Skip to content
Back to skills

Verify Work

ASecurity

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

  • 549 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added June 6, 2026
developmentgotestinggitapisecurity

Works with

  • terminal
  • cli
  • api
  • mcp

Security analysis

A100/100

Scanned October 3, 2026

npx -y skills add HoangNguyen0403/agent-skills-standard --skill verify-work --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Verify Work?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Verify Work
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hoangnguyen0403-verify-work/badge)](https://www.skillsdirectory.com/skills/hoangnguyen0403-verify-work)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: verify-work
description: "Verify feature, bug, UI, API, mobile, security, or deployment work against acceptance criteria."
metadata:
  internal: true
  triggers:
    keywords:
    - verify work
    - workflow
---
# 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
1. 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).
2. Select verification lanes:
   - Unit/component, integration/API, E2E/visual, mobile, security, migration, or deployment smoke.
3. Execute:
   - Run the smallest reliable automated checks first.
   - Use Playwright/Appium only when user-facing behavior changed. Run the driver skill's `scripts/preflight.sh` and take the first rung that works (web: `playwright-cli` → Playwright MCP; mobile: Appium MCP local → cloud). A lane whose driver is missing and has no exported evidence is `BLOCKED (driver: <name>)`.
   - Use Zephyr/Jira/GitHub/GitLab/ADO MCPs only when configured; otherwise ask for exported ticket/PR/TC data or mark that lane BLOCKED.
   - **Capture Evidence**: logs, screenshots, traces, or terminal output summaries, under `.playwright-cli/<session>/` or `.appium-mcp/<session>/` as `<AC|step>-<before|after>.*`.
   - **Comparative Audit**: If it's a bug fix, prove the "Before" (failure) vs "After" (success).
4. Judge:
   - PASS: all acceptance criteria proven. FAIL: original bug or missed requirement still reproducible.
   - BLOCKED: environment, credentials, or approval prevents proof.
5. 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-[slug].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
```md
# 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)

driver: playwright-cli | playwright-mcp | appium-mcp | none (BLOCKED); evidence_dir: <relative path>

## Risks Observed

## Next Workflow
```

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

## Outcome Report
{schema_version: 1, run_id: "[run-id]", slug: "[slug]", workflow: verify-work, feature_status: implemented, started_at: "[timestamp]", completed_at: "[timestamp]", requirement_trace: {brd_objectives: [], requirements: [], acceptance_criteria: [], srs: []}, completed_evidence: [], missing_evidence: [], decision_needed: [], recommended_next_workflow: uat-signoff, cost: {source: unavailable}, agent: {identity: "[agent-identity]", model: "[model]"}}

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

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…