packages/qfai/assets/init/.qfai/assistant/skills/qfai-atdd/SKILL.md
Implement automated acceptance tests (E2E/API/Integration) aligned with US/TC/CON-API obligations from specs and contracts.
npx skillsauth add aganesy/qfai qfai-atddInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
[DRIFT-PROTOCOL:MANDATORY]
.qfai/** artifact, read and follow the relevant directory README template and sample.When unsure, read inputs in this order:
.qfai/assistant/instructions/*.qfai/assistant/steering/*.qfai/specs/<spec-id>/01_Spec.md (Primary SSOT / Consumer View).qfai/specs/<spec-id>/02_User-stories.md (US).qfai/specs/<spec-id>/03_Acceptance-Criteria.md (AC).qfai/specs/<spec-id>/05_Examples.md (EX).qfai/specs/<spec-id>/06_Test-Cases.md (TC).qfai/contracts/api/** (CON-API).qfai/specs/<spec-id>/09_delta.md (Decision Records; if no spec yet, state "not applicable").qfai/specs/<spec-id>/scenario.feature.qfai/specs/<spec-id>/01_Spec.md.qfai/specs/<spec-id>/03_Acceptance-Criteria.md.qfai/specs/<spec-id>/05_Examples.md.qfai/specs/<spec-id>/06_Test-Cases.md01_Spec.md Escalation Hook signals ambiguity / conflict / missing constraint / trade-off.qfai/specs/_policies/01_Objective.md and .qfai/specs/_policies/08_Decisions.md_policies/** by default.This section is mandatory and overrides any conflicting fallback text in this file.
Simulation mode allowed.Subagents: simulated (reason: <why unavailable>)User approval: <quote or reference>Every major artifact in this stage MUST include this fixed table schema:
| Step | Role (sub-agent) | Task title | Input (refs) | Output (refs) | Status (PASS/REVISE) | | ---- | ---------------- | ---------- | ------------ | ------------- | -------------------- | | 1 | <role> | <task> | <refs> | <refs> | PASS/REVISE |
Output (refs) must point to in-file anchors or relative evidence file paths.test-design-analyst defines coverage and layer ownership.acceptance-test-engineer implements E2E, API, and integration acceptance tests.devops-ci-engineer captures execution evidence when CI/runtime proof is needed.orchestrator consolidates delegated outputs and presents results.completion-reviewer is delegated independently and returns only PASS or REVISE.completion-reviewer.test-layers.md.US, Integration covers TC, API covers CON-API.references/test-case-depth-checklist.md).qfai validate --fail-on error passes.scenario.feature and coverage ledgers are optional legacy inputs, not completion gates..qfai/assistant/steering/agent-routing.yml.completion-reviewerqa-gatekeeperimplementation-reviewer only when helper/runtime support code changed.PASS.Task title: <short>
Role: <sub-agent role>
Goal: <what to decide/produce>
Inputs (refs):
- <file/section>
Constraints:
- must: enforce Drift Protocol (no upstream edits without user approval + CR)
- must: verify test-layer obligations from `steering/test-layers.md`
- must: provide validation evidence (`qfai validate --fail-on error`)
- must_not: treat volume ratios/floors as hard gates
- must_not: accept upstream edits made directly by downstream phase
Output format:
- <headings / bullet schema>
Quality bar:
- PASS if ...
- REVISE if ...
Result: PASS | REVISE
Findings:
- <issue>
Required fixes:
- <action>
Evidence checked:
- <refs>
Before moving forward in this stage, refresh:
.qfai/assistant/steering/manifest.md.qfai/assistant/steering/product.md.qfai/assistant/steering/structure.md.qfai/assistant/steering/tech.mdRules:
<...>, TBD, stale facts).[RE-OPEN] Decision Record that references prior DR-ID and explicit approval.10_Plan.md is the primary How SSOT for execution phases.10_Plan.md is missing, stop and run owner planning flow before proceeding.qfai validate --fail-on error).tests/e2e/** must cover all required US-*.tests/integration/** must cover all required TC-*.tests/api/** must cover all required CON-API-*.tests/api/** must not contain QFAI:SPEC-XXXX:TC-YYYY.tests/e2e/** must not contain QFAI:SPEC-XXXX:TC-YYYY.US/TC/CON-API not declared) must be treated as errors.scenario.feature or coverage ledgers may exist but are not mandatory inputs for completion..qfai/evidence/ and must not be committed.Before declaring completion, you MUST:
TBD, TODO, ???, etc.).Turn specs/contracts obligations (US / TC / CON-API) into runnable acceptance tests in this repository.
