Menu
Implement an ai-sdd feature plan within this repo's conventions and record the acceptance ids covered.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | implement-feature |
| description | Implement an ai-sdd feature plan within this repo's conventions and record the acceptance ids covered. |
Read .ai-sdd/artifacts/feature-plan.v1.yaml and .ai-sdd/conventions/<stack>.md (this slice's
vertical) first. Stay strictly inside the plan's files scope — the changeset.diff-in-scope gate
compares the working tree against it.
Per-vertical layout & toolchain (from the conventions):
contracts/ — Python 3.12 · the frozen schemas (pydantic v2, ADR-06), adapter interfaces,
Synthetic oracle, Replay sources. All schemas live here; nowhere else.operator/ — Python 3.12 · Generator, 3-critic panel, gap analyzer, markdown presenter, demo
replay. The Generator must not read the oracle config (information separation).coprocessor/ — Python 3.11 · live Serial/Camera sources, vision pipeline (YOLO11n + AprilTag),
serial_bridge.py merge → session_*.jsonl.brain/ — VEXcode Python single file, ruff dev-lint only, no runtime package manager.Toolchain (non-negotiable): uv for deps/envs (uv sync / uv add / uv run); ruff for
lint/format. No pip/poetry/black/isort/flake8.
Run the commands in the plan's tests field. At minimum: uv sync, make test, make validate
(pydantic fixtures vs frozen schemas), make lint (ruff check + ruff format --check). Any change to
a frozen contract must keep .ai-sdd/schemas/examples/*.json valid — the task-telemetry.structure,
self-model.structure, and parts-catalog.structure gates run every slice.
Write .ai-sdd/artifacts/changeset.v1.yaml with:
summary: what changed.satisfies: the acceptance item ids addressed.The deterministic gates run after submit and reject missing artifacts, failed build/test/validate/ lint, files outside scope, or a broken frozen contract. Discovered out-of-scope work is a new slice (flag it), never an inline change.
Update the ai-sdd framework binary + skills to the latest release — an apply-on-confirm wrapper that runs `ai-sdd update --check`, surfaces the current-to-latest version transition, and (only on explicit confirmation) runs `ai-sdd update` and lands a standalone reseed commit. Agent-agnostic (claude-code or codex). Use when a teammate wants to update / upgrade ai-sdd, sees the update-available notice, or invokes `/ai-sdd-update`.
Stand up (or refresh) an ai-sdd factory for a repository so any coding agent — claude-code, codex, … — can drive it. Discovers the repo's conventions, scaffolds the .ai-sdd/ home, authors worker skills + schemas, compiles the deterministic gates, and wires provider-neutral skill surfacing (AGENTS.md + per-agent symlinks). Use when onboarding a repo to ai-sdd or re-bootstrapping after the codebase/conventions drift.
Drive a software-factory run by dispatching a sub-agent per worker — the deterministic `ai-sdd` engine plans (next), a fresh sub-agent does each worker's work via its skill, the engine gates and advances (submit), and each completed slice is committed. Agent-agnostic (claude-code or codex). Use when asked to run, drive, continue, or advance a factory run / pipeline / orchestration, or when the user mentions `ai-sdd next` / `ai-sdd submit`.
Print the diagram-driven ai-sdd workflow cheatsheet — the canonical command sequence (bootstrap → plan → run, validate/next/submit/status) that travels with the binary. Use when a user forgets which command comes next, asks "how do I drive a run / what's the workflow", or needs the command reference without leaving the repo.
Turn a complete PROGRAM brief into a runnable master plan — a decision-closed program requirements doc and a master orchestration graph whose nodes are whole sub-features (kind:pipeline) sequenced by milestone validation gates with owners. The program tier above ai-sdd-plan. Requires a real program brief (refuses a one-liner) and human approval of the program requirements draft before emitting the graph. Use when planning a multi-feature, multi-person project in a bootstrapped repo (run ai-sdd-bootstrap first); each sub-feature is then planned with ai-sdd-plan. Re-run on an existing program to amend it in place (create-vs-amend is auto-detected from disk): append sub-features/milestones and rewire pending nodes; a started node (completed or in-flight) is immutable and corrected forward with a downstream `<node>-revert` node.
Turn a complete feature brief into a runnable plan for a bootstrapped repo — a decision-closed requirements doc and an orchestration graph (slices + depends_on) the engine executes. Requires a real brief (refuses a bare one-liner — asks for one) and human approval of the requirements draft before generating slices. The planning layer between an idea and ai-sdd-run. Use when starting a new feature in a repo that already has a .ai-sdd/ (run ai-sdd-bootstrap first). Re-run on an existing feature to amend it in place (create-vs-amend is auto-detected from disk): append slices and rewire pending ones; a started slice (completed or in-flight) is immutable and corrected forward with a downstream `<slice>-revert` slice.