Implement

Standard implementation flow: load style rules, make the change, run post-implementation QA.

Task Tracking

At the start, use update_plan to track each step, restating any remaining steps of a parent workflow alongside them:

1. Run $code-style skill
2. Load task-specific skills
3. Make the change
4. Run verification
5. Run $smoke-test skill for UI/UX changes
6. Run $preview skill for UI/UX changes
7. Post-implementation QA

Workflow state lives at .turbo/workflows/<slug>.md — slug from the governing plan when one is in context, otherwise the current branch name with non-alphanumerics replaced by hyphens. It pairs one-to-one with the thread's goal. When this run's create_goal attempt succeeds, write the file fresh: Status: active plus this invocation's update_plan list as a checkbox list. When an unfinished goal already exists, mirror into the workflow file its objective names; when it names none, continue without workflow state. Mirror every update_plan call into the file; it holds the pipeline's remaining steps and their statuses. When this run created the goal, run the terminal step in order: mark the final entry completed and mirror it, set Status: closed, mark the goal complete with update_goal, then emit any halt message.

Then attempt create_goal with the objective: "Make this change: <one-line task summary>. Carry it through Step 7, which runs $finalize unless a lighter pass or stopping is chosen. Workflow state: .turbo/workflows/<slug>.md; mirror every update_plan call into it. Loop state lives under .turbo/loops/. After any context compaction, re-read the workflow file and any active ledger, and continue from the first unfinished entry. Mark this goal complete when Step 7 has finished." If an unfinished goal already exists, an outer workflow owns it; continue without creating one.

Step 1: Run $code-style Skill

Run the $code-style skill to load existence, reuse, mirror, and symmetry rules before editing.

Step 2: Load Task-Specific Skills

Scan the work for types that match available skills, matching against the richest context available: a plan's Implementation Steps if a plan is in conversation context, otherwise the user request, a prior skill's task description, or an improvement entry. For each unambiguous match, run the skill by reading and following the installed skill instructions. For example, if the work includes "add a Drizzle migration" and a skill exists whose triggers reference Drizzle migrations, load it. If a work type has no matching skill trigger, do not load a generic skill.

If unsure, do not load.

Step 3: Make the Change

Apply the change described by the current context — the user request, a prior skill's task description, or an improvement entry. Keep the edit scoped to what the context describes.

When the fix changes how a value is constructed, grep for every other site that constructs it and fix the ones carrying the same defect; treat these siblings as part of the same change. If the scope balloons beyond what the context specified, stop and confirm scope before continuing.

Step 4: Run Verification

If a Verification section is in conversation context (e.g., from a plan file), execute the commands, smoke checks, or MCP tool invocations it specifies. If a check fails, run the $investigate skill. If a check is blocked by a dependency, unclear requirement, or environmental issue, use request_user_input to surface the blocker and let the user choose how to proceed. If no Verification section is in context, skip this step.

Step 5: Run $smoke-test Skill for UI/UX Changes

If the change touches a user-facing surface (UI components, styles, templates, markup, user-facing routes or screens), run the $smoke-test skill. When that is unclear, use request_user_input to ask whether the change is user-facing rather than skipping silently. Skip this step for changes with no user-facing surface (backend-only, CLI, library, build or config).

$smoke-test verifies without modifying code, so act on what it reports here: fix each failure and re-run it. When the same failure survives a fix attempt, run the $investigate skill; if investigation finds no root cause, stop and report with its findings. When a blocker cannot be cleared in this session (a path needing real credentials, an external service, or state unavailable here), carry it into Step 6 rather than treating it as a failure.

Step 6: Run $preview Skill for UI/UX Changes

If Step 5 determined the change is user-facing, run the $preview skill so the user can try it firsthand before QA. Skip this step otherwise. Pass along any blocker Step 5 could not clear, so the hand-over names the cases still left to the user.

Step 7: Post-Implementation QA

When a plan file governs the work, hold this step until every Implementation Step has been applied, and continue to the next Implementation Step at every earlier boundary. Then run the $finalize skill.

When no plan file governs the work, use request_user_input to offer three options:

• Full QA — run the $finalize skill
• Lighter pass — run the $simplify-all skill
• Stop here — leave the change as-is

If this run created a goal, mark it complete with update_goal. Then call update_plan to mark this step completed and continue with the next step of the active workflow.

Rules

• Defer git commit, git push, and PR creation to Step 7.
• Don't reference .turbo/ content (filenames, acceptance criteria, step numbers, headings) in code or comments. .turbo/ is gitignored, so these references would be opaque to anyone reading without local copies.