CtrlK
BlogDocsLog inGet started
Tessl Logo

lark-whiteboard

飞书画板:查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。 当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责:飞书云文档内容编辑(lark-doc)、文档内嵌电子表格/Base(lark-sheets / lark-base)。

68

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

A tight, well-structured overview body that routes user needs to concrete commands and cleanly defers detail to real one-level-deep reference files. The only gap is that the body does not itself sequence the destructive 创作/修改 workflows with explicit validation checkpoints — those live entirely in the referenced workflow file.

Suggestions

Add a brief inline outline of the 创作/修改 workflow's key validation checkpoints (e.g. 'export source → review → update → re-export to verify') in the body, so error-recovery feedback for the destructive update path is visible without opening the reference.

Make the body commands fully copy-paste ready by showing the full invocation form once (e.g. 'lark-cli whiteboard +export --output-type preview --token <wbcn> --as user') alongside the shortcut, so the overview is self-sufficient for the common case.

DimensionReasoningScore

Conciseness

The body is lean — decision tables, short pointer lines, and reference links — with no padding or explanation of concepts Claude already knows; every line earns its place.

3 / 3

Actionability

Maps user needs to concrete subcommands with real flags (e.g. '+export --output-type preview', '+update --input_format mermaid/plantuml/svg', '--as user') via the 快速决策 table and Shortcuts, giving specific executable guidance rather than vague direction.

3 / 3

Workflow Clarity

The decision table provides clear need→action routing and a pre-flight version check, but the multi-step 创作/修改 sequences with their validation checkpoints and error-recovery feedback loops are delegated to the reference file rather than sequenced in the body, leaving checkpoints implicit here.

2 / 3

Progressive Disclosure

Clear overview that signals one-level-deep references (export.md, update.md, workflow.md) — all verified to exist — via the decision table and Shortcuts, with content appropriately split and easy to navigate.

3 / 3

Total

11

/

12

Passed

Description

85%

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 well-constructed description that states concrete capabilities, gives explicit use-when triggers, and clearly delineates scope against sibling skills. The main weakness is trigger-term variety, which reuses the single noun '画板' across scenarios rather than covering the range of natural phrasings a user might say.

Suggestions

Broaden trigger terms beyond repetitions of '画板' — add natural variations users might actually say, e.g. '飞书白板', 'whiteboard', '看板/图示/流程图导出', so the description matches a wider range of real requests.

Consider naming the supported update formats inline in the trigger clause (e.g. '用 Mermaid/PlantUML/SVG 更新画板') to surface more discoverable keywords.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '查询和编辑飞书云文档中的画板', '导出画板为预览图片', '导出原始节点结构', '使用多种格式更新画板内容' — rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (query/edit/export/update capabilities) and 'when' ('当用户需要...时使用此 skill'), matching the anchor for explicit triggers on both.

3 / 3

Trigger Term Quality

Includes relevant triggers ('查看画板内容、导出画板图片、编辑画板时使用此 skill') but these are repetitive variations on '画板' and miss common natural phrasings users might say, so coverage is incomplete.

2 / 3

Distinctiveness Conflict Risk

Has a clear niche (飞书画板) and an explicit out-of-scope clause ('不负责:...lark-doc...lark-sheets / lark-base') that distinguishes it from sibling skills, making mis-triggering unlikely.

3 / 3

Total

11

/

12

Passed

Validation

75%

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

Validation12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 5 suspicious

Warning

Total

12

/

16

Passed

Repository
larksuite/cli
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.