agent-rules-skill-auth…
Maintain WebDev Agent Kit source rules, skills, metadata, and validators. Excludes upgrading installed copies.
Inspect Figma links through MCP or browser computer use, or analyze screenshots and selected-layer properties. Produce frontend specs and clarify unresolved product behavior before implementation.
Claude Code
$ npx -y skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec --agent claude-code
Codex
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a codex -y
Cursor
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a cursor -y
Gemini CLI
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a gemini-cli -y
GitHub Copilot
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a github-copilot -y
OpenCode
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a opencode -y
Windsurf
$ npx skills add ytvee-dev/webdev-agent-kit --skill design-screenshot-spec -a windsurf -y
name: design-screenshot-spec
description: 'Inspect Figma links through MCP or browser computer use, or analyze screenshots and selected-layer properties. Produce frontend specs and clarify unresolved product behavior before implementation.'
id: 'agents.skills.design-screenshot-spec.skill'
title: 'Design Screenshot Spec'
doc_type: 'skill'
layer: 'skill'
status: 'active'
publishable: true
local_only: false
skill: 'design-screenshot-spec'
tags:
- 'agents/skill-package'
- 'frontend/design'
- 'frontend/spec'
parent:
- '[[AGENTS|Canonical Agent Policy]]'
related:
- '[[skills/design-screenshot-spec/references/effect-evidence]]'
- '[[common/webdev-role-selection]]'
- '[[skills/design-screenshot-spec/references/design-source-inspection|Design Source Inspection]]'
- '[[skills/design-screenshot-spec/references/product-behavior-review|Product Behavior Review]]'
- '[[skills/design-screenshot-spec/references/spec-extraction-checklist|Spec Extraction Checklist]]'
- '[[skills/frontend-design-director/SKILL|Frontend Design Director]]'
- '[[skills/frontend-layout-implementer/SKILL|Frontend Layout Implementer]]'
- '[[skills/frontend-visual-qa/SKILL|Frontend Visual QA]]'
depends_on:
- '[[AGENTS|Canonical Agent Policy]]'Inspect live Figma designs or supplied screenshots, property panels, assets, and notes to produce a traceable `Design Implementation Spec`. Review the observed design as a product flow and resolve unspecified design and behavior decisions with the user before handing affected work to an implementer. The existing skill name remains stable for bundle compatibility.
panels.
to inspect it or implement its design.
spec.
generate a design system, or write Code Connect mappings.
implement it. Use `frontend-layout-implementer`.
1. Read `AGENTS.md`. 2. Confirm the classified task is `design-spec` or design intake for later frontend implementation. 3. Read `common/approved-patterns.md`. 4. Read `common/anti-patterns.md`. 5. Read `project/design-reference-profile.md` when present. 6. Read `references/spec-extraction-checklist.md`. 7. For live links, read `references/design-source-inspection.md`. 8. For effects or a visual-effect mismatch, read `references/effect-evidence.md`. 9. After extraction, read `references/product-behavior-review.md` before formulating product questions or an implementation handoff.
tool registry and `tool-capabilities-manifest.json` for the active source.
permitted provider selected by the current explicit role/tool instruction; otherwise use callable Figma MCP first with browser/computer-use fallback. Apply `common/webdev-role-selection.md` for an explicitly selected role.
canvas and property panel. Search results or an HTTP fetch are not inspection.
a Figma connection. Never invent a tool, session, node, or successful read.
access settings, edit the source canvas, or write mappings during intake.
1. Inventory links, screenshots, inspect panels, exports, notes, target screens, and existing user decisions. Identify the requested frame and state scope. 2. Inspect live links using `references/design-source-inspection.md`; use supplied screenshots directly when no link exists. If neither source can be inspected, request the smallest missing reference and report the limitation. 3. Group evidence by screen, component, variant, state, and viewport. Record source ID, node or selected-layer identity, frame size, image crop/zoom when known, access path, and inspection coverage. Match property panels to their selected elements before assigning values. Inspect every in-scope component; reuse proven identical instances while recording overrides and state changes. 4. Treat each screenshot or design-frame size as a reference coordinate system, not as a production container cap. Record whether containment is explicitly visible and capture desktop edge anchors plus expected behavior beyond the reference viewport. 5. Extract visible layout, hierarchy, typography, color, spacing, sizing, radius, shadow, assets, states, and responsive behavior. 6. For typography, prefer copied inspect values or selected-text properties for `font-family`, `font-size`, `font-weight`, `line-height`, color, alignment, max width, and wrapping. When properties are unavailable, estimate from the screenshot and mark each estimate as `screenshot-inferred`. 7. For spacing, separate outside margins, section rhythm, inter-component gaps, container padding, and internal control padding instead of merging them into one generic gap value. 8. Mark values `source-provided`, `screenshot-inferred`, or `unknown`, with the exact source/selection and units; keep user decisions separately traceable. 9. Prefer exact properties only for the same node, state, mode, and revision. Reinspect mismatches; ask the user which reference governs unresolved conflicts. 10. Apply `references/product-behavior-review.md`: map observed actions and stat
A cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.
Maintain WebDev Agent Kit source rules, skills, metadata, and validators. Excludes upgrading installed copies.
Project memory: remember this mistake, save for learning, запиши себе в базу, сохрани для обучения, запомни эту ошибку. Requested…
Create, resume, analyze, or converge standard and deep frontend execution plans with traceable slices, evidence, and stop/resume…
Plan architecture and ownership for standard or deep React/Next.js work across routing, state, data, styling, forms, builds,…
Diagnose and fix frontend defects from evidence, including unclear UI/runtime errors, broken routes, styling regressions, and…
Set subject-grounded visual direction for standard or deep UI work, redesign, polish, critique, anti-template review, or design…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.