Agent skill

Openlark Design Review

by foxzool in foxzool/openlark

OpenLark Rust SDK 的代码设计/公共 API 规范审查技能(面向 crate/模块)。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制,并输出按优先级排序的整改清单与可落地改造方案。触发关键词:设计审查、crate 设计、API 设计、public…

Apache-2.0Auto-check: notesMedia & Creative

Install Openlark Design Review

skills CLI
$ npx skills add foxzool/openlark --skill openlark-design-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install foxzool/openlark openlark-design-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/foxzool/openlark.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/openlark-design-review .claude/skills/openlark-design-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openlark-design-review
GitHub stars
106
Token cost
~2.1k tokens
SKILL.md length
514 words
Files
2 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

OpenLark Rust SDK 的代码设计/公共 API 规范审查技能(面向 crate/模块)。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制,并输出按优先级排序的整改清单与可落地改造方案。触发关键词:设计审查、crate 设计、API 设计、public…

  • Works in 6 steps: 完成度统计(必须先做) → 对外范式(必须选 1 套,避免混用) → 设计检查清单(按重要性) → …
  • Tasks that involve Design review and critique
  • SKILL.md covers 🧭 技能路由指南, 目标, 适用范围 and 0. 完成度统计(必须先做), plus 7 more sections
  • Calls rg, python3 and cargo

What it does

Openlark Design Review is an agent skill from foxzool/openlark. OpenLark Rust SDK 的代码设计/公共 API 规范审查技能(面向 crate/模块)。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制,并输出按优先级排序的整改清单与可落地改造方案。触发关键词:设计审查、crate 设计、API 设计、public API、feature flag、端点、Builder/Service、架构一致性

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/design-review-report-template.md`).

It sits in Media & Creative, covering Design review and critique and Messaging and chat bots. It works with Rust and Feishu (Lark). The repository describes itself as: 飞书开放平台的非官方 Rust SDK,支持自定义机器人、长连接机器人、云文档、飞书卡片、消息、群组等 API 调用。 The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Design review and critique
  • Tasks that involve Messaging and chat bots

Example prompts

  • “/openlark-design-review”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Grep, Glob, Edit, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 完成度统计(必须先做)
  2. 对外范式(必须选 1 套,避免混用)
  3. 设计检查清单(按重要性)
  4. 常见整改套路(建议)
  5. 使用方式(给用户的最短指令)
  6. References

What it can do on your machine

Read from SKILL.md and the folder at commit 393f140. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Grep
    • Glob
    • Edit
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • python3
    • cargo

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openlark Design Review loads about 2.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 514 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Grep, Glob, Edit, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from foxzool/openlark at commit 393f140, republished under its Apache-2.0 licence (© foxzool). 514 words, ~2,066 tokens.

Download SKILL.mdSave it as .claude/skills/openlark-design-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
openlark-design-review
description
OpenLark Rust SDK 的代码设计/公共 API 规范审查技能(面向 crate/模块)。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制,并输出按优先级排序的整改清单与可落地改造方案。触发关键词:设计审查、crate 设计、API 设计、public API、feature flag、端点、Builder/Service、架构一致性
allowed-tools
Read, Grep, Glob, Edit, Bash
argument-hint
[crate-name|path]

OpenLark 代码设计规范审查(Skill)

🧭 技能路由指南

本技能适用场景:

  • 审查 crate 或模块的整体设计规范
  • 需要统计 API 完成度(已实现/未实现/完成率)
  • 需要检查架构一致性(端点体系、范式选择、feature gating)
  • 需要输出按优先级排序的整改清单(P0-P3)

其他技能:

  • 仅做代码规范体检(不做深度设计审查)→ Skill(openlark-code-standards)
  • 添加/重构单个 API → Skill(openlark-api)
  • 统一 validate() 写法 → Skill(openlark-validation-style)
关键词触发映射
  • 架构设计、public API、收敛方案、feature gating、兼容策略、breaking change → openlark-design-review
  • 代码规范、规范检查、风格一致性、体检 → openlark-code-standards
  • validate、必填校验、空白字符串、validate_required → openlark-validation-style
  • 新增 API、重构 API、Builder、Request/Response、mod.rs 导出 → openlark-api
  • 覆盖率、缺失 API、实现数量、CSV 对比 → openlark-api-validation
双向跳转规则
  • 若先做设计审查,但缺少全仓规范证据,先补跑 openlark-code-standards。
  • 若主要问题退化为校验写法统一,转 openlark-validation-style。

目标

把“设计审查”变成可重复执行的流程,而不是随手点评。

你要输出:

  • 一份 可执行的整改清单(P0~P3,含证据与影响)
  • 一份 收敛方向(选定 1 套对外范式,并说明迁移策略)
  • 一段 接口完成度量化(完成/缺失/完成率,排除 meta.Version=old)
  • 如用户同意:直接落地修复(优先处理 P0/P1)

适用范围

  • 任意 crate(如 crates/openlark-docs/)或任意模块树(如 src/ccm/wiki/v2/)
  • 重点面向 public API 与 跨模块一致性

0. 完成度统计(必须先做)

目的:把“我觉得实现了很多”变成可验证数据。统计口径默认排除 meta.Version=old。

0.1 以 crate 为单位统计(推荐)

使用仓库已有脚本直接对比 CSV 与落盘实现(strict 命名规范):

bash
python3 tools/validate_apis.py --crate <crate-name>

输出包含:API 总数/已实现/未实现/完成率,以及按 bizTag 的统计表;同时会生成默认报告到 reports/api_validation/<crate>.md。

0.2 以 bizTag 为单位统计(当用户只关心某些业务域)
bash
python3 tools/validate_apis.py --src <crate-src-path> --filter <bizTag...>
0.3 预期总量参考(快速对齐)

若需要快速确认“某 bizTag 的有效 API 总数(排除 old)”,可参考仓库文档 crates.md 的统计表(数据源为 api_list_export.csv)。

如需从 api_list_export.csv 重新生成 bizTag 统计(排除 old),可运行:

bash
python3 - <<'PY'
import csv
from collections import Counter

counts = Counter()
counts_all = Counter()
with open("api_list_export.csv", newline="", encoding="utf-8") as f:
    r = csv.DictReader(f)
    for row in r:
        biz = row.get("bizTag")
        ver = row.get("meta.Version")
        if not biz:
            continue
        counts_all[biz] += 1
        if ver != "old":
            counts[biz] += 1

print("bizTag,total,exclude_old,old")
for biz in sorted(counts_all.keys()):
    total = counts_all[biz]
    ex = counts[biz]
    print(f"{biz},{total},{ex},{total-ex}")
print(f"TOTAL,{sum(counts_all.values())},{sum(counts.values())},{sum(counts_all.values())-sum(counts.values())}")
PY

审查输入(先问清楚)

如果用户没说清楚范围,必须先追问 2 个问题:

  1. 审查目标:仅该 crate,还是需要和全仓库一致(对齐 openlark-client/openlark-core)?
  2. 改造约束:允许 breaking change 吗?(例如移除旧入口、调整 re-export 路径)

输出模板(强制)

按以下结构输出,不得随意变形:

  1. 结论概览:用 3~6 条 bullet 总结现状与最大风险
  2. 接口完成度(排除 old):必须给出完成/缺失/完成率(来源见“0. 完成度统计”)
  3. 问题清单(P0~P3):
    • 每条问题必须包含:现象 → 证据(文件:行) → 影响 → 建议
  4. 收敛方案:
    • 选定 1 套“对外调用范式”(见 §1)
    • 给出迁移步骤与兼容策略(保留旧 API、deprecated 周期等)
  5. 可执行 TODO:
    • 最多 10 条,按优先级排序,能拆 PR 的粒度

注:证据必须精确到 path:line,避免“我觉得/好像”。

1. 对外范式(必须选 1 套,避免混用)

