Skip to content
Development
Command

/traceability-audit

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

From plugin
agent-skills-standard
57033 skills21 agents33 commands1 MCP
Install
$ npx -y skills add hoangnguyen0403/agent-skills-standard --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/traceability-audit

Context preview

What this command does when you run it.

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

Command definition

traceability-audit.md

Traceability Audit

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

**Input:** $ARGUMENTS

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

Instructions

Execute the following steps for **$ARGUMENTS**.

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:

  • BRD objective -> PRD requirement ID.
  • PRD requirement ID -> SRS/FRS contract.
  • AC -> implementation file/function.
  • AC -> automated test, manual/Zephyr TC, or verification step.
  • Release note -> shipped user-visible change.

3. Classify each AC:

  • Covered: code and verification evidence exists.
  • Partial: code or evidence incomplete.
  • Missing: no implementation or no verification.
  • Out of scope: explicitly deferred with owner/link.

4. Flag gaps:

  • Missing requirement mapping.
  • Missing AC implementation.
  • Missing test or manual coverage.
  • Release note missing shipped user impact.

5. Persist:

  • Write the run record to `artifacts/runs/[slug]/[compactISO]-traceability-audit.json` when file writes are 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 | Verification | Status |
| --- | --- | --- | --- |
| [REQ] | [contract] | [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.
Read more
Ships withagent-skills-standard

The portable SDLC standards layer for AI coding agents. Sync once, then work in your own runtime.

Get the whole plugin

Other commands on agent-skills-standard.