Official agent skill

Create a Verification Skill

by cursor in cursor/plugins

Generates a project-local skill that launches your app, exercises a feature the way a user would and captures evidence, for web, CLI, API or desktop projects.

OfficialNo licenceAuto-check passedTesting & QA

Install Create a Verification Skill

skills CLI
$ npx skills add cursor/plugins --skill create-verification-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cursor/plugins create-verification-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cursor/plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/pstack/skills/create-verification-skill .claude/skills/create-verification-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
create-verification-skill
GitHub stars
10k
Used in
8 other repos
Token cost
~1.5k tokens
SKILL.md length
868 words
Files
4 (incl. references)
Skills in repo
99
Repo updated
First seen
Licence
None found

At a glance

Generates a project-local skill that launches your app, exercises a feature the way a user would and captures evidence, for web, CLI, API or desktop projects.

  • Works in 5 steps: Interview the repo, not the user → Generate the skill → Seed the feature map → …
  • A repository has no scripted way to prove that its UI, CLI or service works
  • SKILL.md covers 1. Interview the repo, not the…, 2. Generate the skill, 3. Seed the feature map and 4. Prove the generated skill…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill generates a project-local verification skill, stored under `.cursor/skills/`, that tells a later agent how to launch the real app, use a feature the way a user would and capture evidence. It works for any language, framework or platform, and the output is written for an agent that will read it cold in the middle of a task, not for a person.

Generation starts by interviewing the repository rather than you, asking only for what cannot be observed. It works out the surface users touch (web UI, CLI or TUI, desktop, API, mobile or library), how the app starts locally, how an agent can drive it, what evidence can be captured and whether two instances can run side by side. Existing harnesses such as Playwright or Cypress specs come first; otherwise it picks a recipe such as a browser with CDP for web and Electron, a tmux or PTY harness for terminal apps, or plain HTTP for services. If the checkout does not build or start, that is fixed or reported first.

The generated `SKILL.md` needs YAML frontmatter with a name and a description naming the app, the surface and when to use it, since the skill will not register without it, and every section must reflect what the interview found, with no placeholders left. A feature-map example with a README and note-creation and search files is included as reference.

When your agent uses it

  • A repository has no scripted way to prove that its UI, CLI or service works
  • Creating a control skill so future agents can launch and exercise the app
  • Recording screenshots, transcripts or response bodies as evidence of behavior

Example prompts

  • “Create a verification skill for this repo so agents can launch the app and test the search feature.”
  • “Make a control skill for this CLI that records terminal transcripts as evidence.”
  • “We have no scripted way to check the dashboard UI. Generate one that takes screenshots.”

Requirements

  • A repository that builds and starts locally

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Interview the repo, not the user
  2. Generate the skill
  3. Seed the feature map
  4. Prove the generated skill before handing it over
  5. Offer the maintenance loop

What it can do on your machine

Read from SKILL.md and the folder at commit ccb5507. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Create a Verification Skill loads about 1.5k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 868 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 868 words (~1,468 tokens).

“Every serious project needs a scripted way to drive the real app and prove behavior: launch it, exercise a feature the way a user would, and capture evidence. This skill generates that as a project-local skill (.cursor/skills/verify-/) tailored to the…”

— opening of SKILL.md by cursor
name
create-verification-skill
disable-model-invocation
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (references) in pstack/skills/create-verification-skill of cursor/plugins.

  • SKILL.md
  • references/feature-map-example/README.md
  • references/feature-map-example/create-note.md
  • references/feature-map-example/search.md

Open the folder on GitHubat commit ccb5507

Used in 8 other repositories

We found 8 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in cursor/plugins, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Create a Verification Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Create a Verification Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create a Verification Skill this skillcursor/plugins10k8 repos~1.5kAutomated safety check: PassNone
Heavy Verify Loop for Peri TUIKonghaYao/peri223—~2.1kAutomated safety check: NotesApache-2.0
Cypress To Scout Migrationelastic/kibana21k—~3.8kAutomated safety check: PassCustom licence
E2E Testing Patternstry-works/role-model11814 repos~990Automated safety check: PassCustom licence
Verify Omnigent End-to-Endomnigent-ai/omnigent11k—~1.6kAutomated safety check: PassApache-2.0
Playwright Testingchongdashu/vibejam-starter-pack149—~2.1kAutomated safety check: PassNone

Similar skills

  • Verifies and repairs a feature by using the real Peri terminal UI as a user would, looping verify, decide, fix and review until a fresh round shows no blockers.