/qfai-implement).references/test-case-depth-checklist.md)US / TC / CON-API)PASS or concrete rework list).qfai/evidence/atdd-<spec-id>.mdUS-*CON-API-*TC-*| Layer | Raw count | Signal | Evidence | Notes | | ----------- | --------: | -----: | ------------- | ----- | | E2E | #US | E2E_s | user stories | | | API | #CON | API_s | API contracts | | | Integration | #TC | INT_s | test cases | |
Every generated ATDD test MUST include QFAI annotations by layer:
tests/e2e/**: QFAI:SPEC-XXXX:US-YYYYtests/integration/**: QFAI:SPEC-XXXX:TC-YYYYtests/api/**: QFAI:CON-API-XXXXNotes:
QFAI:CON-API-* in E2E is not forbidden, but contract guarantee belongs to API tests.US are covered by E2E tests.TC are covered by integration tests.CON-API are covered by API tests.qfai validate --fail-on error.US / TC / CON-API remains uncovered.Create and update: .qfai/evidence/atdd-<spec-id>.md
Required sections:
Template:
# ATDD Evidence: <spec-id>
## Objective
## Inputs reviewed (files/paths)
## Decisions made (with rationale)
## Work performed (what changed, where)
## Commands executed + key outputs
## Test volume estimate
## Coverage obligations checklist
## Work Orders Summary
## Execution logs
## Gaps / Open risks
## Final status (PASS/FAIL) + who confirmed
test-design-analyst evaluates test cases using references/test-case-depth-checklist.md, produces Coverage Depth Matrix, flags gaps in boundary/error/edge coverage.US coverage.CON-API coverage.TC coverage.PASS or REVISE only).Before declaring completion:
Confirm required US / TC / CON-API coverage is complete.
Run:
qfai validate --fail-on error
Run repository standard gates:
Record exact commands and outcomes.
If commands cannot be run due to environment limits, request user execution and do not assume PASS.
When declaring DONE, include:
When this skill is complete, provide a final user-facing completion message and enumerate all actionable next steps.
/qfai-implement.
Action: run unified TDD micro-cycle (Red/Green/Refactor) one test at a time from test-list.md./qfai-atdd.
Action: close uncovered US / TC / CON-API obligations and rerun validation.testing
# /qfai-prototyping-full-harness [DRIFT-PROTOCOL:MANDATORY] Premium prototyping skill with planner/generator/evaluator iteration loop. Full-harness mode is an **explicit, non-default** path activated only via `qfai prototyping --mode full-harness` or discussion artifact recommendation. > This skill defines a real execution workflow — it is NOT a routing-only redirect. ## When to Use - Projects requiring L3–L5 fidelity evidence (production-ready prototypes). - Evaluation needs: weighted mult
testing
# /qfai-prototyping-full-harness [DRIFT-PROTOCOL:MANDATORY] Premium prototyping skill with planner/generator/evaluator iteration loop. Full-harness mode is an **explicit, non-default** path activated only via `qfai prototyping --mode full-harness` or discussion artifact recommendation. > This skill defines a real execution workflow — it is NOT a routing-only redirect. ## When to Use - Projects requiring L3–L5 fidelity evidence (production-ready prototypes). - Evaluation needs: weighted mult
testing
Run and document quality gates (repo + qfai validate/report), fix until PASS.
testing
Create and update layered SDD artifacts ( policies + spec-XXXX) in one workflow.