Agent skill

Openlark Code Standards

by foxzool in 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…

Apache-2.0Auto-check: notesAgent Workflows

Install Openlark Code Standards

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

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

GitHub CLI
$ gh skill install foxzool/openlark openlark-code-standards --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-code-standards .claude/skills/openlark-code-standards && 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-code-standards
GitHub stars
106
Token cost
~1.8k tokens
SKILL.md length
465 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
Apache-2.0

At a glance

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…

  • Works in 6 steps: API 实现套路一致性 → 端点定义规范 → 参数校验规范 → …
  • Tasks that involve Agent instruction files
  • SKILL.md covers 适用场景, 目标, 检查范围 and 核心检查项, plus 6 more sections
  • Calls just, rg and cargo

What it does

Openlark Code Standards is an agent skill from 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 AGENTS.mdANTI-PATTERNS。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files and Messaging and chat bots. It works with 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 Agent instruction files
  • Tasks that involve Messaging and chat bots

Example prompts

  • “/openlark-code-standards”

Requirements

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

Workflow steps

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

  1. API 实现套路一致性
  2. 端点定义规范
  3. 参数校验规范
  4. 命名与公开 API 表达
  5. 导出与 feature gating
  6. CI 与测试门控(#228 审核闭环)

What it can do on your machine

Read from SKILL.md and the folder at commit 6128d6d. 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
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • just
    • rg
    • 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 Code Standards loads about 1.8k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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, 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 6128d6d, republished under its Apache-2.0 licence (© foxzool). 465 words, ~1,821 tokens.

Download SKILL.mdSave it as .claude/skills/openlark-code-standards/SKILL.md (or your agent's skills folder).
name
openlark-code-standards
description
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.md#CONVENTIONS 与 AGENTS.md#ANTI-PATTERNS。
allowed-tools
Read, Grep, Glob, Bash
argument-hint
[crate-name|path]

OpenLark 代码规范检查(Skill)

适用场景

  • 用户要求“检查项目代码规范”
  • 新增 API 前想确认实现套路是否一致
  • 评审 PR 时需要快速验证是否遵循 OpenLark 既有约定
  • 发现模块风格漂移,想做一次统一体检

目标

输出一份可落地的规范检查结果,包含:

  • 规范结论(通过/风险)
  • 规则-证据对(每条规则附 path:line)
  • 风险分级(P0/P1/P2)
  • 新 API 最小检查清单(可直接用于 PR Review)

检查范围

覆盖全部 crates/openlark-*(按 AGENTS.md#STRUCTURE 有 18 个业务/基础设施 crate)。

  • 重点核审:核心基础设施(openlark-core、openlark-client、openlark-protocol)与高频业务 crate(openlark-docs、openlark-communication、openlark-hr)。
  • Client 命名(XxxClient)权威映射表见 docs/CLIENT_NAMING_CONVENTION.md 的「当前映射」,命名核审以此为准。
  • 可按参数缩小为某个 crate 或目录(如 openlark-mail、crates/openlark-hr/src/)。

核心检查项

1) API 实现套路一致性
  • 是否使用 Request/Response + Builder 模式
  • 是否提供 execute() 与 execute_with_options(RequestOption)
  • 是否通过 Transport::request(...) 发送请求

🔴 硬规则(grep 命中即 P0 违规):

  • 业务 crate(除 openlark-core 与 openlark-webhook)不得出现 reqwest::Client::new()——一旦命中,说明有端点绕过了 Transport,必为不一致源头。检查命令:
    bash
    rg "reqwest::Client::new" crates/ --type rust -g '!openlark-core/**' -g '!openlark-webhook/**'
  • 白名单说明:openlark-webhook 是有意例外——自定义机器人不是飞书开放平台 API(目标 URL 为用户配置的绝对地址、用 URL 携带签名密钥鉴权、响应体为非标准 {code,msg}),不适用 Transport 的 /open-apis/ 基址与 token 注入,故保留独立 reqwest 路径(见 issue #214 调研结论,注释位于 crates/openlark-webhook/src/robot/v1/send.rs:13-26)。勿改 webhook 的 reqwest 用法。
  • 不得手工 Authorization 头 / get_app_token(token 由 Transport 自动注入)
  • Service/Request 不得持有 HTTP client 字段(只持 Config)

