Agent skill

Spot Check

Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test.

MITAuto-check passedTesting & QA

Install Spot Check

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a claude-code

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

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check --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/ZenUml/web-sequence.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/spot-check .claude/skills/spot-check && 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/

Paste into Claude Code

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .claude/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/spot-check .agents/skills/spot-check && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .agents/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/spot-check .cursor/skills/spot-check && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .cursor/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/ZenUml/web-sequence.git --path .claude/skills/spot-check

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/spot-check .gemini/skills/spot-check && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .gemini/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/spot-check .github/skills/spot-check && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .github/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add ZenUml/web-sequence --skill spot-check -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install ZenUml/web-sequence spot-check --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/ZenUml/web-sequence.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/spot-check .opencode/skills/spot-check && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "spot-check" agent skill from https://github.com/ZenUml/web-sequence/tree/master/.claude/skills/spot-check into .opencode/skills/spot-check/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spot-check", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: spot-check
GitHub stars: 150
Token cost: ~1.7k tokens
SKILL.md length: 725 words
Files: 2
Skills in repo: 7
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test.

Works in 3 steps: Behavior — what changed or what you are… → Observable signal — DOM text in… → Method — Playwright step, pnpm exec…
Run a spot check on X
SKILL.md covers Key principles, Write the plan first, Choosing the environment and Verification methods, plus 6 more sections
Calls pnpm and yarn; reaches staging.zenuml.com

What it does

Spot Check is an agent skill from ZenUml/web-sequence. Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test. Use after developing a feature, fixing a bug, validating a branch, checking staging, or post-release on app.zenuml.com. Drives Playwright (CLI or MCP) against the live app and demo-frame preview. Triggers on "spot check", "run a spot check on X", "spot check this fix", "spot check on staging", "spot check staging.zenuml.com", "verify on prod".

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Testing & QA, covering Browser testing, End-to-end testing and Diagrams. It works with Playwright and Model Context Protocol. The repository describes itself as: Realtime tool for generating sequence diagrams. The licence is MIT.

When your agent uses it

Run a spot check on X
Spot check this fix
Spot check on staging
Spot check staging.zenuml.com

Example prompts

“spot check”
“run a spot check on X”
“spot check this fix”
“/spot-check”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Behavior — what changed or what you are verifying
Observable signal — DOM text in #demo-frame, visible SVG, modal title, localStorage key, network response, etc.
Method — Playwright step, pnpm exec playwright test …, screenshot, console check

What it can do on your machine

Read from SKILL.md and the folder at commit e38bd91. 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
Shell commands in SKILL.md call:
- pnpm
- yarn
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- staging.zenuml.com
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

Spot Check loads about 1.7k tokens when it runs. Until then it costs about 117 tokens; SKILL.md has 725 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~117
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k

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

The full file from ZenUml/web-sequence at commit e38bd91, republished under its MIT licence (© ZenUml). 725 words, ~1,747 tokens.

Download SKILL.mdSave it as .claude/skills/spot-check/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: spot-check
description: Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test. Use after developing a feature, fixing a bug, validating a branch, checking staging, or post-release on app.zenuml.com. Drives Playwright (CLI or MCP) against the live app and #demo-frame preview. Triggers on "spot check", "run a spot check on X", "spot check this fix", "spot check on staging", "spot check staging.zenuml.com", "verify on prod".

Spot Check

A spot check is an ad hoc, AI-driven, ephemeral verification of a specific behavior. It is not meant to become a permanent regression suite entry unless the team explicitly promotes it later.

What it is NOT: inventing a new e2e/tests/*.spec.js during the spot check, a full regression pass, or a substitute for CI.

What it CAN reuse: existing Playwright specs as recipes (run them; do not edit them unless fixing a real bug).

Key principles

Lightweight — smallest set of checks that cover the delta.
AI-driven — plan assertions first, then execute with Playwright CLI and/or browser tools.
Ephemeral — steps live in the chat/report, not a new committed test file.
Targeted — verify the behavior under review, not every sidebar modal.
Real world — prefer deployed staging/prod when the question is “did the deploy work?”

Write the plan first

STOP. Do not open the browser or run Playwright until the plan is written.

Each planned check must name:

Behavior — what changed or what you are verifying
Observable signal — DOM text in #demo-frame, visible SVG, modal title, localStorage key, network response, etc.
Method — Playwright step, pnpm exec playwright test …, screenshot, console check

Each item must be independently pass/fail before you run it.

text

Spot check plan: <short title>

Target: <http://127.0.0.1:3000 | https://staging.zenuml.com | https://app.zenuml.com>
  - [ ] <specific observable assertion>  [method]
  - [ ] <specific observable assertion>  [method]

Skipped: <anything out of scope> — <reason>

For post-release spot checks (release delta, commit triage, N/A rules), follow Step 5.5 in the release-app skill.

