Agent Skills: Traceability Audit Skill

Map requirements, acceptance criteria, implementation, tests, and release artifacts into one traceability report.

UncategorizedID: hoangnguyen0403/agent-skills-standard/traceability-audit

Install this agent skill to your local

pnpm dlx add-skill https://github.com/HoangNguyen0403/agent-skills-standard/tree/HEAD/.codex/skills/traceability-audit

Skill Files

Browse the full folder contents for traceability-audit.

Download Skill

Loading file tree…

.codex/skills/traceability-audit/SKILL.md

Skill Metadata

Name
traceability-audit
Description
"Map requirements, acceptance criteria, implementation, tests, and release artifacts into one traceability report."

Traceability Audit Skill

[!IMPORTANT] Map requirements, acceptance criteria, implementation, tests, and release artifacts into one traceability report.

Optional args: slug=<feature>, ticket=<id/url>, mode=interactive|autonomous|channel, channel=<id>, auto_continue=true|false, profile=business|hybrid|technical.

Instructions

When the user asks to perform this workflow, execute the following steps:

Traceability Audit Workflow

Goal: Prove every acceptance criterion has implementation and verification evidence before release or handoff.

Steps

  1. Load sources:
    • BRD-lite, PRD, SRS/FRS, AC list, implementation plan, changed files, tests, walkthrough, PR comments, release notes.
    • Jira/GitHub/GitLab/ADO/Zephyr/Confluence MCPs when configured; otherwise use exported files and local evidence.
  2. Build trace map across 4 V-Model levels (skills/quality-engineering/quality-engineering-test-plan-authoring/references/lifecycle-and-roles.md):
    • BRD objective -> PRD requirement ID <-> Acceptance Testing (UAT/signoff).
    • PRD requirement ID -> SRS/FRS contract <-> System Testing (E2E web/mobile scenarios).
    • AC -> exact implementation file/function.
    • AC -> automated test ID, manual/Zephyr TC, or verification step <-> Integration / Unit Testing.
    • Mobile trace (Contract C6): map mobile ACs to app artifact digest/build, OS/device cells, and driver evidence.
    • Release note -> shipped user-visible change. Low-risk work uses equivalent existing evidence; four new docs not required.
  3. Classify each AC & test disposition (STLC Stage 6 Closure):
    • Covered / PASS: implementation file/function exists AND fresh verification evidence verified.
    • Partial: code or verification evidence incomplete.
    • Missing: no implementation or unverified.
    • BLOCKED: missing environment, driver, or credential; listed under missing_evidence.
    • Deferred / Risk-Accepted: formally waived with named human owner, rationale, and expiry.
  4. Flag gaps and open defects:
    • Missing requirement or V-model interface mapping.
    • Missing AC implementation (unmapped file/function).
    • Missing test or manual coverage (unmapped automated test, manual/Zephyr TC, or untested device cell).
    • Open defect ledger with severity, affected AC impact, and owner.
    • Release notes claiming unverified or unreleased capabilities.
    • Write run record to artifacts/runs/[slug]/[compactISO]-traceability-audit.json when file writes allowed.

Runtime Contract

  • Use pre-release or handoff to prove requirement-to-evidence coverage.
  • Required inputs: PRD/SRS with AC list plus implementation, test, and release artifacts to map against.
  • Return BLOCKED only when no requirement or AC list exists to trace.

Handoff Payload

  • slug, requirement map, gap classification, outcome report, next workflow.

Blocking Questions

  • Ask max 3 at a time with a recommended default and 2-3 options.

Output Template

# Traceability Audit

## Summary

## Requirement Map

| Requirement | SRS/FRS Contract | Implementation (File/Fn) | Verification (Test/TC) | Status |
| --- | --- | --- | --- | --- |
| [REQ] | [contract] | [file:fn] | [test/evidence] | [status] |

## Gaps

## Outcome Report
{schema_version: 1, run_id: "[run-id]", slug: "[slug]", workflow: traceability-audit, feature_status: verified, started_at: "[timestamp]", completed_at: "[timestamp]", requirement_trace: {brd_objectives: [], requirements: [], acceptance_criteria: [], srs: []}, completed_evidence: [], missing_evidence: [], decision_needed: [], recommended_next_workflow: deploy-release, cost: {source: unavailable}, agent: {identity: "[agent-identity]", model: "[model]"}}

## Next Workflow

## Cost Report
Call `get_session_cost(workflow="traceability-audit")` before final handoff.