Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/AI & Agent Building
hoangnguyen0403 avatar

Traceability Audit

hoangnguyen0403/agent-skills-standard

This workflow connects every acceptance criterion to its implementation, tests, and release artifacts in one auditable report. You give it your PRD, AC list, code changes, test evidence, and PR history, and it builds a traceability matrix showing what's covered, what's partial, and what's missing verification. It works with Jira, ADO, Zephyr, and Confluence MCPs when configured, or you can feed it exported files. Most useful right before release or handoff when you need to prove compliance or explain gaps to stakeholders. The classification step is the real value here: it forces you to admit when something shipped without tests or when an AC never got implemented at all.

GitHub stars
504
last updated
Jun 11, 2026
View on GitHubSave

Install

$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill traceability-audit --agent claude-code

Installs into .claude/skills of the current project.

Files

Traceability Audit Skill

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

Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, 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.
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/hoangnguyen0403/agent-skills-standard
Categories
AI & Agent Building, Release Management
License
Apache-2.0
First seen
Jun 11, 2026

More from hoangnguyen0403/agent-skills-standard

All 28
  • Update Docs
  • Verify Bug
  • Verify Work
  • Zephyr Coverage Analysis
  • Battle Test
  • Brainstorm Feature
  • Caveman
  • Caveman Commit
  • Caveman Compress
  • Caveman Review
  • Code Review
  • Codebase Review
  • Deploy Release
  • Design Solution
  • Dev Fix
  • Implement Feature
  • Implementation Readiness
  • Pentest
  • Plan Feature
  • Publish Notes
  • Retro Learn
  • Review Ticket
  • Sdlc
  • Security Test

Recommended

More AI & Agent Building
1hoangnguyen0403 avatarupdate-docshoangnguyen0403/agent-skills-standardAutomated workflow to detect and fix missing documentation0installs
2hoangnguyen0403 avatarverify-bughoangnguyen0403/agent-skills-standardPost-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status 0installs
3hoangnguyen0403 avatarverify-workhoangnguyen0403/agent-skills-standardVerify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.0installs
4hoangnguyen0403 avatarzephyr-coverage-analysishoangnguyen0403/agent-skills-standardAnalyze Zephyr test case coverage for a Jira user story and produce a QE management report with metrics, risk scoring, and prioritized recommendations.0installs
5hoangsonww avataranomaly-alerthoangsonww/claude-code-agent-monitor>0installs
6hoangsonww avatarcost-breakdownhoangsonww/claude-code-agent-monitor>0installs