CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-implementing-figma-designs

Implements Figma designs 1:1 using OneKey component library (还原设计稿).

56

Quality

64%

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

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-implementing-figma-designs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-organized, highly actionable guide with concrete repo paths, tool commands, and copy-paste-ready code patterns; its main weaknesses are a partially redundant do/don't section and the absence of a verification checkpoint in the workflow. Structure is solid, though the reference-style catalogs could be split into a bundled reference file.

Suggestions

Collapse the 'What NOT to do'/'What TO do' bullet lists into the 'Focus on UI First' numbered principles to remove the duplicated guidance and tighten the token budget.

Add a final verification step to the workflow, e.g. 'Compare implemented layout against the Figma design (spacing, colors, typography) and fix discrepancies before finishing', to support the 1:1 goal.

Move the component category catalog and token tables into a references/ file (e.g. references/components.md) and link to it, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

The body is efficient — lean code snippets, terse token tables, no explanations of concepts Claude already knows — but the "What NOT to do"/"What TO do" bullet lists largely restate points 1-4 of "Focus on UI First, Data Later" (mock data, skip i18n/APIs, match the design). This matches 'efficient; minor instances of over-explanation that could be trimmed'. It is not a 5 due to that duplicated section, and not a 3 because the padding is localized rather than pervasive.

4 / 5

Actionability

Concrete file-path patterns ("packages/components/src/{category}/{ComponentName}/"), explicit tool commands ("Read: ...index.tsx", "Glob: ...stories/*{ComponentName}*.tsx"), and copy-paste-ready snippets for Stack layouts, spacing/color/font tokens, and mock data give mostly executable guidance. It is not a 5 because step 1 of the workflow ("Analyze the Figma design using Figma MCP") gives no concrete command or tool invocation, and not a 3 because virtually everything else is directly executable.

4 / 5

Workflow Clarity

The 5-step Workflow (analyze → identify components → look up source/demo → create mock data → implement) is a clear, well-ordered sequence that links to the detailed lookup section. It is not a 5 because there is no explicit verify-against-design checkpoint (useful for a stated 1:1/pixel-perfect goal), and not a 3 because the sequence is complete and unambiguous, and the task is not destructive or batch-operational so no validation cap applies.

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the ~150-line body is cleanly sectioned (Core Principles, Component Lookup, Quick Reference, Workflow) with consistent heading hierarchy. It is not a 5 because the full component-category catalog and token tables are inlined reference material that could live in a separate file, and the skill exceeds the under-50-line simple-skill exception; it is not a 3 because nothing is buried and the structure makes navigation easy.

4 / 5

Total

16

/

20

Passed

Description

53%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 concise, specific, and clearly niched to Figma-to-OneKey implementation, but it omits any 'when to use' trigger guidance and lists only a single action. Adding an explicit use-when clause with natural trigger phrases would raise both completeness and trigger-term quality.

Suggestions

Append a trigger clause such as 'Use when implementing a Figma design or mockup in the OneKey codebase, or when the user shares a Figma link to build UI from' to satisfy the missing 'when' half of completeness.

Add natural synonyms users might say — e.g. 'design mockup', 'UI implementation', 'design handoff' — alongside 'Figma designs' to broaden trigger-term coverage.

Mention one or two more concrete capabilities (e.g. component lookup, design tokens/mocking data) to move specificity beyond a single action.

DimensionReasoningScore

Specificity

"Implements Figma designs 1:1 using OneKey component library" names the domain and one concrete action with a specific library, but does not list several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor. It is not a 2 because the action is concrete and library-specific rather than generic, and not a 4 because no additional capabilities (mock data, component lookup, token usage) are enumerated.

3 / 5

Completeness

The description has a clear 'what' ("Implements Figma designs 1:1 using OneKey component library") but contains no 'Use when...' or equivalent trigger guidance, which per the guidelines caps completeness at 3. It is not a 2 because the 'what' is specific and unambiguous, and it cannot be a 4 or higher without any explicit 'when' clause.

3 / 5

Trigger Term Quality

"Figma designs", "1:1", and "还原设计稿" are terms a user would naturally say, but common variations and synonyms such as "mockup", "UI implementation", or "design handoff" are missing, matching the 'some relevant keywords but missing variations' anchor. It is not a 4 because keyword coverage stops at the most obvious term, and not a 2 because 'Figma' is a strong, natural, domain-specific trigger rather than generic filler.

3 / 5

Distinctiveness Conflict Risk

The combination of "Figma designs 1:1" with the proprietary "OneKey component library" carves out a distinct niche unlikely to trigger the wrong skill, matching 'mostly distinct; minor overlap risk'. It is not a 5 because "Figma designs" alone could overlap with generic design-implementation or design-export skills, and not a 3 because the named proprietary library anchors it firmly.

4 / 5

Total

13

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.