New: 97,000+ 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

Fraimz End-to-End Proof

by Devin-AXIS in Devin-AXIS/iPolloWork

Proves a change works by driving the running app and writing fraimz.html, a proof file with one frame per step: claim, action, assertion, voiceover and screenshot.

Custom licenceAuto-check passedTesting & QA

Install Fraimz End-to-End Proof

skills CLI
$ npx skills add Devin-AXIS/iPolloWork --skill fraimz -a claude-code

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

GitHub CLI
$ gh skill install Devin-AXIS/iPolloWork fraimz --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/Devin-AXIS/iPolloWork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/fraimz .claude/skills/fraimz && 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
fraimz
GitHub stars
6.7k
Token cost
~1.9k tokens
SKILL.md length
939 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
Custom licence

At a glance

Proves a change works by driving the running app and writing fraimz.html, a proof file with one frame per step: claim, action, assertion, voiceover and screenshot.

  • Works in 6 steps: Frame the experience as a one-line claim… → Get the script. Approved voiceover at… → Code the flow. The end user is the… → …
  • Finishing a task that ends with a request to create a fraimz for the change
  • SKILL.md covers Every fraimz is a demo, Voiceover first, When this applies and The loop, plus 4 more sections
  • Calls pnpm and bash

What it does

A fraimz is a single HTML proof file, saved in a per-run folder under evals/results, with one frame per step. Each frame binds a claim, the action the end user took, an assertion that witnesses the side effect, a spoken-style voiceover and a validated screenshot, so a reviewer can see and hear that an experience works at a glance. The skill owns the prove-it loop: frame the claim, drive the real app through CDP, validate and repair, then output the file. When an orchestrator runs the work, it drives this loop and hands code repairs to the executor.

Each flow declares a kind in its file under evals/flows. A user-facing flow walks a real journey through the interface and is the default for features, fixes and UX changes. An internal flow covers changes with no visible surface, such as performance work, storage swaps or refactors, and terminal demos can set requiresApp to false to skip CDP and carry command output instead of screenshots.

Narration comes before the flow. An approved script in evals/voiceovers is turned into a flow by pnpm fraimz scaffold, the runner fails any flow whose narration drifts from that script, and frames without a voiceover are flagged in the artifact. The skill applies whenever a change could alter behavior visible from outside the process (files, a runtime database, endpoints, sessions, configuration or network traffic), including changes that should be inert.

When your agent uses it

  • Finishing a task that ends with a request to create a fraimz for the change
  • Proving a UI feature or fix works end to end in the running app
  • Showing a reviewer that a refactor or storage swap left behavior as it was
  • Attaching step-by-step screenshots and voiceover evidence to a pull request

Example prompts

  • “Create a fraimz for the new project-rename flow and show me fraimz.html.”
  • “Prove the settings sync fix works end to end before I open the PR.”
  • “Make a fraimz for the storage swap as an internal flow, with command output as evidence.”
  • “Scaffold the flow from the approved voiceover script for the onboarding walkthrough.”

Requirements

  • An app the agent can drive over CDP, unless the flow sets requiresApp to false
  • The repository's evals folder with flow files and voiceover scripts
  • pnpm for the fraimz scaffold command

Workflow steps

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

  1. Frame the experience as a one-line claim ("user can do X and sees Y")
  2. Get the script. Approved voiceover at evals/voiceovers/.md
  3. Code the flow. The end user is the protagonist (driven via CDP);
  4. Drive it for real. Launch the app (see below), then
  5. Validate, repair, repeat. If a frame does not support its claim (wrong
  6. Verdict, on the PR. The run writes fraimz.html + report.md /

What it can do on your machine

Read from SKILL.md and the folder at commit 71a74ad. 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
    • bash

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, which can reach the network depending on how they are called.

    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

Fraimz End-to-End Proof loads about 1.9k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 939 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 939 words (~1,900 tokens).

“fraimz is the canonical proof artifact: a single fraimz.html (evals/results//fraimz.html) with one frame per step. Each frame binds a claim, the action the end user took, the assertion that witnesses the side effect, a voiceover that narrates the step, and…”

— opening of SKILL.md by Devin-AXIS, Custom licence
name
fraimz

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .opencode/skills/fraimz of Devin-AXIS/iPolloWork.

Open the folder on GitHubat commit 71a74ad

Compare with similar skills

Fraimz End-to-End Proof 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.

Fraimz End-to-End Proof compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fraimz End-to-End Proof this skillDevin-AXIS/iPolloWork6.7k—~1.9kAutomated safety check: PassCustom licence
Verify PRduckduckgo/autoconsent130—~609Automated safety check: PassMPL-2.0
Test PRmrzmyr/pixy-mood-tracker-app153—~391Automated safety check: PassMIT
Testdriver E2E Testingsickn33/agentic-awesome-skills47k1 repos~1.1kAutomated safety check: NotesApache-2.0
Vhs E2E Gifdimetron/pi-go207—~1.7kAutomated safety check: PassMIT
Nitro Sound Workflowshyochan/react-native-nitro-sound961—~1.2kAutomated safety check: PassMIT

Similar skills

  • Verify PR

    duckduckgo/autoconsent

    Verifies an autoconsent pull request by running local CI checks, reviewing rule quality, and inspecting Jenkins E2E results.

    130 GitHub stars~609 tokensUpdated today
    Testing & QAAuto-check passed

  • Test PR

    mrzmyr/pixy-mood-tracker-app

    Run changed e2e flows for a pull request and note the result.

    153 GitHub stars~391 tokensUpdated today
    Testing & QAAuto-check passed

  • Testdriver E2E Testing

    sickn33/agentic-awesome-skills

    Build E2E tests with TestDriver.ai, the AI code reviewer that runs every pull request in a real desktop sandbox, finds bugs, and builds regression tests

    47k GitHub starsUsed in 1 repo~1.1k tokens
    Testing & QAAuto-check: notes

  • Vhs E2E Gif

    dimetron/pi-go

    Record a test run, a TUI session, or any terminal command as a GIF with VHS and attach it to a GitHub PR as a release-hosted asset, never a repo commit.

    207 GitHub stars~1.7k tokensUpdated 6 days ago
    Testing & QAAuto-check passed

  • Nitro Sound Workflows

    hyochan/react-native-nitro-sound

    A skill your agent uses for react-native-nitro-sound repository work that should follow the project workflows for PR review, code audit, knowledge compilation, full verification, iOS or Android…

    961 GitHub stars~1.2k tokensUpdated 7 days ago
    MobileAuto-check passed

  • Cherry Studio PR Tester

    CherryHQ/cherry-studio

    Tests a Cherry Studio pull request by checking it out, inspecting changes, driving the UI in an owned Electron instance and reporting, then restoring the branch.

    52k GitHub stars~1.2k tokensUpdated today
    Testing & QAAuto-check passed

More from Devin-AXIS/iPolloWork

All 30 skills in this repo

  • Maintainable Code for iPolloWork

    Devin-AXIS/iPolloWork

    A code-change gate for the iPolloWork repository: search and reuse first, keep one source of truth, justify every new file or dependency, and audit the change.

    6.7k GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Daytona Windows Certificate Test

    Devin-AXIS/iPolloWork

    Reproduces iPolloWork enterprise TLS behavior in a Daytona Windows sandbox by installing a fake corporate CA and proving the app and its runtimes use the OS trust store.

    6.7k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed

  • Build iPolloWork Templates

    Devin-AXIS/iPolloWork

    Builds a reusable iPolloWork template for Design, Slides or PPT, or HyperFrames Video through conversation, keeping a manifest, reusable variables and a validated package current.

    6.7k GitHub stars~925 tokensUpdated today
    Auto-check passed

  • OpenCode Plugin Creator

    Devin-AXIS/iPolloWork

    Scaffolds an OpenCode plugin for iPolloWork with the right async factory shape, zod-based tool definitions and hook registration, and explains where to place and register it.

    6.7k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

  • Agent-First Screenshots

    Devin-AXIS/iPolloWork

    Has an agent drive the real app through CDP and capture clean, defect-free product screenshots, gated by DOM, pixel and vision checks in a loop.

    6.7k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Daytona Chrome CDP

    Devin-AXIS/iPolloWork

    Launches a standalone Chrome or Chromium in a Daytona sandbox and drives it over CDP for web sign-in, OAuth and other flows that should bypass the Electron app.

    6.7k GitHub stars~582 tokensUpdated today
    Auto-check passed

Categories

Questions about Fraimz End-to-End Proof

What does Fraimz End-to-End Proof do?

Proves a change works by driving the running app and writing fraimz.html, a proof file with one frame per step: claim, action, assertion, voiceover and screenshot. A fraimz is a single HTML proof file, saved in a per-run folder under evals/results, with one frame per step. Each frame binds a claim, the action the end user took, an assertion that witnesses the side effect, a spoken-style voiceover and a validated screenshot, so a reviewer can see and hear that an experience works at a glance.

When should I use Fraimz End-to-End Proof?

Fraimz End-to-End Proof fits situations like: finishing a task that ends with a request to create a fraimz for the change; proving a UI feature or fix works end to end in the running app; showing a reviewer that a refactor or storage swap left behavior as it was; attaching step-by-step screenshots and voiceover evidence to a pull request.

How do I install Fraimz End-to-End Proof in Claude Code?

Run `npx skills add Devin-AXIS/iPolloWork --skill fraimz -a claude-code`. Or copy the skill folder (.opencode/skills/fraimz in Devin-AXIS/iPolloWork) into .claude/skills/fraimz in your project. Claude Code loads it when a task matches its description.

How do I install Fraimz End-to-End Proof in Codex?

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

Can I use Fraimz End-to-End Proof 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 Devin-AXIS/iPolloWork --skill fraimz -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fraimz, .gemini/skills/fraimz, .github/skills/fraimz and .opencode/skills/fraimz in your project.

What does Fraimz End-to-End Proof need to run?

Going by SKILL.md and its folder, Fraimz End-to-End Proof needs the command-line tools its instructions call (pnpm and bash). Our summary lists: An app the agent can drive over CDP, unless the flow sets requiresApp to false; The repository's evals folder with flow files and voiceover scripts; pnpm for the fraimz scaffold command.

Does Fraimz End-to-End Proof 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 Fraimz End-to-End Proof 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 Fraimz End-to-End Proof use?

Fraimz End-to-End Proof has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Fraimz End-to-End Proof use?

About 1.9k tokens (SKILL.md is roughly 7.6k 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 Fraimz End-to-End Proof?

Skills that share tags, products or a category with Fraimz End-to-End Proof: Verify PR (duckduckgo/autoconsent, 130 stars), Test PR (mrzmyr/pixy-mood-tracker-app, 153 stars), Testdriver E2E Testing (sickn33/agentic-awesome-skills, 47k stars) and Vhs E2E Gif (dimetron/pi-go, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fraimz End-to-End Proof?

Devin-AXIS (a GitHub user) maintains it in Devin-AXIS/iPolloWork, which has 6,717 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 6, 2026.

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