From a7cce3d88251e56371f9dbd590c7280fd2d1e31e Mon Sep 17 00:00:00 2001 From: Amolith Date: Tue, 9 Jun 2026 23:25:53 -0600 Subject: [PATCH] Add looping skill --- .agents/skills/loop-through-slices/SKILL.md | 37 +++++++++++++++++++ .../loop-through-slices/SKILL.md.license | 3 ++ 2 files changed, 40 insertions(+) create mode 100644 .agents/skills/loop-through-slices/SKILL.md create mode 100644 .agents/skills/loop-through-slices/SKILL.md.license diff --git a/.agents/skills/loop-through-slices/SKILL.md b/.agents/skills/loop-through-slices/SKILL.md new file mode 100644 index 0000000000000000000000000000000000000000..d3a3f5306fed544c94f123a7e76cd384c58e4213 --- /dev/null +++ b/.agents/skills/loop-through-slices/SKILL.md @@ -0,0 +1,37 @@ +--- +name: loop-through-slices +description: Guides the vertical-slice development loop for cooked-mcp. Use when explicitly told to loop through one or multiple slices. +user-invocable: true +--- + +Each unit of work must deliver independently verifiable and observable +behaviour. In addition to what AGENTS.md says, + +- Check `jj status`. If the working copy already contains completed or + unrelated work, run `jj new -m "area: imperative, kernel-style change + description"`. + +- For design or behaviour questions, consult the oracle before implementation + and adjust the spec or plan based on the answer. Include the slice goal, + already-completed behaviour, relevant specs/files, explicit in-scope and + out-of-scope ACIDs, and ask for spec adjustments, target ACIDs, tests to add, + and implementation pitfalls. + +- Write the failing test first. Avoid ad-hoc smoke tests as a substitute for + coverage; if manual testing finds a gap, add or improve automated tests so + the gap stays covered. Then implement the smallest correct change using + existing project patterns. + +- Verify with `mise`, using narrower tasks while iterating and `mise run check` + before calling the slice done. After checks pass, get a formal code review + for meaningful behaviour changes. Validate review findings before acting on + them; fix clear and obvious findings directly, and ask the user about + validated findings whose solution is not obvious. + +- When the slice is complete, review `jj status`, `jj diff --git`, and the + working-copy description. Push relevant acai specs/refs and update completed + ACID statuses without comments: `acai set-status @payload.json --product + lipu-kute --impl main --json`. The payload is a JSON object keyed by full + ACID, e.g. `{"notes.ENCRYPT.1": {"status": "completed"}}`. Only move on to + the next slice after the tests, check, review, and acai state for the current + slice are coherent. diff --git a/.agents/skills/loop-through-slices/SKILL.md.license b/.agents/skills/loop-through-slices/SKILL.md.license new file mode 100644 index 0000000000000000000000000000000000000000..3dbb1e29808ff6ce1e89aa3211dbfa6c8aa5ef0e --- /dev/null +++ b/.agents/skills/loop-through-slices/SKILL.md.license @@ -0,0 +1,3 @@ +SPDX-FileCopyrightText: Amolith + +SPDX-License-Identifier: CC0-1.0