CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lark-apps

妙搭(Spark/Miaoda)应用开发与托管:应用创建、本地全栈开发、云端生成迭代、创意设计(UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索)、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用协作者与协作权限设置、应用角色与成员管理、自动化触发器(定时/记录变更/Webhook/飞书审批)。当用户要开发/新建一个系统·工具·平台·应用,或要本地开发 / 云端开发 / 修改 / 部署 / 发布 / 上线 / 拿可分享链接,或用 HTML 做页面·网站·部署到妙搭,或要设计 / design / mockup / prototype / wireframe / 做 PPT / deck / 视觉探索,或提到妙搭/Spark/Miaoda 应用(链接形如 `/app/app_xxx` 或 `/page/<token>`,运行时域名形如 *.aiforce.cloud)、应用数据库、应用文件存储、开放 API Key、可见范围、应用协作者/开发权限、应用角色/角色成员、线上日志、接口请求量、错误量、延迟、访问量、环境变量、给妙搭应用配自动化任务/定时触发/审批通过后自动触发时使用。不负责普通云盘文件上传(lark-drive)、飞书文档编辑(lark-doc)、原生幻灯片创建(lark-slides)。

Quality

89%

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

85%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 dense, highly actionable router: concrete commands, confirmation gates for destructive operations, and real feedback loops. The main defect is progressive disclosure — the creative-design route, one of the three app_type paths, is a dangling reference, and the access-scope pointer is vague — with minor conciseness losses from repetition and overlong guardrail sentences.

Suggestions

Add the missing creative-design/creative-design.md to the bundle (or repoint the six references to an existing file such as references/lark-apps-local-dev.md) — the primary HTML/创意模式 development route currently dead-ends.

Replace the vague access-scope row ('对应 access-scope reference') with explicit links to references/lark-apps-access-scope-get.md and references/lark-apps-access-scope-set.md, matching the style of every other routing row.

Consolidate the six repetitions of the creative-design link and tighten the longest guardrail sentences (发布态护栏, 禁止预授权判定底线) into shorter condition→action rules to cut token cost without losing the gates.

DimensionReasoningScore

Conciseness

Almost entirely non-obvious domain rules (error subtypes, ID-type enums, scope names, approval states) with no teaching of known concepts, but the creative-design link is repeated six times and several guardrail sentences (发布态护栏, 预授权底线) are long run-ons that restate conditions and could be trimmed.

4 / 5

Actionability

Copy-paste-ready commands with placeholders throughout (e.g. 'lark-cli apps +member-add --app-id <app_id> --member-type openid --member-id ou_xxx --perm view --dry-run --as user', '+metric-list --metric requests --since <range>'), and the intent table maps every intent to an exact subcommand plus its reference file — even edge cases like meta_token resolution get a concrete command.

5 / 5

Workflow Clarity

Clear sequencing (dev-path decision table → intent routing → app_id resolution → release guardrails) with explicit validation gates (dry-run before member writes, --yes gating, db-execute dry-run), a genuine error-recovery feedback loop (git failure → +git-credential-init → retry → stop and report), release polling with terminal-state precedence, and a non-preauthorization checklist for destructive operations.

5 / 5

Progressive Disclosure

The 27 reference files are all one level deep, clearly signaled, and resolve — but the primary HTML/creative route points to 'creative-design/creative-design.md' which does not exist in the bundle (referenced 6 times as the complete dev/publish flow), and the access-scope row says only '对应 access-scope reference' with no link, so navigation fails on a main path.

3 / 5

Total

17

/

20

Passed

Description

96%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 strong description: concrete capability enumeration, explicit bilingual 'use when' triggers with platform-recognizable tokens, and explicit boundary exclusions against sibling skills. The only weakness is the broad '系统·工具·平台·应用' trigger phrase, which creates minor overlap risk with generic development requests.

DimensionReasoningScore

Specificity

Enumerates 10+ concrete capability areas (应用创建、本地全栈开发、创意设计含 UI mockup/原型/线框图/落地页/仪表盘/deck、日志/Trace/监控/PV/UV 查询、环境变量管理、协作者与权限、角色成员、自动化触发器) with sub-details, comprehensively covering the command surface with no notable gaps.

5 / 5

Completeness

Explicitly answers both 'what' (first sentence enumerates capabilities) and 'when' ('当用户要…时使用' with concrete trigger phrases), and adds negative scope ('不负责…lark-drive…lark-doc…lark-slides') to prevent misfires.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms in both Chinese and English (开发/新建、部署/发布/上线/拿可分享链接、设计/design、mockup、prototype、wireframe、做 PPT/deck), plus platform-specific tokens users would paste (app_ links, /page/<token>, *.aiforce.cloud, 接口请求量、错误量、延迟、环境变量).

5 / 5

Distinctiveness Conflict Risk

Clear 妙搭/Spark/Miaoda niche with explicit exclusions against the most likely sibling skills, but the very broad trigger '开发/新建一个系统·工具·平台·应用' can fire on generic build-a-tool requests outside this platform — minor overlap risk rather than minimal.

4 / 5

Total

19

/

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: 3 missing, 4 suspicious

Warning

Total

12

/

16

Passed

Repository

larksuite/cli

Path

skills/lark-apps/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.