范式 A:Request 自持 Config(流式 Builder)

适用:大量端点、调用侧更偏“链式设置参数”。

特征:

  • Request::new(Config) 保存 Config
  • Request::execute() / execute_with_options(RequestOption)
  • Service(若存在)只负责“分组/版本入口”,不承载网络逻辑
范式 B:Builder → build(Request) → execute(Service)

适用:希望把“执行上下文(Config/Transport)”都集中在 Service 上,便于 mock/注入。

特征:

  • Builder 只拼 Request
  • 统一 execute 由 openlark_core::trait_system::ExecutableBuilder 提供(trait 定义在 crates/openlark-core/src/trait_system/executable_builder.rs:11,业务 crate 通过宏批量 impl,例如 crates/openlark-meeting/src/common/macros.rs 的 impl_executable_builder!/impl_executable_builder_owned!)
  • Service 持有 Config,并负责实际请求发送

⚠️ trait 名核实:现码中 trait 名是 ExecutableBuilder(不是单字母 n)。引用时写完整路径 openlark_core::trait_system::ExecutableBuilder,不要写成 trait_system::n。

规则:同一个 project/version 内不得同时出现 A+B;若历史原因混用,必须定义清晰的迁移路线。

2. 设计检查清单(按重要性)

2.1 Public API 入口与导出
  • 是否存在多个“同义入口”(例如 Client/Service/MainService)导致用户困惑?
  • 是否存在“占位/空实现”的 public API(例如 builder setter 不生效)?
  • re-export 是否稳定、是否引入 ambiguous_glob_reexports 需要大量 allow?
  • prelude 是否只导出“高频且稳定”的类型,避免把内部实现细节暴露出去?
  • event/回调类不进统一 Client ServiceRegistry:event 模块在业务优先级模型中属 P2(非 P0 核心业务),按基础设施类对待(与 WebSocket LarkWsClient 同类),仅在所属业务 crate(如 openlark-communication)暴露,不进 declare_client!/ServiceRegistry 注册表(统一 client 仅注册 P0/P1 资源客户端)。详见 docs/CI_TEST_TARGET_COVERAGE.md(#228 决策)。
2.2 Feature gating 一致性(Cargo.toml ↔ cfg)
  • Cargo.toml 的 feature 是否与 lib.rs/mod.rs 的 #[cfg(feature = "...")] 对齐?
  • 子模块是否按 feature 做最小编译单元,避免“开了一个 feature 实际编进来一大坨”?
  • default features 是否合理(默认开启过多会放大编译成本与 API 面积)?
2.3 端点体系收敛

检查点:

  • 是否复用 crate 的 endpoints 常量或 enum(而非手写 "/open-apis/...")?
  • 是否只通过唯一端点来源(enum 或常量系统二选一)进行生产调用?
  • 是否避免多套端点系统并存(enum/const/path-template)?
  • 端点定义是否可被静态检查(避免遗漏、避免 typo)?

详细规范见 Skill(openlark-api) §3.2(模板)和 §4.3(检查清单)

2.4 Config/生命周期与性能
  • openlark-core::Config 本身已使用 Arc 共享;crate 内再包一层 Arc<Config> 通常是冗余设计。
  • Service/Request 是否在不必要的地方 clone 大对象(如 http client)?
  • RequestOption 是否在所有对外执行入口都可用并被透传?
Show full SKILL.md (211 more words)Show less
⚠️ Service 层模式检查(P0 级)

禁止模式:

  • ❌ Service 持有独立的 HTTP client 字段
  • ❌ 使用 LarkClient 作为具体类型(它是 openlark_client::traits 中的 trait)
  • ❌ 在测试中使用 .unwrap() 调用 Config::build()(build() 直接返回 Config)

正确模式(参考 openlark-docs/src/common/chain.rs):

  • ✅ Service 只持有 Arc<Config>
  • ✅ 子 Service 通过 new(Arc<Config>) 透传配置
  • ✅ HTTP 传输统一由 openlark_core::http::Transport(pub struct Transport<T>,http.rs:23,prelude 导出于 lib.rs:93)处理
  • ✅ Config::build() 直接返回 Config,不需要 .unwrap()

