implement · diff
git:20261118.549ccf7 to git:20261118.581e4cd
45 added, 41 removed. Audit A to A.
What this update changes in the checks
No check changed: every fixed check gives the same answer before and after this update.
A tripped check is a label, not a verdict: read the matched text and the lines below. This week's updates that newly trip a check.
---
name: implement
- description: Audits a ticket, PRD, or feature slice for ambiguity and codebase feasibility, maps reusable shared UI and helpers, and executes test-first production implementation through full verification. Use when implementing any ticket, GitHub issue, Jira task, or feature slice, even if small.
+ description: Audits any ticket or PRD for ambiguity, designs modular/configurable/optimized solutions reusing shared UI and utilities, executes test-first production code, runs post-ticket independent review, and checkpoints cross-machine handover commits. Use when implementing any ticket, issue, or feature slice.
---
- # Implement (Anti-Yes-Man Ticket Audit → Reuse Map → TDD → Verify)
+ # Implement (Ambiguity Audit → Pre-Code Design → TDD → Post-Ticket Review & Handover)
- Execute **one ticket or vertical slice** from strict ambiguity & feasibility auditing through codebase reuse mapping, test-first production implementation, and closed-loop verification.
+ Build **one ticket or vertical slice** to industrial production quality—never MVP stubs, hardcoded values, or unreviewed diffs.
## Decision tree
- 1. **Does the ticket/PRD/request pass the Ambiguity & Feasibility Audit (Phase 0)?**
- - **No (missing rules, unclear UI states, missing auth/validation/error behavior, or conflict with existing code)** → **STOP. Do NOT write code and do NOT invent defaults.** Call `ask_question` with the exact gaps and proposed `(Recommended)` options.
+ 1. **Does the ticket/PRD/request pass Phase 0 (Ambiguity & Feasibility Audit)?**
+ - **No (unclear rules, UI states, auth/tenancy, config keys, API contracts, or repo conflicts)** → **STOP. Do NOT write code and do NOT invent defaults.** Call `ask_question` with exact gaps and `(Recommended)` options.
- **Yes** → Proceed to step 2.
- 2. **Is the ticket blocked by an unfinished dependency (`Blocked by` in `docs/sprint/SPRINT.md`)?**
- - **Yes** → Stop and report the blocking ticket to the user.
+ 2. **Is the ticket blocked by an unfinished ticket (`Blocked by` in `docs/sprint/SPRINT.md`)?**
+ - **Yes** → Stop and report the blocking ticket first.
- **No** → Proceed to step 3.
- 3. **Is `CONTEXT.md` populated for the target area of the repo?**
- - **No** → Run `/index-project` reconnaissance on the relevant directories first so you know exact existing components, helpers, and commands.
- - **Yes** → Proceed to Phase 1.
+ 3. **Is `CONTEXT.md` populated for the target area of the codebase?**
+ - **No** → Run `/index-project` (including `scan-repo.mjs`) first so you know exact dependencies, UI primitives, config/logging seams, and verification commands.
+ - **Yes** → Execute Phases 1–3 below.
---
## Phase 0: Mandatory Ticket / PRD Ambiguity Audit (Anti-Yes-Man Gate)
- Never blindly implement an incomplete ticket (whether from Jira, Linear, GitHub Issue, chat prompt, or `docs/sprint/tickets/`). Audit these 7 checks against the actual repository:
-
- 1. **Scope & Acceptance Criteria**: Is the observable outcome unambiguous and testable?
- 2. **Actors & Authorization**: Who can access/mutate this? What happens on unauthenticated (`401`) or unauthorized/cross-tenant (`403`/`404`) requests?
- 3. **Inputs, Validation & Boundaries**: Required vs optional fields, min/max lengths, numeric precision, empty/duplicate handling?
- 4. **Data & API Contract**: Exact request/response fields, status codes, schema changes—and do the referenced endpoints/tables/types actually exist in the repo?
- 5. **UI / UX States (if UI)**: Loading, empty, validation error, server error, success feedback, disabled/in-flight state, responsive layout?
- 6. **Failure & Concurrency**: External API timeouts/retries, race conditions, idempotency?
- 7. **Codebase Contradictions**: Does the ticket contradict `CONTEXT.md`, existing types, or current behavior?
+ Audit Jira/GitHub/Linear/chat/Sprint tickets against these 7 checks before designing or coding:
+ 1. **Scope & Acceptance Criteria**: Is every expected behavior and exclusion testable?
+ 2. **Actors & Auth**: Who can access/mutate this? What happens on `401`/`403`/`404` or cross-tenant access?
+ 3. **Inputs & Edge Cases**: Required/optional fields, bounds, formats, empty/duplicate/idempotent cases?
+ 4. **Data & API Contract**: Exact fields, status/error codes, schema migrations—and do referenced tables/endpoints exist?
+ 5. **UI / UX States (if UI)**: Loading, empty, validation error, server/offline error, disabled/in-flight, responsive, disposal?
+ 6. **Config, Logging & Failures**: Env/config keys, timeouts/retries, offline/partial failure behavior?
+ 7. **Codebase Contradictions**: Does anything contradict `CONTEXT.md` or existing code?
