Steps

See diagram for a visual flow overview.

Add the following steps as tasks using the TaskCreate, TaskUpdate, TaskGet, and TaskList tools. Update the status as you progress through each step to keep the user informed.

1. Execute the /tlc-spec-driven skill to generate a plan/spec based on the described problem.
2. Execute the /spec-to-requirements-table skill to generate a requirements.md file.
3. Verifier pass (always-on, author ≠ verifier): dispatch a fresh sub-agent — no inherited context from steps 1-2 — to run /sd-review-spec in report-only mode against the generated spec.md, design.md, tasks.md, requirements.md, and any cited ADRs. Give it only: the original feature request (verbatim, as the user stated it), and the feature's spec dir path. It audits every doc claim against the real code and checks the full set covers everything the original request needs — scope, constraints, edge cases, dependencies, and every requirement in requirements.md traced to a task. It does not edit anything; it returns the severity-classified gap report (same table as /sd-review-spec step 8). If gaps exist: show them to the user and apply fixes per /sd-review-spec steps 4-7 before continuing. Do not skip this step and do not ask the user whether to run it — only ask what to do with findings.
4. Once planning is complete, ask the user if they wish to register the feature in taskmaster. If the answer is "yes," use the /sd-insert-taskmaster skill.
5. Check the definitions in docs-adr and consider offering to create an ADR when the criteria are met.
6. At the end of the session, evaluate whether there is anything worth saving as permanent memory. Save as permanent memory only what the next session will need and cannot rediscover by reading the code, Git, or CLAUDE.md—such as the reason behind a decision, a non-obvious invariant, or a user preference; if it is already in the repo or only matters for this specific conversation, do not save it. Use the ai-memory-durable-pages skill to persist it.