检查点:

bash
# 搜索错误的 LarkClient 用法
# 注:本仓已历史清零(无命中),此命令作“回归守卫”——命中即 P0。
rg "LarkClient::new" crates/

# 搜索错误的 Config::build().unwrap() 用法
# 注:本仓已历史清零(无命中),此命令作“回归守卫”——命中即 P0。
rg "Config::builder\(\).*\.build\(\)\.unwrap\(\)" crates/

Transport 精确路径:HTTP 传输统一走 openlark_core::http::Transport(pub struct Transport<T>,定义在 crates/openlark-core/src/http.rs:23,由 crates/openlark-core/src/lib.rs:93 的 prelude 导出)。

2.5 错误处理与类型边界
  • crate 自定义 Error 是否真正被使用?还是存在“孤儿文件/未被 mod 引入”的失效实现?
  • 错误是否统一携带上下文(operation/resource_id/request_id)?
  • validate 规则是否与全仓一致(必要时使用 Skill(openlark-validation-style))
2.6 测试与告警控制
  • cargo check --all-features 是否无 warning?(deprecated/unused 要么修,要么显式 allow)
  • 单元测试是否只验证“构建正确”,避免依赖真实网络?
  • 文档示例是否可 compile(必要时 no_run/ignore 但要有理由)
2.7 CI/测试门控一致性(#251 后约定)

背景:CI clippy 三个维度(all-features / no-default-features / 各 feature 组合)统一加 --all-targets(#250/#254),把 test/bench target 纳入 lint;门控写法不当会直接被 CI 拦或触发 E0601/missing_docs。详见 docs/CI_TEST_TARGET_COVERAGE.md。

检查点:

  1. example 必须在 Cargo.toml [[example]] 声明 required-features(CI clippy 跑 --all-targets 会编译 example)。

    • example 不要用 #![cfg(feature="...")](会把 example 清空成无 main,报 E0601)。
    • 现码范例:crates/openlark-docs/Cargo.toml 的 required-features = ["baike", "bitable", "ccm-core"]。
  2. feature 契约测试文件结构约定://! 文档注释 在前 + #![cfg(feature="x")] 紧随其后。

    • 文件首行必须是 //! ... 文档;#![cfg(...)] 放第 2 行(顺序反了会触发 clippy missing_docs)。
    • 不要用 #[cfg] 包整文件,不要把 #![cfg] 放在 //! 之前。
    • 现码范例:crates/openlark-application/tests/application_contract_models.rs:1-2(//! 在第 1 行,#![cfg(feature = "v1")] 在第 2 行)。
  3. 检查命令:

    bash
    # 测试文件门控写法(确认 //! 在前、#![cfg(feature)] 紧随)
    rg -n '^#!\[cfg\(feature' crates/<crate>/tests/
    
    # example 是否声明 required-features
    rg -n 'required-features' crates/<crate>/Cargo.toml

3. 常见整改套路(建议)

  • 入口收敛:保留一个 canonical(例如 DocsClient),其余入口标 deprecated 并给迁移路径。
  • 删除占位 API:对外暴露的 builder 若无法工作,要么补齐实现,要么移除/隐藏。
  • 范式统一:先在一个子域(如 wiki/v2)试点,再逐步复制到同域其他模块。
  • 端点统一:明确“生产用 enum,测试用 const”(或反之),并把另外两套标记为 internal/test-only。
  • feature 对齐:把 mod 粒度切到能明显减少编译体积的位置(以“用户开哪个 feature 就编进来什么”为目标)。

4. 使用方式(给用户的最短指令)

当用户说“审查 XXX 设计”时:

  • 先确认范围与 breaking 约束(见“审查输入”)
  • 按“输出模板”给出报告
  • 只要用户同意,就按 P0→P1 顺序落地改造并跑 cargo check/test

5. References

  • PR 审查报告模板:references/design-review-report-template.md

© foxzool, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/openlark-design-review of foxzool/openlark.

