菜单
Fetches a Figma node screenshot via MCP and saves it to disk. Use when the user asks to save a Figma design reference, capture a design for specs, or store a screenshot for verification.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Manual asset processing skill for Figma layers. Accepts layer URLs and writes deterministic files to drafts/media using curl+sips, with optional get_screenshot fallback.
Phase 3 of athenai-implement pipeline — execute tasks from plan.md and produce working block code. Includes lint-aware CSS generation and mandatory design compliance check when design.md exists.
Phase 0 of athenai-implement pipeline — conditionally produce design.md from Figma. Includes decision logic, extraction-only rules, manual asset handoff, and Phase 1 context pre-loading optimization.
End-to-end implementation pipeline — design, plan, tasks, implement, test cases, test content. Demo mode: skips unit tests and research deep-dives. Records phase wall times via `.specify/scripts/phase-timer.py` (per-phase start/end, subagent logs + merge when parallel). Explicit invocation only — never load from context or topic. Optional flags: --no-parallel (run all phases sequentially in main agent, no subagents), --no-test-cases (skip Phase 4 test case generation).
Phase 1-2 of athenai-implement pipeline — produce plan.md with authored HTML structure, parsing logic, and tasks section. Includes draft test content generation with mandatory edge case coverage.
Phase 4 of athenai-implement pipeline — generate testcases.csv from spec.md. Includes guard for --no-test-cases flag and coverage requirements for user journeys, acceptance criteria, and edge cases.
| name | figma-screenshot |
| description | Fetches a Figma node screenshot via MCP and saves it to disk. Use when the user asks to save a Figma design reference, capture a design for specs, or store a screenshot for verification. |
Fetches a screenshot of a Figma node using the Figma MCP get_screenshot tool and saves it to the filesystem.
| Requirement | Purpose |
|---|---|
| Figma MCP | get_screenshot tool available |
Figma URL or fileKey + nodeId | Identifies the design node to capture |
| Input | Example | Source |
|---|---|---|
| Figma URL | https://figma.com/design/abc123/Component?node-id=1-2 | User, spec (e.g. design.md), or command args |
| fileKey | abc123 | Extracted from URL |
| nodeId | 1:2 or 1-2 | Extracted from URL (node-id=1-2 → 1:2 for MCP) |
| Output path | .specify/specs/001-my-component/design-screenshot.jpg | User, command args, or inferred from spec folder |
| imageFormat | jpg | Output image format: jpg (default), png, or source (preserve original — no conversion) |
design.md links), or ask the user.https://figma.com/design/:fileKey/:name?node-id=1-2 → fileKey=:fileKey, nodeId=1:2 (use colon format for MCP)..specify/specs/{feature}/design-screenshot.jpg when in a spec folder, else figma-screenshot.jpg. If imageFormat is png, use .png extension instead.get_screenshot (server: plugin-figma-figma) with fileKey and nodeId.sips, then remove the temp file:
echo "<base64>" | base64 -d > <output-path>.tmp
sips -s format <imageFormat> <output-path>.tmp --out <output-path>
rm <output-path>.tmp
imageFormat is source, skip the sips step: echo "<base64>" | base64 -d > <output-path> (no conversion).jpeg as the sips format value when imageFormat is jpg (sips uses jpeg, not jpg).imageFormat: .jpg for jpg, .png for png.imageFormat=jpg — output is JPEG unless the caller specifies otherwise.Output the saved file path and confirm success.