Menu
Turn a coarse roadmap item into reviewable local tasks with one output, one dominant touched area, and one main verification signal.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Prepare, publish, verify, and record AIDD Python package releases through this repository's release/v<version> branch and GitHub Release published-event flow; use when cutting a new prerelease or release, running release dry-runs, checking PyPI/pipx/uv tool evidence, or performing post-release version-bump follow-up.
Run or prepare a manual full-flow live end-to-end scenario against a public GitHub repository with repository pinning, authored task selection, execution evidence capture, and manual post-run quality reporting.
Run harness and eval scenarios for ai_driven_dev_v2, validate document-first stage outputs, preserve runtime logs, analyze failures, and produce durable audit artifacts for deterministic and manual-live lanes.
Select, split, create, promote, and close roadmap tasks while keeping `roadmap.md` and `backlog.md` synchronized.
Map a task to the right AIDD docs, modules, checks, and scenario assets before making changes.
Analyze runtime and adapter logs to identify the first decisive failure signal and classify it correctly.
| name | task-slicing |
| description | Turn a coarse roadmap item into reviewable local tasks with one output, one dominant touched area, and one main verification signal. |
Use this skill when a roadmap task or slice still feels too vague to implement directly.
A strong local task has:
Split again if the proposed task:
implement stage, finish adapter, wire everything, or support all cases.Always try this order:
Too broad:
Implement the Claude Code adapter.Better:
Implement Claude Code command assembly from stage brief, workspace path, and prompt-pack inputs.Stream raw Claude Code stdout and stderr to the operator CLI in real time.Persist a full runtime.log that matches the raw streamed output as closely as possible.Detect Claude Code question or pause events when the runtime exposes them.Too broad:
Finalize the implement stage.Better:
Define the required implement inputs, including task selection, repository state, and allowed write scope.Define the required implement outputs, including change summary, touched files, and verification notes.Define validator rules for missing diffs, unverifiable claims, and incomplete execution summaries.Create the implement prompt-pack scaffold with explicit edit and verification guidance.When you use this skill, report: