Agent skill

Voiceover-First Development

by Devin-AXIS in Devin-AXIS/iPolloWork

Starts a feature as a demo narration instead of a PRD: you approve the script before any code, then the agent builds in a fresh worktree and opens a PR with proof.

Custom licenceAuto-check passedAgent Workflows

Install Voiceover-First Development

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

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

GitHub CLI
$ gh skill install Devin-AXIS/iPolloWork voiceover --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/voiceover .claude/skills/voiceover && 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
voiceover
GitHub stars
6.8k
Token cost
~879 tokens
SKILL.md length
399 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
Custom licence

At a glance

Starts a feature as a demo narration instead of a PRD: you approve the script before any code, then the agent builds in a fresh worktree and opens a PR with proof.

  • Works in 4 steps: Align on words (no code) → Start clean (fresh worktree) → Build until the demo holds → …
  • A feature request arrives and you want to agree on the demo first
  • SKILL.md covers Phase 1 — Align on words (no…, Phase 2 — Start clean (fresh…, Phase 3 — Build until the demo… and Phase 4 — Ship (PR with the…, plus 2 more sections
  • Calls git, pnpm and gh

What it does

In phase one the agent drafts the voice-over: one numbered paragraph per frame, usually four to eight frames, in spoken present tense with the end user as protagonist and no implementation talk. You revise the words until you would actually record them, and no code is written until you approve. If a frame is hard to narrate, the feature or the frame is reshaped.

On approval it creates a git worktree on a new feat branch from origin/dev, saves the script under evals/voiceovers with the flow ID as the filename, and scaffolds a flow file with pnpm fraimz scaffold, one proof stub per paragraph. The build phase delegates coding to an executor subagent and loops through the fraimz skill until every frame passes. Last, it pushes the branch, opens a PR with the GitHub CLI and posts the frame-by-frame proof as a PR comment.

When your agent uses it

  • A feature request arrives and you want to agree on the demo first
  • Replacing a written PRD with a narrated walkthrough
  • Shipping a feature with frame-by-frame proof attached to the PR

Example prompts

  • “Write the voice-over for a bulk-export feature before we touch any code.”
  • “/voiceover for dark-mode scheduling: draft the script and wait for my approval.”

Requirements

  • A Git repository with a dev branch
  • pnpm and the project's fraimz tooling
  • The GitHub CLI for opening the PR

Workflow steps

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

  1. Align on words (no code)
  2. Start clean (fresh worktree)
  3. Build until the demo holds
  4. Ship (PR with the proof on it)

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:

    • git
    • pnpm
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use git, pnpm and gh, 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

Voiceover-First Development loads about 879 tokens when it runs. Until then it costs about 100 tokens; SKILL.md has 399 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~100
When it runs · the whole SKILL.md, loaded when a task matches
~879

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 399 words (~879 tokens).

“The voice-over is the spec. Instead of a PRD, a feature starts as the demo narration the user would record if the feature had already shipped. This skill owns the whole journey: script → worktree → build → fraimz →…”

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

Read the full SKILL.md on GitHub

Files

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

Open the folder on GitHubat commit 71a74ad

Compare with similar skills

Voiceover-First Development 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.

Voiceover-First Development compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Voiceover-First Development this skillDevin-AXIS/iPolloWork6.8k—~879Automated safety check: PassCustom licence
Badstephenleo/bmad-autonomous-development107—~7.7kAutomated safety check: PassMIT
PRP Workstream OrchestratorWirasm/prp2.3k—~3.5kAutomated safety check: PassMIT
MoAI SPEC Workflowmodu-ai/moai-adk1.2k—~5.1kAutomated safety check: PassApache-2.0
Devcontainer Devstacklok/toolhive-studio170—~3.8kAutomated safety check: NotesApache-2.0
Work With PR Lifecyclecode-yeongyu/oh-my-openagent70k—~4.6kAutomated safety check: PassCustom licence

Similar skills

  • Bad

    stephenleo/bmad-autonomous-development

    BMad Autonomous Development — orchestrates parallel story implementation pipelines.

    107 GitHub stars~7.7k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed
  • Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.

    2.3k GitHub stars~3.5k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed
  • MoAI SPEC Workflow

    modu-ai/moai-adk

    Manages SPEC documents for MoAI-ADK development, with GEARS or EARS requirement notation, acceptance criteria and a link into the Plan-Run-Sync workflow.

    1.2k GitHub stars~5.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Devcontainer Dev

    stacklok/toolhive-studio

    Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD).

    170 GitHub stars~3.8k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Work With PR Lifecycle

    code-yeongyu/oh-my-openagent

    Takes a task through to a merged pull request in an isolated git worktree, splitting it into small independent PRs and looping on CI and review gates until they pass.

    70k GitHub stars~4.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Branch Standup Facilitator

    thedotmack/claude-mem

    Facilitates a read-only standup between git worktrees, branches or PRs, where each acts as an agent in a shared markdown chat to agree one consolidation plan.

    98k GitHub stars~1.7k tokensUpdated yesterday
    DevelopmentAuto-check: notes

More from Devin-AXIS/iPolloWork

All 30 skills in this repo
  • 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.

    6.8k GitHub starsUsed in 2 repos~3.2k tokens
    Auto-check passed
  • 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.

    6.8k GitHub stars~2.7k tokensUpdated today
    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.

    6.8k 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.

    6.8k 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.

    6.8k 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.

    6.8k GitHub stars~582 tokensUpdated today
    Auto-check passed

Works with

Questions about Voiceover-First Development

What does Voiceover-First Development do?

Starts a feature as a demo narration instead of a PRD: you approve the script before any code, then the agent builds in a fresh worktree and opens a PR with proof. In phase one the agent drafts the voice-over: one numbered paragraph per frame, usually four to eight frames, in spoken present tense with the end user as protagonist and no implementation talk. You revise the words until you would actually record them, and no code is written until you approve.

When should I use Voiceover-First Development?

Voiceover-First Development fits situations like: A feature request arrives and you want to agree on the demo first; replacing a written PRD with a narrated walkthrough; shipping a feature with frame-by-frame proof attached to the PR.

How do I install Voiceover-First Development in Claude Code?

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

How do I install Voiceover-First Development in Codex?

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

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

What does Voiceover-First Development need to run?

Going by SKILL.md and its folder, Voiceover-First Development needs the command-line tools its instructions call (git, pnpm and gh). Our summary lists: A Git repository with a dev branch; pnpm and the project's fraimz tooling; The GitHub CLI for opening the PR.

Does Voiceover-First Development access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Voiceover-First Development 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 Voiceover-First Development use?

Voiceover-First Development 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 Voiceover-First Development use?

About 879 tokens (SKILL.md is roughly 3.5k 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 Voiceover-First Development?

Skills that share tags, products or a category with Voiceover-First Development: Bad (stephenleo/bmad-autonomous-development, 107 stars), PRP Workstream Orchestrator (Wirasm/prp, 2.3k stars), MoAI SPEC Workflow (modu-ai/moai-adk, 1.2k stars) and Devcontainer Dev (stacklok/toolhive-studio, 170 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Voiceover-First Development?

Devin-AXIS (a GitHub user) maintains it in Devin-AXIS/iPolloWork, which has 6,758 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 8, 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.