What is glmv-prd-to-app?

A tool for turning a product requirements document (PRD) and prototype images into a complete web application. It covers the design, database, server, user interface, testing against prototypes, and deployment scripts.

Use it to build a full-stack app from PRD files, prototype screenshots, and resource files, with seed data and a reproducible startup script.

It brings the main stages of app development together when the starting point is a written product plan and visual examples.

glmv-prd-to-app — Skill for Claude Code and Codex by zai-org

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add zai-org/GLM-skills --skill glmv-prd-to-app

Clone the repo

git clone --depth 1 https://github.com/zai-org/GLM-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zai-org/glm-skills/glmv-prd-to-app/github.svg)](https://agentmods.dev/skills/zai-org/glm-skills/glmv-prd-to-app)

Your own site

<a href="https://agentmods.dev/skills/zai-org/glm-skills/glmv-prd-to-app"><img src="https://agentmods.dev/badge/skills/zai-org/glm-skills/glmv-prd-to-app/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zai-org/glm-skills/glmv-prd-to-app"><img src="https://agentmods.dev/badge/skills/zai-org/glm-skills/glmv-prd-to-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 188 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,541 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00188	$0.03541
Opus 5.5	$0.00075	$0.01416
Sonnet 5.5	$0.00038	$0.00708
Haiku 4.5	$0.00019	$0.00354

Measured 2mo ago against content hash c3bfff80ea05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

glmv-prd-to-app scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check_api.py, scripts/render_page.py, scripts/wait_and_check.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

4. Test with curl or equivalent to verify response format

skills/glmv-prd-to-app/SKILL.md · 510 lines

How it starts

The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLM-V PRD-to-App: Full-Stack Application Builder

Language: Respond in the same language the user uses. Code comments should match.

Build a complete, deployed web application from PRD + prototypes + resources. The result must be fully reproducible via a single bash /workspace/start.sh.

Phase 0: Material Discovery & Analysis

Before anything else, understand what you're working with.

0a. Locate all inputs

/workspace/prd.md              ← Product requirement document
/workspace/prototypes/*.jpg    ← UI prototype images (the visual truth)
/workspace/resources/**/*      ← Images, videos, icons, and other assets

If the materials are in a different location, adapt accordingly. Read the PRD fully.

0b. Deep prototype analysis

For every prototype image:

Read each image using the Read tool — you are multimodal, examine them directly.
For each image, document:
- Page identity: which page/view this represents
- Layout structure: header, sidebar, main content, footer, modals
- Component inventory: every button, form, card, table, list, nav element
- Content inventory: all visible text, numbers, labels, placeholder content
- Color extraction: primary, secondary, accent, background, text colors (hex values)
- Typography: font sizes, weights, hierarchy observed
- Interactive states: hover effects, active tabs, selected items, toggles
- Data patterns: what data populates lists/tables/cards — this drives seed data
Build a page map showing navigation flow between prototype pages.

0c. Resource inventory

List all files in /workspace/resources/ and map each to where it appears in the prototypes. Every resource file must be used in the final application where relevant.

Phase 1: System Design Document

Produce a comprehensive design document at /workspace/docs/design.md.

1a. Data Model

For each entity, specify:

Table/collection name
All fields with types, constraints, defaults
Relationships (foreign keys, many-to-many)
Indexes needed for query patterns
Content mapping: which prototype elements map to which fields

Read the full file on GitHub · 510 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 510 lines · 188 tokens per session scan A c3bfff80ea05

Subscribe to this mod's changes

glmv-prd-to-app is a skill published in the GitHub repository zai-org/GLM-skills (473 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 188 tokens to every session and 3,541 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Frontend GLM Multimodal Planning ocr skills vision

vision-skills

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/htmlshot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long…

Anionex/agent-vision-toolkit · 132 tokens

watch

Watch any video (URL, stream, or local path) via Watch Skill. Downloads, extracts scene-aware deduped frames, OCRs them, transcribes (captions first, then local Whisper — offline by default), indexes everything, and hands the result to the agent. Follow-up questions are answered from the persistent index without…

oxbshw/watch-skill · 71 tokens

the-loop

The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does the animation glitch". Use this to record the running thing, critique the recording against plain-language pass criteria…

oxbshw/watch-skill · 81 tokens

asking-with-evidence

The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y". Use this to answer from the persistent index with timestamped evidence and a confidence score instead of re-watching or guessing.

oxbshw/watch-skill · 74 tokens

configuring-vision

The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models. Use this to configure provider-neutral visual understanding without tying Watch Skill to one agent or model vendor.