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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with real validation gates and executable code for every write operation. Its weaknesses are modest: duplicated wrapper/re-stack code between the conventions section and Step 7, and a large inline visual-conventions block that overlaps the foundation reference files.

Suggestions

Keep the wrapper-creation and re-stack code in one place only (the conventions section or Step 7) and cross-reference the other, removing the duplicated ~30 lines.

Trim the inline color/typography tables to the hue-pairing rule plus a pointer to foundation/palette.md and foundation/layout.md, keeping only the 'what NOT to use' rows that prevent actual mistakes.

Fix the typo in the yellow table row ('#FFEC BD' has a stray space) so the hex value is copy-paste usable.

Dimension	Reasoning	Score
Conciseness	The body is dense with project-specific knowledge Claude cannot know (ARCH_PALE hex constants, the connector text.fills=[] invisibility trap, hug/resize rules), but there is duplication: the wrapper-creation and re-stack code appears in both the visual-conventions section and Step 7, and the color table duplicates foundation/palette.md. Mostly efficient with minor trim opportunities — anchor 4, not 5.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready JS for the first-run probe, outer-wrapper creation, diagram-column positioning, and the re-stack pass; exact font sizes, gap values, and padding constants; exact MCP tool calls with parameters (create_new_file payload, useArchitectureLayoutCode); expected probe return values; and a concrete failure-handling recipe for failed diagram generation. Specific examples cover the common cases.	5 / 5
Workflow Clarity	Nine clearly typed steps (Research/Confirm/Write) each with inputs, ask-if-missing, refs to load, actions, and an explicit checkpoint; every board write is gated by screenshot + AskUserQuestion; self-check lists with loop-back instructions; an atomic error rule ('no changes made. Read the error, fix, retry'); and a final inspection checklist with targeted-fix-not-regenerate guidance. Exemplary validation and feedback loops.	5 / 5
Progressive Disclosure	All 14 bundle files exist and are referenced with a per-block 'when to load' table plus per-step 'Tools / refs loaded' lists, one level deep — good structure. Minor gap: the ~150-line inline visual-conventions block (colors, typography, spacing) substantially duplicates foundation/palette.md and foundation/layout.md content; justified as a single-place summary but it keeps the file from being a lean overview, so anchor 4 rather than 5.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concrete third-person capability statement, an explicit 'Use when…' clause with natural trigger phrases, and a distinctive niche. The only weakness is that trigger-term coverage omits a few natural synonyms a user might say.

Suggestions

Add one or two natural synonyms to the 'Use when' clause, e.g. 'roadmap' or 'planning board', to broaden trigger coverage.

Mention the PRD-to-board conversion phrasing (e.g. 'turn this PRD into a board') since users often phrase the request that way.

Dimension	Reasoning	Score
Specificity	"Generate a FigJam project plan board from a PRD plus codebase context" plus the enumerated pipeline ("research → propose sections → … → skeleton → fill → diagrams → wrap") and the full list of nine content blocks names multiple concrete actions with comprehensive coverage. It is written in third person and contains no vague filler.	5 / 5
Completeness	Explicitly answers "what" (first two sentences describing the board generation and interactive flow) and "when" ("Use when the user asks for 'project plan in FigJam', 'interactive project plan', '/generate-project-plan', or provides a PRD…") with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — "project plan in FigJam", "interactive project plan", "/generate-project-plan", "provides a PRD" — but a few natural synonyms and variations are missing (e.g. "roadmap", "planning board", "PRD to board"). Coverage is good but not comprehensive, fitting between anchors 4 and 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (FigJam project-plan board generation from a PRD with per-section user confirmation) with distinctive triggers unlikely to fire for other skills; overlap risk even within the Figma plugin family is minimal given the very specific trigger phrases.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 17 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 18 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: figma/mcp-server-guide
Path: workflow-skills/generate-project-plan/SKILL.md
Commit: 38308b7

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.