🟡 R 语义检查(防止双重嵌套陷阱):

  • ApiRequest<R> 的 R 应是响应 data 字段的内容类型,不是外层包装。
  • 可疑信号:某个 XxxResponse struct 带 data: Option<...> 字段、同时又作为 ApiRequest<XxxResponse> 的泛型——大概率双重嵌套(core 已把 R 当作 data 内容解析)。
  • 详细契约见 Skill(openlark-api) 的"🔒 核心契约"。
2) 端点定义规范
  • 是否使用 per-crate 类型安全端点枚举:每个 crate 在 src/common/api_endpoints.rs 定义各自的 <Domain>ApiV1 枚举,并实现 pub fn to_url(&self) -> String(注意 to_url() 返回的是相对路径 String,形如 /open-apis/mail/v1/...,不带基址)。
  • 是否避免手写业务 URL(统一走枚举 to_url())
  • 命名注意:枚举名是 <Domain>ApiV1,Domain 通常但并非总是等于 crate 名——以现况为准:
    • 与 crate 同名:MailApiV1(crates/openlark-mail/src/common/api_endpoints.rs:5)、DocsApiV1(crates/openlark-docs/src/common/api_endpoints.rs:440)、HelpdeskApiV1、AppApiV1(application)。
    • 与 crate 名不同:VcApiV1(meeting,crates/openlark-meeting/src/common/api_endpoints.rs:224)、TaskApiV1/BoardApiV1(workflow)、AdminApiV1(platform)、AuthenApiV1(auth)、HR 多枚举(AttendanceApiV1/HireApiV1/OkrApiV1/...)、Docs 多枚举(BitableApiV1/WikiApiV1/DocxApiV1/MinutesApiV1/...)。
  • 新增端点时改枚举与 to_url() match 分支,不要在 Request/Builder 里手写 URL 字面量。
3) 参数校验规范
  • 必填校验是否统一用 openlark_core::validate_required!
  • 字符串是否优先 trim() 后再校验
  • 列表字段是否校验非空与长度上限(如 validate_required_list!)

🟡 Token 类型与 Config 形态:

  • token 类型是否与接口文档「请求头 → Authorization」标注一致——ApiRequest 默认 [User, Tenant];仅当文档要求 app_access_token(→ App)等非默认凭证时才显式 .with_supported_access_token_types(...)。注意 App = app_access_token ≠ tenant_access_token(→ Tenant),不要把要求 tenant_access_token 的接口设成 App(详见 #511)。
  • Request/Service 是否用 owned Config(非 Arc<Config>)——新代码与重构以 owned 为准(openlark-docs 历史用 Arc 属例外)。

🟡 RequestOption(单数)vs RequestOptions(复数)切勿混用:

  • openlark_core::req_option::RequestOption(单数,crates/openlark-core/src/req_option.rs:7)——Transport/execute_with_options 实际接受的类型(token、tenant_key、file_upload/download 等运行时请求控制),业务 crate 调用 execute_with_options(RequestOption::default())。
  • openlark_client::types::client::RequestOptions(复数,crates/openlark-client/src/types/client.rs:180)——高级客户端的 timeout/retry_count/headers 构造参数,语义不同。
  • 二者字段集合完全不同,不得互相替代或导出混名;业务 crate 写 Builder 时用单数 RequestOption。
4) 命名与公开 API 表达
  • Client/Service/Resource/Request/Builder 命名是否语义清晰
  • 对外入口是否统一(避免同义入口并存)
  • meta 调用链命名是否与仓库约定一致
5) 导出与 feature gating
  • mod.rs 与 prelude 是否完整导出新增 API
  • Cargo.toml feature 与 #[cfg(feature = "...")] 是否对齐
  • 是否存在导出但不可编译或不可访问路径
Show full SKILL.md (210 more words)Show less
6) CI 与测试门控(#228 审核闭环)

详细背景见 docs/CI_TEST_TARGET_COVERAGE.md(相关 issue:#228 / #246 / #248 / #250 / #251;PR:#247 / #249 / #252 / #253 / #254)。