    223 GitHub stars~2.1k tokensUpdated today
    Testing & QAAuto-check: notes
  • Official

    Migrate Kibana Cypress E2E tests (.cy.ts) to Scout (Playwright).

    21k GitHub stars~3.8k tokensUpdated today
    Testing & QAAuto-check passed
  • E2E Testing Patterns

    try-works/role-model

    Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment.

    118 GitHub starsUsed in 14 repos~990 tokens
    Testing & QAAuto-check passed
  • Verify Omnigent End-to-End

    omnigent-ai/omnigent

    Spins up an isolated Omnigent server, runner and mock model to prove a user-facing behavior or bug fix with recorded evidence instead of reasoning from code.

    11k GitHub stars~1.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Playwright Testing

    chongdashu/vibejam-starter-pack

    Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.

    149 GitHub stars~2.1k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed
  • Open Browser

    JasonHonKL/Openbrowser

    A skill your agent uses whenever the task involves browsing web pages, extracting page content, clicking forms, or completing web workflows.

    114 GitHub stars~1.6k tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

More from cursor/plugins

All 99 skills in this repo
  • Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    10k GitHub starsUsed in 9 repos~1.6k tokens
    Auto-check passed
  • Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    Auto-check passed
  • Official

    Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.

    10k GitHub starsUsed in 5 repos~1.2k tokens
    Auto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Auto-check passed
  • Advisor Mode

    cursor/plugins

    Official

    Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.

    10k GitHub stars~2.6k tokensUpdated today
    Auto-check: notes
  • Official

    Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.

    10k GitHub starsUsed in 3 repos~569 tokens
    Auto-check passed

Questions about Create a Verification Skill

What does Create a Verification Skill do?

Generates a project-local skill that launches your app, exercises a feature the way a user would and captures evidence, for web, CLI, API or desktop projects. cursor/skills/`, that tells a later agent how to launch the real app, use a feature the way a user would and capture evidence. It works for any language, framework or platform, and the output is written for an agent that will read it cold in the middle of a task, not for a person.

When should I use Create a Verification Skill?

Create a Verification Skill fits situations like: A repository has no scripted way to prove that its UI, CLI or service works; creating a control skill so future agents can launch and exercise the app; recording screenshots, transcripts or response bodies as evidence of behavior.

How do I install Create a Verification Skill in Claude Code?

Run `npx skills add cursor/plugins --skill create-verification-skill -a claude-code`. Or copy the skill folder (pstack/skills/create-verification-skill in cursor/plugins) into .claude/skills/create-verification-skill in your project. Claude Code loads it when a task matches its description.

How do I install Create a Verification Skill in Codex?

Run `npx skills add cursor/plugins --skill create-verification-skill -a codex`. Or copy the skill folder (pstack/skills/create-verification-skill in cursor/plugins) into .agents/skills/create-verification-skill in your project. Codex loads it when a task matches its description.

Can I use Create a Verification Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cursor/plugins --skill create-verification-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-verification-skill, .gemini/skills/create-verification-skill, .github/skills/create-verification-skill and .opencode/skills/create-verification-skill in your project.

What does Create a Verification Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: Create a Verification Skill is instructions for the agent only. Our summary lists: A repository that builds and starts locally.

Does Create a Verification Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Create a Verification Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Create a Verification Skill use?

No licence was found for Create a Verification Skill or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Create a Verification Skill use?

About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.

What are the alternatives to Create a Verification Skill?

Skills that share tags, products or a category with Create a Verification Skill: Heavy Verify Loop for Peri TUI (KonghaYao/peri, 223 stars), Cypress To Scout Migration (elastic/kibana, 21k stars), E2E Testing Patterns (try-works/role-model, 118 stars) and Verify Omnigent End-to-End (omnigent-ai/omnigent, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create a Verification Skill?

cursor (a GitHub organization, an official publisher) maintains it in cursor/plugins, which has 10,278 GitHub stars. The repository holds 99 skills in this directory. The repository was last updated on October 8, 2026.

Source: cursor/plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.