For branch validation before push, follow Step 3 in the validate-branch skill after writing the plan here.

Choosing the environment

Situation	Target
Unreleased frontend (local branch)	`yarn dev` → `http://127.0.0.1:3000` (Vite default)
PR / “did staging deploy work?”	`https://staging.zenuml.com`
Production issue or post-release	`https://app.zenuml.com`
Prod-build bundling only (no deploy)	`PW_PROD_BUILD=1 pnpm exec playwright test e2e/tests/production-build.spec.js`
CI already green on staging	Trust gate, then spot-check only the delta on staging or prod

Verification methods

Signal	How
Diagram render / DSL	Set CodeMirror value or type; poll `#demo-frame` `contentDocument` for SVG + label text; screenshot preview
Editor / modals / pages	Playwright on parent page (`getByTitle`, `getByRole('dialog')`)
Save / localStorage	`Meta+s` / `Control+s`; poll `item-*` keys (see `e2e/tests/smoke.spec.js`)
Deployed URL regression (broad)	`PW_BASE_URL=<url> pnpm exec playwright test --project=chromium`
DSL shapes (recipe)	`PW_BASE_URL=<url> pnpm exec playwright test e2e/tests/dsl-spot-check.spec.js --project=chromium --workers=1`
Fast prod sanity (recipe)	`PW_BASE_URL=https://app.zenuml.com pnpm exec playwright test --grep @smoke --project=chromium`
Analytics (optional)	Mixpanel MCP if the change emits events

Pre-flight (UI checks)

Before interacting on any URL:

Suppress first-save dialog (unsigned-in): in page.addInitScript or browser console before reload: localStorage.setItem('loginAndsaveMessageSeen', 'true')
Preview iframe — most diagram truth lives in #demo-frame, not the parent DOM. Use page.frameLocator('#demo-frame') or contentDocument polling like the smoke spec.
Third-party noise — GTM/Zaraz/Paddle may throw; CI ignores known sources (THIRD_PARTY_ERROR_SOURCES in smoke.spec.js). Do not fail the spot check on those alone.

Show full SKILL.md (290 more words)Show less

Workflow

Plan — behavior, target URL, observable assertion per line (see above).
Choose environment — table above.
Execute — run each [ ] check; capture screenshots for diagram assertions (render-diagram-* style evidence in report).
Report — pass / fail / skipped per assertion; attach screenshot paths or Playwright report URL.

text

Spot check report: <title>
- Target: <url>
- Results: <n> pass, <n> fail, <n> skipped
- Evidence: <screenshots / playwright report / CI run>
- Failures: <assertion> — <what you saw>

Playwright recipes (existing specs)

Use these when they match the plan — do not treat running a spec as “the whole spot check” unless the delta is genuinely “general deploy health.”

Recipe	Command
Full staging gate (CI parity)	`PW_BASE_URL=https://staging.zenuml.com pnpm exec playwright test --project=chromium --workers=1`
DSL + diagram screenshots	`PW_BASE_URL=<url> pnpm exec playwright test e2e/tests/dsl-spot-check.spec.js --project=chromium --workers=1`
Prod smoke subset	`PW_BASE_URL=https://app.zenuml.com pnpm exec playwright test --grep @smoke --project=chromium`
Static `dist/` guard	`pnpm build && PW_PROD_BUILD=1 pnpm exec playwright test e2e/tests/production-build.spec.js --project=chromium`

After a recipe run, open the HTML report if the user needs visual proof:

bash

pnpm exec playwright show-report

Browser tooling

Tool	Use for
Playwright CLI	Repeatable checks, CI parity, screenshot attachments in report
Playwright MCP (`user-playwright`)	Ad-hoc navigation when CLI is awkward
cursor-ide-browser	Quick visual confirmation; use `browser_cdp` / `Runtime.evaluate` for `#demo-frame` innards

The preview iframe is same-origin accessible from Playwright tests; still scope selectors to the frame for diagram content.

Skill	When
validate-branch	Pre-push; write plan here, then execute
release-app	Step 5.5 — release-delta spot check after publish
ship-branch	Merge path; staging gate is CI, not a substitute for delta spot check
babysit-pr	Fix CI, not product verification

Rules

Never mark PASS without observing the planned signal (text in iframe, screenshot, or green Playwright assertion).
Never write a new spec file during a spot check unless the user asks to promote the check into CI.
Never spot-check prod with destructive flows (account deletion, billing, mass Firebase writes).
Prefer staging for experimental DSL edits; use prod for release-delta confirmation only.

Files

SKILL.md and 1 other file in .claude/skills/spot-check of ZenUml/web-sequence.

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit e38bd91

Compare with similar skills

Spot Check 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.

Spot Check compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Spot Check this skillZenUml/web-sequence	150	—	~1.7k	Automated safety check: Pass	MIT	5 days ago
Playwright E2E Testsonyx-dot-app/onyx	32k	1 repos	~2.8k	Automated safety check: Notes	Custom licence	today
E2E VerificationChorus-AIDLC/Chorus	1.2k	—	~1.5k	Automated safety check: Notes	AGPL-3.0	yesterday
Playwright Testingchongdashu/vibejam-starter-pack	149	—	~2.2k	Automated safety check: Pass	None	5 mo ago
Frontend Playwright E2Eansible/ansible-ui	113	—	~2.5k	Automated safety check: Notes	Apache-2.0	today
Playwright POM Discoverycomet-ml/opik	22k	—	~4.4k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Playwright E2E Tests
onyx-dot-app/onyx
Write and maintain Playwright end-to-end tests for the Onyx application.
32k GitHub starsUsed in 1 repo~2.8k tokens
Testing & QAAuto-check: notes
E2E Verification
Chorus-AIDLC/Chorus
A skill your agent uses when manually verifying a Chorus frontend change in a real browser — finding local login credentials, driving the running dev server with the Playwright MCP, logging in…
1.2k GitHub stars~1.5k tokensUpdated yesterday
Testing & QAAuto-check: notes
Playwright Testing
chongdashu/vibejam-starter-pack
Plan, implement, and debug frontend tests: unit/integration/E2E/visual/a11y.
149 GitHub stars~2.2k tokensUpdated 5 mo ago
Testing & QAAuto-check passed
Frontend Playwright E2E
ansible/ansible-ui
Write, run, and debug Playwright E2E / integration / live tests.
113 GitHub stars~2.5k tokensUpdated today
Testing & QAAuto-check: notes
Playwright POM Discovery
comet-ml/opik
Procedure for choosing stable selectors when building Page Object Models for the Opik E2E suite by exploring the live UI with the Playwright MCP.
22k GitHub stars~4.4k tokensUpdated today
Testing & QAAuto-check passed
Agentic Browser Testing
petrkindlmann/qa-skills
Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script.
170 GitHub stars~4.5k tokensUpdated 4 mo ago
Testing & QAAuto-check passed

Questions about Spot Check

What does Spot Check do?

Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test. Spot Check is an agent skill from ZenUml/web-sequence. Ad hoc, AI-driven verification of a specific behavior on ZenUML web-sequence — not a new checked-in E2E test.

When should I use Spot Check?

Spot Check fits situations like: run a spot check on X; spot check this fix; spot check on staging; spot check staging.zenuml.com.

How do I install Spot Check in Claude Code?

Run `npx skills add ZenUml/web-sequence --skill spot-check -a claude-code`. Or copy the skill folder (.claude/skills/spot-check in ZenUml/web-sequence) into .claude/skills/spot-check in your project. Claude Code loads it when a task matches its description.

How do I install Spot Check in Codex?

Run `npx skills add ZenUml/web-sequence --skill spot-check -a codex`. Or copy the skill folder (.claude/skills/spot-check in ZenUml/web-sequence) into .agents/skills/spot-check in your project. Codex loads it when a task matches its description.

Can I use Spot Check 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 ZenUml/web-sequence --skill spot-check -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spot-check, .gemini/skills/spot-check, .github/skills/spot-check and .opencode/skills/spot-check in your project.

What does Spot Check need to run?

Going by SKILL.md and its folder, Spot Check needs the command-line tools its instructions call (pnpm and yarn).

Does Spot Check access the network?

SKILL.md names 1 domain. In commands or code: staging.zenuml.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Spot Check 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 Spot Check use?

Spot Check is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Spot Check use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Spot Check?

Skills that share tags, products or a category with Spot Check: Playwright E2E Tests (onyx-dot-app/onyx, 32k stars), E2E Verification (Chorus-AIDLC/Chorus, 1.2k stars), Playwright Testing (chongdashu/vibejam-starter-pack, 149 stars) and Frontend Playwright E2E (ansible/ansible-ui, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spot Check?

ZenUml (a GitHub organization) maintains it in ZenUml/web-sequence, which has 150 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 5, 2026.

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

Install Spot Check

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Spot Check

Key principles

Write the plan first

Choosing the environment

Verification methods

Pre-flight (UI checks)

Workflow

Playwright recipes (existing specs)

Browser tooling

Related skills

Rules

Files

Compare with similar skills

Similar skills

More from ZenUml/web-sequence

Related

Questions about Spot Check