CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lark-vc-agent

仅当用户或上游配置显式指定 lark-vc-agent 时使用,相关请求统一交由 lark-meeting 技能处理。

Quality

79%

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 ./skills/lark-vc-agent/SKILL.md

The canonical home for this skill is lark-minutes in larksuite/cli

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.

An exemplary minimal redirect stub: the body is maximally token-efficient, states its sole purpose (legacy-name compatibility), and gives one unambiguous, clearly signaled instruction to defer to lark-meeting. The only weakness is that the cross-bundle relative reference has no fallback if the sibling skill is missing.

DimensionReasoningScore

Conciseness

Three lines, no padding, no explanation of concepts Claude already knows — "本技能只用于兼容旧名称,不直接处理业务" plus a single MUST directive. Every token earns its place, matching the lean-and-efficient anchor exactly.

5 / 5

Actionability

The single instruction is concrete and executable — "完整读取 ../lark-meeting/SKILL.md,并按照其中的路由和行动指南执行" gives an explicit path and an unambiguous action. Not a 5 because there is no fallback or verification if the referenced sibling SKILL.md is absent, a minor gap for copy-paste-ready execution.

4 / 5

Workflow Clarity

Per the simple-skill note, a single unambiguous action can score 5: read lark-meeting's SKILL.md fully, then execute per its routing and action guide. No destructive or batch operations, so the validation cap at 3 does not apply.

5 / 5

Progressive Disclosure

The 3-line body is well organized (heading, purpose statement, directive) with a clearly signaled, one-level-deep reference (../lark-meeting/SKILL.md) — matching 'good structure, references mostly clear, minor organization gaps'. Not a 5 because the reference points outside this skill's own bundle (no references/, scripts/, or assets/ exist here), so navigation depends on a sibling skill directory that cannot be verified within this bundle.

4 / 5

Total

18

/

20

Passed

Description

66%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 well-scoped compatibility-shim description: it is honest about being a redirect, gives an explicit and narrow trigger condition, and cleanly avoids conflicts by delegating to lark-meeting. Its weaknesses are thin trigger-term coverage (no natural synonyms for the underlying meeting/VC capability) and a 'what' that describes only the delegation, not the capability itself.

Suggestions

Add natural trigger synonyms for the underlying capability (e.g., 飞书会议, 视频会议, Lark meeting, VC) so users who describe the task rather than the skill name can still hit this entry.

Briefly state what the capability actually is (e.g., '会议管理与视频会议操作,由 lark-meeting 技能提供') instead of only the delegation instruction '相关请求统一交由 lark-meeting 技能处理'.

Note the deprecated-name status with common old-name variants (e.g., lark-vc, lark video conference) to improve recall of the legacy trigger terms.

DimensionReasoningScore

Specificity

The description names its domain ("lark-vc-agent" / "lark-meeting") and one concrete action — "相关请求统一交由 lark-meeting 技能处理" (delegate requests to the lark-meeting skill) — but offers no coverage of what the capability actually is. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive); a 4 would require several specific actions listed.

3 / 5

Completeness

Both parts are explicit: 'when' is concrete ("仅当用户或上游配置显式指定 lark-vc-agent 时使用") and 'what' is stated (delegate to lark-meeting), so the missing-'Use when' cap at 3 does not apply. Not a 5 because the 'what' is only the delegation mechanism and never states the underlying capability in concrete trigger phrases; not a 3 because 'when' is explicit and specific.

4 / 5

Trigger Term Quality

Relevant keywords are present ("lark-vc-agent", "lark-meeting") and the explicit-name trigger is captured, but common variations and natural synonyms (e.g., 视频会议, 飞书会议, VC, video conference) are absent — matching anchor 3, 'some relevant keywords but missing common variations or synonyms'. Not a 2, because the keywords present are specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

The trigger is maximally narrow — only explicit mention of the deprecated name "lark-vc-agent" — and all overlapping work is explicitly routed to lark-meeting, giving a clear niche with minimal conflict risk. Anchor 4's 'minor overlap risk' would apply if the trigger could fire on sibling-skill requests, but the explicit-only condition prevents that.

5 / 5

Total

15

/

20

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.

Validation — 12 / 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: 1 suspicious

Warning

Total

12

/

16

Passed

Repository

larksuite/cli

Path

skills/lark-vc-agent/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.