each on six dimensions, surface dependencies and conflict groups, promote drafted tasks to ready. Use this skill once the PRD is approved and before any agent claims work.

Bootstrap a `.anvil/prd.md` draft from a rough project idea — interview the user question-by-question and write the result so `anvil prd parse` can consume it. Use this skill when the user has a project intent but does not yet have a PRD (e.g., asks to "start a PRD", "draft requirements", "author a PRD", or "spec out a project").

Run the agentic execution loop on a claimed anvil task — fetch the work packet, do the work, submit completion evidence. Use this skill when an agent has just claimed a task and needs to execute it end-to-end without juggling individual CLI commands.

Inspect anvil project state — list tasks, show task details, find the next claimable task, summarize active claims and blockers, check file-conflict warnings, and reconcile state with the filesystem and git. Use this skill when you want to see what anvil knows without changing anything.

Acquire an exclusive lease on an anvil task — pick from the ready queue, check for file conflicts, claim the task, and get a working git branch to commit into. Use this skill when ready to start work on an approved task.

Walk the PRD's unresolved items — `[NEEDS DECISION]` markers, `## Open Questions`, and missing acceptance-criteria or verification fields — and drive each one as a Q&A turn with the user, proposing concrete options when possible and applying the chosen answer with `anvil prd resolve-decision`. Use this skill when `anvil prd find-decisions` reports unresolved items, or when other skills (prd, plan) detect decisions blocking progress.

Drive backlog/roadmap items end-to-end, autonomously and in parallel. For each item — research the problem with multiple agents, judge approaches with /ponytail:ponytail-review, implement in an isolated git worktree, adversarially review for blind spots (pass/fail), then ship ONE PR per item (wait for CI + Greptile, address the review, merge). Use when the user says "run the loop", "resolve the backlog", "work the roadmap", "clear the issues", or asks for autonomous multi-item delivery on this repo.