generate-project-plan
Generate a FigJam project plan board from a PRD plus codebase context. Interactive flow: research → propose sections → per-section deep research → per-section content + block-shape proposal → create FigJam → skeleton → fill → diagrams → wrap. Each content block (section, nested section, intro callout, table, multi-column text, sticky column, diagram section, metadata strip) has its own subskill reference file. Use when the user asks for 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', or provides a PRD and wants per-section confirmation on content + rendering.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers what the skill does (multi-step interactive FigJam project plan generation from PRDs), how it works (detailed workflow steps and block types), and when to use it (explicit trigger phrases and scenarios). It is highly specific, distinctive, and complete, with strong natural trigger terms. The only minor concern is that the description is quite dense, but the information density is justified by the complexity of the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifacts: 'research → propose sections → per-section deep research → per-section content + block-shape proposal → create FigJam → skeleton → fill → diagrams → wrap'. Also enumerates specific block types like 'section, nested section, intro callout, table, multi-column text, sticky column, diagram section, metadata strip'. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate a FigJam project plan board from a PRD with an interactive multi-step flow) and 'when' (explicit 'Use when...' clause with specific trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', 'PRD', 'per-section confirmation on content + rendering'. These cover both natural language and command-style triggers. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of FigJam, PRD, project plan, interactive per-section confirmation flow, and specific block types creates a very clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at actionability and workflow clarity — the 9-step interactive flow is meticulously structured with concrete code, explicit checkpoints, and robust error handling. However, it severely undermines its own progressive disclosure architecture by inlining ~300 lines of visual conventions, palette constants, and layout code that are already delegated to foundation reference files. This duplication bloats the token budget significantly, making it the skill's primary weakness.
Suggestions
Move the entire 'Visual UI conventions — STRICT' section (colors, typography, spacing, tables, diagrams, 'What NOT to use') into the referenced foundation files (palette.md, layout.md, plugin-api-traps.md) and replace with a 3-line summary pointing to those files — this would cut ~60% of the content.
Remove the inline JavaScript code blocks for wrapper creation and diagram column positioning, placing them in layout.md or a dedicated wrapper subskill file, and reference them from the step that needs them.
Consolidate the repeated 're-load figma-use-figjam before every use_figma call' instruction into a single operational rule rather than restating it in every step's 'Tools / refs loaded' section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines with extensive inline repetition of visual constants (colors, typography, spacing) that should live in the referenced foundation files. The color tables, typography tables, and 'What NOT to use' table duplicate content from palette.md and other references. The outer wrapper code examples and diagram reparenting details are repeated rather than delegated to their block subskill files. | 1 / 3 |
Actionability | The skill provides fully executable JavaScript code snippets for wrapper creation, section positioning, and probe calls. Every step has concrete inputs, specific tool calls, exact MCP tool names, and precise checkpoint actions. The block reference table clearly maps content types to specific files with loading instructions. | 3 / 3 |
Workflow Clarity | The 9-step workflow is clearly sequenced with explicit step types (Research/Confirm/Write), each step has defined inputs, tools, actions, and checkpoints. Validation is thorough — screenshots at every Write step, AskUserQuestion gates before proceeding, failure handling for diagram generation, and atomic error recovery. The feedback loops (Edit/Fix/Cancel at each checkpoint) are well-defined. | 3 / 3 |
Progressive Disclosure | The skill correctly references ~15 external files (foundation refs, block subskills, section catalog) with clear navigation tables and links. However, it massively violates progressive disclosure by inlining hundreds of lines of visual convention details (color tables, typography specs, spacing rules, wrapper code, diagram conventions, 'What NOT to use' table) that belong in the referenced foundation files. The SKILL.md should be an orchestration overview pointing to these details, not a monolithic dump. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- figma/mcp-server-guide
- Commit
a742f0a
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.