CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

od-figma-migration

Default reference pipeline for the figma-migration taskKind — figma-extract → token-map → generate → critique.

60

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/scenarios/od-figma-migration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, configuration-dense body that sequences the pipeline clearly and includes an explicit critique feedback loop with a termination condition. Its main weaknesses are prose-described rather than snippet-complete GenUI configs and dangling spec citations with no bundled document behind them.

Suggestions

Ship the spec sections cited ('§10.3.1', '§21.3.1', etc.) as a bundle reference file, or inline the one or two rules actually needed — currently the citations are unresolvable dead ends.

Provide the two GenUI surfaces as complete config snippets (like the pipeline block) instead of field-value prose, so the plugin layer can be implemented copy-paste.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and dense: 'the canonical figma-migration flow. The pipeline is sequenced so each stage's output is the next stage's input' plus concrete artifact paths, with zero concept over-explanation or padding. Matches the 'lean and efficient; every token earns its place' anchor, not 4 because there is no over-explanation left to trim.

5 / 5

Actionability

The pipeline JSONC block ('stages', atom lists, repeat/until) is copy-paste ready, and the surfaces section gives concrete field values ('oauth.route=\'connector\'', connectorId=\'figma'', 'kind=\'form\''). Not 5 because the GenUI surface configs are described in prose rather than given as complete snippets, leaving minor gaps.

4 / 5

Workflow Clarity

The stage sequence is explicit with data-flow rationale ('figma-extract writes figma/tree.json ... generate reads both') and an explicit feedback loop ('repeat: true, until: critique.score>=4 || iterations>=3'). Not 5 because per-stage failure handling and validation checkpoints between extract/tokens/generate are not specified.

4 / 5

Progressive Disclosure

Under 50 lines with well-organized sections ('## Default pipeline', '## Required GenUI surfaces') and no external files needed, which would merit 5 — but the 'Spec §1 / §10.1 / §21.3.1 / §23.3.3' citations point to a spec document that is not in the bundle, leaving unresolvable references.

4 / 5

Total

17

/

20

Passed

Description

58%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 states a concrete, well-scoped 'what' via the four named pipeline stages, but provides no 'use when' trigger guidance and only thin natural-language keyword coverage. It is distinct within its niche yet under-serves discovery.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the figma-migration taskKind is requested or the user asks to convert a Figma design to HTML') — its absence currently caps completeness at 3.

Broaden trigger terms to include natural user phrasing and synonyms such as 'Figma design to HTML', 'design-to-code', 'Figma file URL', or '.fig' links.

Give each stage a brief concrete verb or artifact (e.g., 'figma-extract pulls the Figma tree; token-map derives the color palette') to lift specificity from naming stages to describing actions.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'figma-extract → token-map → generate → critique' — naming the full pipeline. It falls short of 5 because the stages are bare identifiers without verbs or artifacts, and short of 3 because it enumerates four specific stages rather than 1-2.

4 / 5

Completeness

It has a clear 'what' (the default four-stage pipeline for the figma-migration taskKind) but no 'when' clause or equivalent trigger guidance at all, capping completeness at 3 per the judging guideline. Not 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

'figma-migration' and 'figma' are natural terms a user would plausibly say, but coverage is narrow — missing common variations like 'convert Figma design', 'design-to-code', or 'Figma URL'. Not 2 because real natural keywords are present rather than pure technical jargon; not 4 because several obvious synonyms are absent.

3 / 5

Distinctiveness Conflict Risk

Scoped to a specific 'figma-migration taskKind' with distinct pipeline stage names, giving a clear niche with minimal wrong-trigger risk. Not 5 because the stage identifiers (figma-extract, token-map) could overlap with closely related figma or pipeline skills.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

nexu-io/open-design

Path

plugins/_official/scenarios/od-figma-migration/SKILL.md

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.