  • 测试/#[cfg(test)] 改动后必跑 just lint:just lint = cargo clippy --workspace --all-targets --all-features(justfile:12-14)。CI 在 all-features / no-default-features / 各 feature 组合 三个维度都用 --all-targets,因此 #[cfg(test)] 类 lint 回归(如 #248 的未用 use super::*)会被 CI 直接拦住,不只依赖本地。
  • tests/*.rs feature 门控约定(#251):文件引用 feature-gated 模块时,文件顶部加 #![cfg(feature = "...")];且 //! 模块文档必须在 #![cfg] 之上(顺序反了会触发 clippy missing_docs)。
  • examples/*.rs 禁用 #![cfg](#251):feature 门控走 Cargo.toml 的 [[example]] required-features。example 里写 #![cfg] 会把文件清空成无 main,报 E0601。
  • event 模块(openlark-communication)不违规:event 在 tools/api_priority.toml 标为 P2(非 P0 核心业务),按基础设施类对待(与 WebSocket LarkWsClient 同类),有意不经统一 client declare_client! re-export(#228 决策)。审查时勿把它当作「漏 re-export 的违规」上报。

输出模板(必须)

  1. 结论概览(3-6 条)
  2. 规则-证据对(至少 8 条)
    • 规则
    • 证据(path:line)
    • 风险等级(P0/P1/P2)
    • 修复建议
  3. 新 API 最小检查清单(5-8 条)
  4. 建议行动项(按优先级排序)

推荐执行顺序

  1. 先读 AGENTS.md 与目标 crate 的 AGENTS.md/CLAUDE.md
  2. 再扫规则高频证据:api_endpoints、execute_with_options、validate_required、prelude、mod.rs
  3. 最后输出规则-证据对与整改建议

重点提醒

  • 结论必须基于代码证据,不做“纯经验判断”
  • 证据至少精确到文件路径,推荐精确到 path:line
  • 不在规范检查中进行大规模重构,先给出可执行清单

与其他技能的关系

  • 需要审查整体架构与公共 API:openlark-design-review
  • 只聚焦校验写法统一:openlark-validation-style
  • 需要新增/重构具体 API:openlark-api
  • 需要做覆盖率统计:openlark-api-validation

技能分流决策表

场景优先技能何时转交
只想做一次项目规范体检(给出规则-证据对和风险清单)openlark-code-standards若发现架构级冲突/公共 API 设计分歧,转 openlark-design-review
重点是架构收敛、范式选型、兼容策略(含 breaking 评估)openlark-design-review若需要补充全仓规范一致性证据,可回补 openlark-code-standards
只处理 validate()、validate_required!、空白字符串与校验聚合openlark-validation-style若校验问题已扩展到命名/导出/端点体系,转 openlark-code-standards
新增或重构某个具体 API 文件(Request/Response/Builder/导出)openlark-api若实现前需先做规范体检,先跑 openlark-code-standards
关注 API 覆盖率、实现数量、缺失清单openlark-api-validation若覆盖率问题背后是设计不一致,转 openlark-design-review
快速判断
  • 问题是“这个项目现在规范是否一致” → openlark-code-standards
  • 问题是“这个设计该怎么收敛” → openlark-design-review
  • 问题是“这个校验写法到底怎么统一” → openlark-validation-style
  • 问题是“我现在就要实现某个 API” → openlark-api

关键词触发映射

用户关键词/表述建议技能
代码规范、规范检查、风格一致性、体检、对齐约定openlark-code-standards
架构设计、public API、收敛方案、feature gating、兼容策略、breaking changeopenlark-design-review
validate、必填校验、validate_required、空白字符串、校验聚合openlark-validation-style
新增 API、重构 API、Builder、Request/Response、mod.rs 导出openlark-api
覆盖率、实现数量、缺失 API、统计、对比 CSVopenlark-api-validation
组合关键词优先级
  • 同时出现“规范检查 + 覆盖率”时,先用 openlark-api-validation 产出缺失清单,再用 openlark-code-standards 做规范归因。
  • 同时出现“规范检查 + 架构收敛”时,先用 openlark-code-standards 做现状证据,再转 openlark-design-review 定迁移方案。
  • 同时出现“新增 API + 校验统一”时,实现阶段用 openlark-api,校验规则判定用 openlark-validation-style。

© 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

Just SKILL.md in .agents/skills/openlark-code-standards of foxzool/openlark.

