fast-track-ai-spec

1. Read fast-track-ai/tracks/NNN-slug/intent.md in the target repo. Intent status may stay draft. Classify each unanswered item under Open questions:
   • Blocking questions: an answer changes scope, security, data persistence, external integration, architecture, or acceptance. Ask blocking questions interactively using the host ask pattern (at most three per pass). Withhold the summary and do not offer . para implementar while any blocking question remains unanswered.
   • Deferrable questions: questions whose answers do not block overall architecture or scope. Turn each deferrable question into a bounded task whose Validate names the expected answer or artifact, placed in a group that dependent groups list in (depends: ...). Do not invent answers to either kind.
2. Write fast-track-ai/tracks/NNN-slug/spec.md from ./assets/spec.md bundled in this skill. Outcome plus numbered Phases, Out of scope repeated from the intent without widening. Each phase separates the delivered state from its check: Done: names the delivered, observable state an observer can see when the phase closes, and Accept: names the check that proves it, a command with its expected result or an observable procedure with its expected observation. Files: is the explicit list of touched files. Auxiliary outputs go under assets/, never loose at the track root.
3. Write tasks.md from ./assets/tasks.md bundled in this skill: organize tasks into named parallel groups using ## Group <name> headers, with (depends: <group>) on the header when a group depends on another. Tasks within one group touch disjoint files and have no data dependency, so they may run concurrently. When unsure about independence, use separate sequential groups. Each task line carries a (Phase N) tag naming the spec phase it serves, Files: for the files it touches, and Validate: naming a command with its expected result or an observable procedure with its expected observation. Include a task for each deferrable open question. When the user makes a qualifying decision (durable, costly to reverse, surprising without context, or a meaningful trade-off), file fast-track-ai/decisions/<NNN-slug>.md from ./assets/decisions.md without a separate request and cite supporting refs, research, assessments, source URLs, or repository paths when available. Status is accepted | superseded only. Record evidence only in the ## Evidence body section; the ADR frontmatter has no evidence field. Do not create an ADR for local, easily reversible, or obvious choices. To replace an ADR: create the replacement as the next numbered accepted ADR, set the original's status: superseded and add superseded_by: <replacement-id>, and leave the original's decision text and other content unchanged. File outputs point under assets/.
4. Regenerate fast-track-ai/INDEX.md with ../fast-track-ai-init/scripts/fast-track-ai-index.sh <target> using the owner copy and report any validation error instead of presenting the summary as complete.
5. Run ./scripts/fast-track-ai-gate.sh --mode structure --track NNN-slug --root <target> from this skill as an internal smoke test. Fix any gate failure before presenting the draft; structure mode ignores approval status and task checkboxes.
6. Present a post-phase summary. Format:
   • Four short bullets: outcome, phases, task count, parallel groups.
   • Track location: fast-track-ai/tracks/NNN-slug/.
   • Next-step line: . para implementar. Do not report draft status as failure. Do not present an approval gate.
7. Wait for user input. If the user replies . or an affirmative synonym ("sim", "pode continuar", "yes", "continue"), set frontmatter status: approved in both spec.md and tasks.md. Complete this approval-only action before invoking the fast-track-ai-implement skill for the same track or issuing any product edit. A multi-file action may approve both artifacts together, but must not mix approval with product edits. Approval covers exactly the presented spec.md and tasks.md content. After approval, any material change to either file (scope, Files, Accept criteria, tasks, or group dependencies) returns both files to status: draft and requires a new summary before implementation may continue. Checkbox updates and administrative writes defined by the implement workflow do not count as material changes. Any other input is processed as an instruction to revise the spec or tasks before proceeding; after revision, regenerate INDEX.md, re-run the structure gate, and present the summary again.

Path resolution: ./ paths and ../fast-track-ai-* sibling paths resolve from this skill's installed directory, and fast-track-ai/ paths resolve from the target repository root.