Hand a spec that is mid-implementation to another machine or another agent.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
I'm moving this spec's work to another machine or another agent. The next session starts cold: it has the repository and nothing else. It has none of this conversation, none of this machine's files and none of your memory. Leave the spec so that session can carry on as if it had been here.
Collect what this session knows and the spec doesn't yet say, from the discussion and from the work itself, and put it in the spec:
Write it into the spec's own handoff, in place: the spec stays one current account, not a transcript with a new note on top. Then push, so everything the spec points at exists on the remote.
Done when a fresh agent, given only the repository, would pick the same next step you would, and would not repeat a question I've already answered.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.
The English summary is being prepared. Showing the original description.
Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run. Working code still embeds architecture the user never chose; surface it because future work inherits it. Use when the user wants to review the decisions the AI made on their behalf, before merging or committing AI-implemented work, when integrating a delegated subagent's pass, or when a fix "works" but might be a point fix.
The English summary is being prepared. Showing the original description.
Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find performance issues, investigate freezes/500s/OOMs, review retries or polling for no-progress loops, rank a performance backlog, or implement the next simple performance fixes.
The English summary is being prepared. Showing the original description.
Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests, investigating implementation coupling or test-only production hooks, reviewing the value of proposed coverage, or auditing an entire subsystem. Use write-tests to implement the resulting test changes.
The English summary is being prepared. Showing the original description.
Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts, configurations, or other artifacts against a goal or benchmark, or when a long research run needs a planned hypothesis queue, focused trials, and durable findings.
The English summary is being prepared. Showing the original description.
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a launch video, product film, feature trailer, teaser, promo clip, hero shot, or any "cinematic" footage of an app or UI. This skill covers camera, framing, light, and edit. It is stack-agnostic.
The English summary is being prepared. Showing the original description.