Aa import

Skill Peeyushmeher/agent-agile/skills/aa-import

Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution. MIT, no token, ever.

Install

npx -y skills add Peeyushmeher/agent-agile --skill aa-import

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

24 days oldThe repository was created 24 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user has an existing plan, PRD, or spec document they want brought into this planning system instead of a fresh grill and intake — or invokes /aa-import with a path or description of that document.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.2 KB, as published. Nobody here has run it

aa-import

Resolve the Agent-Agile playbook root: use the first of these that exists — (1) ${CLAUDE_PLUGIN_ROOT}/playbooks, (2) ./.claude/agent-agile/playbooks, (3) ./.agents/agent-agile/playbooks, (4) ~/.claude/agent-agile/playbooks, (5) ~/.agents/agent-agile/playbooks, (6) ./playbooks.

Read playbooks/planner.md section Import path in full, and follow it exactly — do NOT re-derive or improvise the system. That section also depends on The 8 intake questions, Pushback patterns, and Drafting the plan; read those too before starting.

Running the import

The skill's argument is a path to, or description of, the user's existing plan document.

Read the document in full — no skimming.
Answer the 8 intake questions from the document alone, without asking the user anything yet. Mark any thinly-answered question as a gap rather than guessing, using the same "thin answer" bar defined in The 8 intake questions.
Ask the user only the gaps, one question at a time, with the same pushback discipline as a fresh intake.
Deliver the split statement exactly as defined at the end of planner.md's The 8 intake questions — the "my part / your part" narration plus the process preview — before writing any files. Imported plans get it too: their authors are the users most likely to assume the system does everything.
Map the result onto the plan format and check the three things Import path names explicitly: whether the Key Results pass the three KR tests, whether every epic has a demo sentence, and whether any existing stories pass the worker-readiness test.
Write .planning/PROJECT.md, .planning/ROADMAP.md, and Epic 1's story cards from the templates at playbooks/templates/PROJECT.md, playbooks/templates/ROADMAP.md, and playbooks/templates/STORY.md, plus .planning/PREREQS.md and .planning/CONFIG.md from their templates. Produce a gap list alongside these files — what was missing or broken in the source document — not a silent rewrite. On a multi-epic import, a missing risk register is itself a gap to report: the source plan named no domain edges and no fixtures (see playbooks/planner.md "Research fan-out and the risk register"), and the user decides whether to run the fan-out before executing.
Update .planning/STATE.md from playbooks/templates/STATE.md, Phase intake.

Panel and exits

Instruct the user to run /aa-panel next — an imported plan gets the same adversarial review as a freshly drafted one, no leniency for "it was already written." After the panel returns, resolve to exactly one of the three exits the playbook defines: