New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Proofshot

by AmElmo in AmElmo/proofshot

Visual verification of UI features. An agent skill from AmElmo/proofshot.

MITAuto-check passed

Install Proofshot

skills CLI
$ npx skills add AmElmo/proofshot --skill proofshot -a claude-code

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

GitHub CLI
$ gh skill install AmElmo/proofshot proofshot --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/AmElmo/proofshot.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codex .claude/skills/proofshot && 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
proofshot
GitHub stars
866
Token cost
~747 tokens
SKILL.md length
304 words
Files
2
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Visual verification of UI features. An agent skill from AmElmo/proofshot.

  • Works in 4 steps: Start the session → Drive the browser and test → Stop and bundle the proof → …
  • SKILL.md covers When to use, The workflow (always follow… and Tips
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Proofshot is an agent skill from AmElmo/proofshot. Visual verification of UI features. Use after building or modifying any UI component, page, or visual feature. Starts a verification session with video recording and error capture, then you drive the browser to test, then stop to bundle proof artifacts for the human.

Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `AGENTS.md`).

It works with GitHub. The repository describes itself as: Give AI coding agents eyes. Records browser sessions, captures screenshots, collects errors, and bundles proof artifacts — so humans can verify what the agent built. The licence is MIT.

Example prompts

  • “/proofshot”

Workflow steps

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

  1. Start the session
  2. Drive the browser and test
  3. Stop and bundle the proof
  4. (optional): Post proof to the PR

What it can do on your machine

Read from SKILL.md and the folder at commit 963aa67. 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 (its code samples are bash).

    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

Proofshot loads about 747 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 304 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~747

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 AmElmo/proofshot at commit 963aa67, republished under its MIT licence (© AmElmo). 304 words, ~747 tokens.

Download SKILL.mdSave it as .claude/skills/proofshot/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
proofshot
description
Visual verification of UI features. Use after building or modifying any UI component, page, or visual feature. Starts a verification session with video recording and error capture, then you drive the browser to test, then stop to bundle proof artifacts for the human.

ProofShot — Visual Verification Workflow

ProofShot is an open-source, agent-agnostic CLI that lets you verify your own work in a real browser — video proof, screenshots, and error reports, no vendor lock-in.

When to use

Use ProofShot after:

  • Building a new UI feature or page
  • Modifying existing UI components
  • Fixing a visual bug
  • Any change that affects what the user sees

The workflow (always follow these 3 steps)

Step 1: Start the session
bash
proofshot start --run "your-dev-command" --port PORT --description "what you are about to verify"

This opens a browser and begins recording. If the port is already in use, proofshot will kill the existing process automatically.

Always use --run to let proofshot start and capture your dev server output (server logs appear in the proof report). Only omit --run if the server was explicitly started by the user or another process — without it, no server logs are captured.

If a previous session was not stopped cleanly, add --force to override it.

Step 2: Drive the browser and test

Use proofshot exec to navigate, interact, and verify:

bash
proofshot exec snapshot -i                                    # See interactive elements
proofshot exec open http://localhost:PORT/page                # Navigate to a page
proofshot exec click @e3                                      # Click a button
proofshot exec fill @e2 "test@example.com"                    # Fill a form field
proofshot exec screenshot step-NAME.png                       # Capture key moments

Take screenshots at important moments — these become the visual proof. Verify what you expect to see by reading the snapshot output.

Step 3: Stop and bundle the proof
bash
proofshot stop

This stops recording, collects console + server errors, and generates a SUMMARY.md with video, screenshots, and error report.

Step 4 (optional): Post proof to the PR
bash
proofshot pr              # Auto-detect PR from current branch
proofshot pr 42           # Target a specific PR number

This uploads screenshots and video to GitHub and posts a formatted comment on the PR. By default it uses the official GitHub contents API on a proofshot-artifacts branch. Use --upload-provider github-web-attachments if you specifically want GitHub attachment URLs.

Tips

  • Always include a meaningful --description so the human knows what was tested
  • Take screenshots before AND after key actions (e.g., before form submit, after redirect)
  • If you find errors during verification, fix them and re-run the workflow
  • Use proofshot pr after stopping to attach proof directly to the pull request

© AmElmo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/codex of AmElmo/proofshot.

  • SKILL.md
  • AGENTS.md

Open the folder on GitHubat commit 963aa67

Compare with similar skills

Proofshot 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.

Proofshot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Proofshot this skillAmElmo/proofshot866—~747Automated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • Diagnosing Superpowers Sessions

    obra/superpowers

    Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed

  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed

  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

Works with

Questions about Proofshot

What does Proofshot do?

Visual verification of UI features. An agent skill from AmElmo/proofshot. Proofshot is an agent skill from AmElmo/proofshot. Visual verification of UI features.

How do I install Proofshot in Claude Code?

Run `npx skills add AmElmo/proofshot --skill proofshot -a claude-code`. Or copy the skill folder (skills/codex in AmElmo/proofshot) into .claude/skills/proofshot in your project. Claude Code loads it when a task matches its description.

How do I install Proofshot in Codex?

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

Can I use Proofshot 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 AmElmo/proofshot --skill proofshot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/proofshot, .gemini/skills/proofshot, .github/skills/proofshot and .opencode/skills/proofshot in your project.

What does Proofshot need to run?

SKILL.md names no scripts, command-line tools or credentials: Proofshot is instructions for the agent only.

Does Proofshot 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 Proofshot 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 Proofshot use?

Proofshot 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 Proofshot use?

About 747 tokens (SKILL.md is roughly 3k 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 Proofshot?

Skills that share tags, products or a category with Proofshot: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars) and Diagnosing Superpowers Sessions (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Proofshot?

AmElmo (a GitHub user) maintains it in AmElmo/proofshot, which has 866 GitHub stars. The repository was last updated on April 14, 2026.

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