CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

This is a high-quality, highly actionable skill body with a rigorous step template and validation checkpoints. Its main weakness is mild token redundancy: some palette/typography detail is duplicated between the inlined conventions tables and the referenced foundation files, pulling conciseness and progressive-disclosure down from perfect.

Suggestions

Move the full colors/typography/section-properties tables into the existing foundation references and keep only the most load-bearing constants inline, reducing duplication between the body and foundation/palette.md + layout.md.

In the 'What NOT to use' table, link to the relevant foundation file for the rationale rather than restating it inline, tightening the overview further.

Consider collapsing the repeated 'Tools / refs loaded' re-load reminders into a single short rule near the prerequisites, since the per-step reload instruction is restated many times.

DimensionReasoningScore

Conciseness

The body is dense and mostly lean, but the large visual-conventions tables, full code snippets, and the 'What NOT to use' matrix repeat detail also captured in referenced foundation/block files, slightly over-explaining for an overview.

4 / 5

Actionability

Each step ships concrete, executable `use_figma`/`generate_diagram` code and exact constants (palette hex, padding, font sizes), making it copy-paste ready with failure handling spelled out.

5 / 5

Workflow Clarity

Nine explicitly numbered steps with a consistent Research/Confirm/Write template, self-checks, and AskUserQuestion+screenshot checkpoints at every gate, plus clear error-recovery loops (probe failure, diagram failure, re-stack pass).

5 / 5

Progressive Disclosure

Structure is good: SKILL.md overviews and points to real, verified one-level-deep references (foundation/*, blocks/*, section-catalog.md). However, substantial constant/detail tables are inlined in the body rather than fully delegated to those reference files, so navigation is slightly duplicated rather than purely one-level.

4 / 5

Total

18

/

20

Passed

Description

100%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.

The description is specific, complete, and rich in natural trigger phrases while clearly delimiting a distinct niche. It is somewhat dense for a description but every clause earns its place, and it answers both what and when explicitly.

DimensionReasoningScore

Specificity

The description enumerates the full interactive flow (research → propose sections → … → wrap) and lists every content block type with its own subskill reference file, giving comprehensive concrete coverage of what the skill does.

5 / 5

Completeness

It clearly states both the 'what' (generate a FigJam project plan board from a PRD plus codebase context) and the 'when' via an explicit 'Use when…' clause with concrete trigger phrasing.

5 / 5

Trigger Term Quality

It includes natural trigger phrases users would say ('project plan in FigJam', 'interactive project plan', '/generate-project-plan', plus the PRD-and-confirmation scenario), covering synonyms and the explicit slash command.

5 / 5

Distinctiveness Conflict Risk

The FigJam project-plan niche with per-section content + rendering confirmation is a clear, distinct trigger set with minimal overlap risk against other skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.