  • SKILL.md
  • references/design-review-report-template.md

Open the folder on GitHubat commit 393f140

Compare with similar skills

Openlark Design Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openlark Design Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openlark Design Review this skillfoxzool/openlark106—~2.1kAutomated safety check: NotesApache-2.0
FeedgrabiBigQiang/feedgrab614—~2kAutomated safety check: PassMIT
Feishu Seedance Video Pipelinedracohu2025-cloud/draco-skills-collection227—~5kAutomated safety check: NotesMIT
Qiaomu Mondo Poster Designnexu-io/nexu3.3k1 repos~4.1kAutomated safety check: PassMIT
Beautiful Feishu Whiteboardzarazhangrui/beautiful-feishu-whiteboard756—~1.3kAutomated safety check: PassMIT
Bili Following Latestdragon-hh/ai-boshu-crawler106—~1.9kAutomated safety check: PassNone

Similar skills

  • Feedgrab

    iBigQiang/feedgrab

    Universal content grabber — fetch any URL and return structured Markdown.

    614 GitHub stars~2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Feishu Seedance Video Pipeline

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when running a Feishu/Lark Base-centered Seedance video production pipeline: inspect/backfill the Base row, create/reference assets, build Row-24-style Chinese Seedance…

    227 GitHub stars~5k tokensUpdated 23 days ago
    Media & CreativeAuto-check: notes
  • 一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。无需懂PS、配色或艺术史,AI自动选择最佳风格(基于33+位传奇设计师)。支持多平台多比例:公众号封面(21:9)、小红书配图(3:4)、文章配图(16:9)、书籍封面(9:16)、专辑封面(1:1)、电影海报(9:16)。包含AI提示词优化、风格对比、图生图转换功能。触发词:"Mondo风格"、"书籍封面设计"、"专辑封面"、"海报设计"…

    3.3k GitHub starsUsed in 1 repo~4.1k tokens
    Media & CreativeAuto-check passed
  • Beautiful Feishu Whiteboard

    zarazhangrui/beautiful-feishu-whiteboard

    A library of 35 curated colour palette styles for building beautiful, editable Feishu / Lark (飞书) whiteboards from SVG.

    756 GitHub stars~1.3k tokensUpdated 4 mo ago
    Productivity & AutomationAuto-check passed
  • Bili Following Latest

    dragon-hh/ai-boshu-crawler

    Run the AI博主爬取 project workflow that downloads the latest Bilibili videos for Feishu Base creators marked 是否持续跟踪=true, writes successful downloads to the Feishu 视频 table, and writes a 爬取任务日志 record.

    106 GitHub stars~1.9k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Feishu Doc

    openclaw/openclaw

    Feishu document read/write workflows. An agent skill from openclaw/openclaw.

    392k GitHub stars~516 tokensUpdated today
    Productivity & AutomationAuto-check passed

More from foxzool/openlark

All 8 skills in this repo
  • Verify Openlark

    foxzool/openlark

    Prove OpenLark (Feishu/Lark Rust SDK) changes the way a maintainer does — cargo build/test, public examples, API coverage and field-verify harnesses.

    106 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Openlark API

    foxzool/openlark

    OpenLark 项目 API 接口实现规范(速查)。用于添加/重构飞书开放平台 API:确定落盘路径、实现 Body/Response + Builder(Request)、对齐 endpoints 常量/enum、补齐 mod.rs 导出,并明确"调用服务端 API"的方法签名/RequestOption 传递约定。触发关键词:API 接口、API 文件、飞书 API、添加…

    106 GitHub stars~3k tokensUpdated 2 days ago
    Auto-check: notes
  • OpenLark API 字段核对技能。用于新增/重构飞书 API 后,核对 Rust 实现的请求体/响应体字段是否与飞书官方文档一致。通过 playwright 渲染飞书 SPA 文档页面,提取真实的请求/响应字段定义,对比代码实现找出不符项。触发关键词:字段核对、字段验证、字段不符、文档核对、核对请求字段、核对响应字段、飞书文档字段、推断字段、user 级接口、用户级接口字段

