greenfield-inc/pane/quick-verify

Claude Code and agent skill by greenfield-inc/pane

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use while working to confirm a change does what you meant before moving on. Observe its real effect the way a user or caller would, compare that with your intent, fix what is off, and observe again.

Install

npx vskill@latest install greenfield-inc/pane/quick-verify

SKILL.md

Quick verify

Code that compiles, and tests that pass, can still do the wrong thing. The only proof is the real effect, seen from where it matters. Run this loop yourself, between edits, in minutes. It is not a full QA pass; use qa-and-verify for that on a finished pull request.

The loop

  1. Say what "working" looks like. One or two sentences, in terms someone could see: "the settings page shows the new toggle, off by default", "export --csv writes a header row". If you cannot say it, you are not ready to check it.
  2. Pick the most faithful cheap way to observe it. Look from where the effect lands: the screen a user sees, the response a caller gets, the file or row that gets written, the log a job emits. Prefer the tool the repository already uses. Find how to run things in AGENTS.md, the README, or the package scripts, and never invent a launch command.
  3. Produce the state. Run the app, command, or job with realistic input. Reuse what is already running; stop only what you start.
  4. Capture evidence. Save it under tmp/verify/<change>/ with ordered names (01-before, 02-after) so each attempt sits next to the last. Capture the states that matter, not only the happy path.
  5. Judge it critically. Compare it with step 1, then check around the change for what else it touched. Believe the evidence over your expectation.
  6. Fix and observe again the same way, until the evidence shows what you meant.

Examples

ChangeObserveLook for
Web UIScreenshot the dev server (Playwright, Cypress, or a temporary script)Layout, spacing, empty and error states, a narrow viewport
Mobile UISimulator or device screenshotThe same, plus safe areas and keyboard overlap
API or backendOne real request, and read the response and the logsStatus, shape, edge input, the error path
CLI or scriptRun it with real argumentsOutput, exit code, files written
Job, queue, or migrationRun it once on test data, then read what changedThe rows or records it touched, and running it twice
Library functionCall it from a scratch script or one focused testReturn value at the edges
Docs or copyRender it and read it as a newcomer wouldWrong commands, missing steps

Always

  • Never commit anything under tmp/verify/, and never point a check at production.
  • Report what you checked, how, and what you did not check.

Security

  • Security scanPassed, 96 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/greenfield-inc/pane/quick-verify/badge)](https://verified-skill.com/skills/greenfield-inc/pane/quick-verify)

Something wrong with this skill or its page? Tell us.