- **If any behavior-changing detail is unclear or contradicts the repo:** stop, cite `ticket/PRD` vs `file:line`, and ask the user via `ask_question`.
+ **Hard rule:** If any behavior-changing detail is missing or contradictory, stop, cite `ticket/PRD` vs `file:line`, and call `ask_question`.
---
- ## Phase 1: Codebase Reuse & Touchpoint Plan (Zero Duplication)
+ ## Phase 1: Pre-Code Design, Config/Logging & Reuse Plan
- Before editing or creating any file:
- 1. Search existing directories (`components/`, `ui/`, `shared/`, `lib/`, `utils/`, `hooks/`, `schemas/`, `api/`) for reusable UI primitives, hooks, validators, formatters, and API clients.
- 2. Read every target file and shared primitive/helper you plan to call so imports, props, and types are 100% verified.
- 3. Search all callers of any shared function/type/component you plan to modify (`rg -n` via `run_command` or search tool).
- 4. Lock the **Touchpoint & Reuse Plan**:
- - Exact existing primitives/helpers to **reuse or extend** (never duplicate).
- - Exact files to modify (and justification if a new file is strictly required).
- - Exact public seam & test file to run.
+ Before editing any file:
+ 1. **Reuse Search**: Search `components/`, `widgets/`, `ui/`, `shared/`, `lib/`, `utils/`, `hooks/`, `schemas/`, `api/` and read target primitives/helpers. Lock what you will **reuse or extend** (never duplicate).
+ 2. **Callers Check**: Search all callers (`rg -n`) of any shared symbol/component you plan to modify.
+ 3. **Engineering Design Check** (invoke `/codebase-design` if non-trivial):
+ - Modularity & narrow DI seam at external I/O boundaries.
+ - Performance optimization: zero N+1, optimal data structures, cursor pagination/`ListView.builder`, isolate/worker offload for heavy CPU, `dispose()`/`close()` plan.
+ - Configurability: exact env, `--dart-define`, or typed config keys (zero hardcoded URLs, limits, or secrets).
+ - Structured logging: events, `traceId`, and `<REDACTED>` secret/PII policy.
---
- ## Phase 2: Execute TDD & Complete Production Implementation
+ ## Phase 2: TDD Execution & Optimization
- 1. Follow `/tdd`: write failing tests at the public seam covering happy path, boundary cases (`N-1`/`N`/`N+1`, empty/malformed), auth/permission failure, idempotency/concurrency (where applicable), and failure handling.
- 2. Implement the **smallest complete production slice**—never a happy-path stub. Include real boundary parsing, auth checks, error wrapping, UI states, and observability.
- 3. Keep production code free of mock stores, dummy tokens, simulated delays, and `TODO` stubs.
- 4. Run the focused test file and typechecker after each increment.
+ 1. Follow `/tdd`: write failing public-seam tests (happy path, `N-1`/`N`/`N+1`, invalid/empty, auth, idempotency, failure mode).
+ 2. Implement complete production logic—zero stubs, mock stores, dummy data, hardcoded secrets/URLs, or stray `print`/`console.log`.
+ 3. Run focused tests and static analyzer/typechecker (`dart analyze`, `tsc --noEmit`, etc.) after each step.
---
- ## Phase 3: Definition of Done & Sync
+ ## Phase 3: Post-Ticket Re-Check, Independent Review & Handover Commit
- 1. Run the **full verification command** (typecheck, linter, build, and test suite) via `run_command` after your final edit and verify exit code `0`.
- 2. Inspect `git diff` to verify:
- - Zero test tampering (`.skip`, weakened assertions, SUT mocking).
- - Zero duplicate UI components, parallel utilities, hardcoded theme colors, or unrequested file churn.
- - All sibling callers of modified exports still work.
- 3. If `docs/sprint/SPRINT.md` and ticket files exist: check off `[x]` criteria, record verification output and `Downstream Handover Notes` in the ticket's completion log, and update `SPRINT.md` (proposing a commit only if authorized).
+ 1. **Ticket Re-Check**: Re-read the ticket/PRD line-by-line and confirm every acceptance criterion, UI state, config key, log event, and edge case is implemented.
+ 2. **Black-Box Diff Audit & Full Verification**:
+ ```bash
+ node .agents/skills/implement/scripts/audit-diff.mjs --help
+ node .agents/skills/implement/scripts/audit-diff.mjs
+ ```
+ Then run the project's full test, static analysis, lint, and build commands via `run_command` and confirm exit code `0`.
+ 3. **Mandatory Post-Ticket Review**: Run `/code-review` (using `adversarial-reviewer` via `invoke_subagent` on multi-file diffs) to verify zero defects, zero secret leaks, zero DRY/UI duplication, and optimal performance.
+ 4. **Cross-Machine Handover & Commit**:
+ - Update `CONTEXT.md` if new shared UI, utilities, config vars, or seams were introduced.
+ - Update the ticket completion log, `docs/sprint/SPRINT.md` (promote newly unblocked tickets), and run `/handoff` to update `docs/sprint/HANDOFF.md` + `.scratch/handoff.md`.
+ - Create one atomic Conventional Commit (`feat(scope): ...`) containing this ticket + updated sprint/handover docs if commits were authorized in this session; otherwise present the verified file list and exact commit command/message for user approval.