mcpbeat Sign in

Verify Work Agent Skill

Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.

907 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
536
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/HoangNguyen0403/agent-skills-standard --skill verify-work

The instruction itself

9 sections, as written by the author

Verify Work Skill

> [!IMPORTANT]

> Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria.

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:

Verify Work Workflow

Goal: Prove the delivered change works against explicit acceptance criteria before handoff.

Steps

  • Load scope:
  • BRD-lite, PRD, SRS/FRS, ticket, implementation plan, release note, acceptance criteria, non-goals, changed files, matched skills, and inherited operator_profile (carry, do not re-infer).
  • Select verification lanes:
  • Unit/component, integration/API, E2E/visual, mobile, security, migration, or deployment smoke.
  • Execute:
  • Run the smallest reliable automated checks first.
  • Use Playwright/Appium only when user-facing behavior changed.
  • Use Zephyr/Jira/GitHub/GitLab/ADO MCPs only when configured; otherwise record local evidence.
  • If external MCP is unavailable, ask for exported ticket/PR/TC data or mark that lane BLOCKED.
  • Capture Evidence: logs, screenshots, traces, or terminal output summaries.
  • Comparative Audit: If it's a bug fix, prove the "Before" (failure) vs "After" (success).
  • Judge:
  • PASS: all acceptance criteria proven.
  • FAIL: original bug or missed requirement still reproducible.
  • BLOCKED: environment, credentials, or approval prevents proof.
  • Record evidence:
  • If verification reveals behavior drift, require PRD/SRS updates before PASS.
  • Update traceability notes from BRD objective -> PRD requirement -> SRS/FRS contract -> verification evidence.
  • Update project-local docs/srs/srs-walkthrough.md.
  • Route next step back to implementation or dev-fix.

Runtime Contract

  • Use after implementation, before handoff, or when validating a bug fix.
  • Required inputs: explicit scope plus acceptance criteria or expected behavior.
  • Return BLOCKED only when environment, credentials, or approval prevents proof.

Handoff Payload

  • operator_profile, verification report, AC trace, comparative evidence, risks observed, updated walkthrough path, outcome report, next workflow.

Blocking Questions

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

Artifact Template

# Walkthrough: [Name]

## Scope

## Acceptance Criteria Trace

| AC ID   | Status    | Proof / Evidence Link |
| ------- | --------- | --------------------- |
| [ac-id] | PASS/FAIL | [link/summary]        |

## Comparative Evidence (Before vs After)

## Negative Testing Proof (Fail Cases)

## Evidence (Screenshots/Logs)

## Risks Observed

## Next Workflow

Output Template

# Verification Report: [Name]
## Scope
## Checks Run (Lanes)
## Acceptance Criteria Status
## Requirement Trace Status (Business -> Test)
## Observed Risks & Edge Cases

## Outcome Report
feature_status: implemented | partially_implemented | blocked
requirement_trace: BRD-OBJ-* -> REQ-* -> AC-* -> SRS-* -> evidence
completed_evidence: []; missing_evidence: []; decision_needed: []; recommended_next_workflow: uat-signoff | dev-fix | implement-feature

## Next Workflow
uat-signoff | implement-feature | dev-fix
## Cost Report
Call `get_session_cost(workflow="verify-work")` before final handoff.

Other skills for the same job

different authors, same section of the catalogue
Modal
by christophacham
×3

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

17k tokens
Github Workflow Automation
by ComeOnOliver
×3

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

9k tokens
Gcloud
by Dicklesworthstone
×2

Google Cloud Platform CLI - manage GCP resources including Compute Engine, Cloud Run, GKE, Cloud Functions, Storage, BigQuery, and more.

2k tokens
Backend Architect
by ComeOnOliver
×2

Expert backend architect specializing in scalable API design, microservices architecture, and distributed systems. Masters REST/GraphQL/gRPC APIs, event-driven architectures, service mesh patterns, and modern backend frameworks. Handles service boundary definition, inter-service communication, resilience patterns, and observability. Use PROACTIVELY when creating new backend services or APIs.

7k tokens
Modal
by ComeOnOliver
×2

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

37k tokens
Aspire
by github
vendor ×1

Aspire skill covering the Aspire CLI, AppHost orchestration, service discovery, integrations, MCP server, VS Code extension, Dev Containers, GitHub Codespaces, templates, dashboard, and deployment. Use when the user asks to create, run, debug, configure, deploy, or troubleshoot an Aspire distributed application.

21k tokens
Bigquery Pipeline Audit
by github
vendor ×1

Audits Python + BigQuery pipelines for cost safety, idempotency, and production readiness. Returns a structured report with exact patch locations.

1k tokens
Msstore CLI
by github
vendor ×1

Microsoft Store Developer CLI (msstore) for publishing Windows applications to the Microsoft Store. Use when asked to configure Store credentials, list Store apps, check submission status, publish submissions, manage package flights, set up CI/CD for Store publishing, or integrate with Partner Center. Supports Windows App SDK/WinUI, UWP, .NET MAUI, Flutter, Electron, React Native, and PWA applications.

4k tokens

How to use it

Copy the folder

Take hoangnguyen0403/verify-work from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.