    106 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check: notes
  • Openlark Code Standards

    foxzool/openlark

    OpenLark 项目代码规范检查技能。用于快速审查仓库内的架构一致性、API 实现套路、参数校验、命名与导出规范,并输出可执行检查清单与证据路径。Triggers: code review / consistency check / architecture audit / 规范检查 / 风格一致性 / 体检 / 对齐约定。项目锚点见 AGENTS.mdCONVENTIONS 与…

    106 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check: notes
  • Openlark API Validation

    foxzool/openlark

    OpenLark API 覆盖率验证技能。用于验证各 crate 的 API 实现数量与覆盖率,基于 tools/validateapis.py 脚本和 apilistexport.csv 对比实际代码实现。触发关键词:API 验证、API 覆盖率、验证 API 数量、检查 API 实现、API 统计

    106 GitHub stars~2k tokensUpdated 2 days ago
    Auto-check: notes
  • Openlark Naming

    foxzool/openlark

    OpenLark Rust SDK 命名与对外 API 表达规范(Client/Service/Resource/Request/Builder)。用于新增/重构公开类型、设计 meta 调用链、调整模块导出与 prelude、或排查 Service 同名/语义错配/V{N}Service 版本层错位、Resource 与 Service 同类型两名、以及…

    106 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check: notes

Questions about Openlark Design Review

What does Openlark Design Review do?

OpenLark Rust SDK 的代码设计/公共 API 规范审查技能(面向 crate/模块)。用于系统化检查入口设计、feature gating、Request/Service/Builder 一致性、端点体系、Config/错误处理、导出与文档同步、测试与告警控制,并输出按优先级排序的整改清单与可落地改造方案。触发关键词:设计审查、crate 设计、API 设计、public…. Openlark Design Review is an agent skill from foxzool/openlark.

When should I use Openlark Design Review?

Openlark Design Review fits situations like: tasks that involve Design review and critique; tasks that involve Messaging and chat bots.

How do I install Openlark Design Review in Claude Code?

Run `npx skills add foxzool/openlark --skill openlark-design-review -a claude-code`. Or copy the skill folder (.agents/skills/openlark-design-review in foxzool/openlark) into .claude/skills/openlark-design-review in your project. Claude Code loads it when a task matches its description.

How do I install Openlark Design Review in Codex?

Run `npx skills add foxzool/openlark --skill openlark-design-review -a codex`. Or copy the skill folder (.agents/skills/openlark-design-review in foxzool/openlark) into .agents/skills/openlark-design-review in your project. Codex loads it when a task matches its description.

Can I use Openlark Design Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add foxzool/openlark --skill openlark-design-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openlark-design-review, .gemini/skills/openlark-design-review, .github/skills/openlark-design-review and .opencode/skills/openlark-design-review in your project.

What does Openlark Design Review need to run?

Going by SKILL.md and its folder, Openlark Design Review needs the command-line tools its instructions call (rg, python3 and cargo). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Grep, Glob, Edit, Bash.

Does Openlark Design Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Openlark Design Review safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Openlark Design Review use?

Openlark Design Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openlark Design Review use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 875 tokens, read only when the agent opens those files.

What are the alternatives to Openlark Design Review?

Skills that share tags, products or a category with Openlark Design Review: Feedgrab (iBigQiang/feedgrab, 614 stars), Feishu Seedance Video Pipeline (dracohu2025-cloud/draco-skills-collection, 227 stars), Qiaomu Mondo Poster Design (nexu-io/nexu, 3.3k stars) and Beautiful Feishu Whiteboard (zarazhangrui/beautiful-feishu-whiteboard, 756 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openlark Design Review?

foxzool (a GitHub user) maintains it in foxzool/openlark, which has 106 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 9, 2026.

Source: foxzool/openlark on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.