Open the folder on GitHubat commit 6128d6d

Compare with similar skills

Openlark Code Standards 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 Code Standards compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openlark Code Standards this skillfoxzool/openlark106—~1.8kAutomated safety check: NotesApache-2.0
Feishu Multi Agenthyperlist/feishu-multi-agent273—~419Automated safety check: PassNone
Sync Specsnexu-io/nexu3.3k—~1.2kAutomated safety check: PassMIT
Autoresearch Feishu Three Tablebosprimigenious/autoresearch-skills151—~413Automated safety check: PassMIT
Aris InfraOpenLAIR/dr-claw1.2k—~1.4kAutomated safety check: NotesMIT
Incremental Implementationskuramatata/my-pi-agent114—~869Automated safety check: NotesNone

Similar skills

  • Feishu Multi Agent

    hyperlist/feishu-multi-agent

    飞书多 Agent 系统搭建指南。当用户要求创建新的功能 Agent、配置飞书群聊绑定、 搭建多 Agent 协作系统时激活此 skill。

    273 GitHub stars~419 tokensUpdated 7 mo ago
    Agent WorkflowsAuto-check passed
  • Sync Specs

    nexu-io/nexu

    A skill your agent uses when code changes may have made documentation outdated, when reviewing docs for consistency, or when the user asks to sync or audit documentation.

    3.3k GitHub stars~1.2k tokensUpdated 5 mo ago
    DevelopmentAuto-check passed
  • Autoresearch Feishu Three Table

    bosprimigenious/autoresearch-skills

    在已获授权的飞书/Lark 多维表格中处理 AutoResearch 的领题、完成提交/验收和组长初检三表流转,核对当期题号、字段权限、证据和写后回读。用于领取题目、提交验收材料或回填初检结论;不用于绕过组织权限、恢复离职账号或替代任务 QA。

    151 GitHub stars~413 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Aris Infra

    OpenLAIR/dr-claw

    ARIS (Auto-claude-code-research-in-sleep) infrastructure setup and configuration.

    1.2k GitHub stars~1.4k tokensUpdated 20 days ago
    Agent WorkflowsAuto-check: notes
  • Incremental Implementation

    skuramatata/my-pi-agent

    A skill your agent uses when implementing my-pi-agent changes that touch multiple files, shared runtime behavior, prompt/skill logic, Feishu channel flow, verifier behavior, or coding workflow lanes.

    114 GitHub stars~869 tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check: notes
  • Feishu Bridge

    AlexAnys/feishu-openclaw

    Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection.

    317 GitHub starsUsed in 1 repo~615 tokens
    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 5 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 5 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 5 days ago
    Auto-check: notes
  • Openlark Design Review

    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…

    106 GitHub stars~2.1k tokensUpdated 5 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 5 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 5 days ago
    Auto-check: notes

Works with

Questions about Openlark Code Standards

What does Openlark Code Standards do?

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…. Openlark Code Standards is an agent skill from foxzool/openlark.

When should I use Openlark Code Standards?

Openlark Code Standards fits situations like: tasks that involve Agent instruction files; tasks that involve Messaging and chat bots.

How do I install Openlark Code Standards in Claude Code?

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

How do I install Openlark Code Standards in Codex?

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

Can I use Openlark Code Standards 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-code-standards -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-code-standards, .gemini/skills/openlark-code-standards, .github/skills/openlark-code-standards and .opencode/skills/openlark-code-standards in your project.

What does Openlark Code Standards need to run?

Going by SKILL.md and its folder, Openlark Code Standards needs the command-line tools its instructions call (just, rg and cargo). Its frontmatter pre-approves these tools: Read, Grep, Glob, Bash.

Does Openlark Code Standards 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 Code Standards 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 Code Standards use?

Openlark Code Standards 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 Code Standards use?

About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openlark Code Standards?

Skills that share tags, products or a category with Openlark Code Standards: Feishu Multi Agent (hyperlist/feishu-multi-agent, 273 stars), Sync Specs (nexu-io/nexu, 3.3k stars), Autoresearch Feishu Three Table (bosprimigenious/autoresearch-skills, 151 stars) and Aris Infra (OpenLAIR/dr-claw, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openlark Code Standards?

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 3, 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.