Skip to content
Agent Orchestration
Skill

/plan-verify

Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.

From plugin
vmark
49819 skills9 agents7 commands2 MCP
Install
$ npx -y skills add xiaolai/vmark --skill plan-verify --agent claude-code

How it fires

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

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/plan-verify

Context preview

The summary Claude sees to decide when to auto-load this skill.

Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.

SKILL.md

plan-verify.SKILL.md
name: plan-verify
description: Verify a completed implementation against a plan by running gates and checking acceptance criteria. Use when the user asks to verify work items or confirm completion.

Plan Verify

Overview

Runs the plan’s required tests/gates and validates acceptance criteria, producing a pass/fail verification report.

Workflow (Verify)

1) **Locate the plan**

  • Prefer `dev-docs/plans/<plan>.md`.
  • If unclear, ask for the plan path.

2) **Extract verification checklist**

  • For each WI, list:
  • Acceptance criteria
  • Required tests
  • Manual checks (if any)

3) **Run gates**

  • Use repo-specific gates from `.claude/commands/feature-workflow.md` or plan “Testing Procedures”.
  • If tests are not runnable, note the blocker explicitly.

4) **Verify acceptance**

  • For each WI, mark each acceptance criterion as Pass/Fail/Blocked.
  • Include evidence (test output, file refs, manual steps).

5) **Report results**

  • Summarize pass/fail with concrete next actions.

Output Format (required)

  • **Verification Summary**
  • Total WIs verified
  • Pass/Fail/Blocked counts
  • **Gate Results**
  • Command → status
  • Failures with key error lines
  • **Acceptance Matrix**
  • WI‑### → criterion → Pass/Fail/Blocked
  • **Manual Checks**
  • Steps executed + outcome

Verification Rules

  • Always run tests unless the user explicitly forbids it.
  • If tests are skipped or fail, mark WI as **Blocked**.
  • Do not claim “verified” without test evidence.
  • Manual checks must include evidence (step list + observed result).
Read more
Ships withvmark

The Plain-Text Workspace Where Humans and AI Collaborate Free. Local-first. Format-aware. VMark is the plain-text workspace where humans and AI collaborate.

Get the whole plugin