Agent skill

Lark Approval

飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

AGPL-3.0Auto-check passedProductivity & Automation

Install Lark Approval

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a claude-code

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

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval --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/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .claude/skills/lark-approval && 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/

Paste into Claude Code

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .claude/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .agents/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .agents/skills/lark-approval && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .agents/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .cursor/skills/lark-approval && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .cursor/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/rongxinzy/RongxinAI.git --path MCPs/feishu/skills/lark-approval

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .gemini/skills/lark-approval && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .gemini/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .github/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .github/skills/lark-approval && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .github/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rongxinzy/RongxinAI --skill lark-approval -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install rongxinzy/RongxinAI lark-approval --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rongxinzy/RongxinAI.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/MCPs/feishu/skills/lark-approval .opencode/skills/lark-approval && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "lark-approval" agent skill from https://github.com/rongxinzy/RongxinAI/tree/main/MCPs/feishu/skills/lark-approval into .opencode/skills/lark-approval/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lark-approval", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: lark-approval
GitHub stars: 154
Used in: 3 other repos
Token cost: ~1.1k tokens
SKILL.md length: 213 words
Files: 17 (incl. references)
Skills in repo: 94
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Works in 3 steps: 先拿最小必要信息，再执行 → 已知对象时直达动作 → 错误码驱动，而不是盲目重试
Tasks that involve Messaging and chat bots
SKILL.md covers 路由优先级（先判断是不是审批，再选命令）, 选哪个命令, 执行原则（减少误路由、误重试和无效消耗） and 写操作失败处理：1395001 决策树, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Lark Approval is an agent skill from rongxinzy/RongxinAI. 飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including reference files (for example `references/lark-approval-approvals-get.md`, `references/lark-approval-approvals-search.md` and `references/lark-approval-initiate.md`).

It sits in Productivity & Automation, covering Messaging and chat bots. The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is AGPL-3.0.

When your agent uses it

Tasks that involve Messaging and chat bots

Example prompts

“/lark-approval”

Workflow steps

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

先拿最小必要信息，再执行
已知对象时直达动作
错误码驱动，而不是盲目重试

What it can do on your machine

Read from SKILL.md and the folder at commit 9c64865. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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

Lark Approval loads about 1.1k tokens when it runs, and up to ~27k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 213 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~36
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~27k

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 passed

The automated check found no risky patterns in SKILL.md.

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 rongxinzy/RongxinAI at commit 9c64865, republished under its AGPL-3.0 licence (© rongxinzy). 213 words, ~1,135 tokens.

Download SKILL.mdSave it as .claude/skills/lark-approval/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.

name: lark-approval
description: 飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。
version: 1.2.0
metadata.cliHelp: lark-cli approval --help

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md，其中包含认证、权限处理

所有命令默认 --as user（审批是人的动作）。调用前先按需读取 references 下对应的文件，查参数结构，不要猜字段；references 是第一信息源，只有在 reference 未覆盖的原生 / 高级场景下，才额外用 lark-cli ... --help、lark-cli schema 等方式补充确认字段。

路由优先级（先判断是不是审批，再选命令）

审批待办不是飞书任务。只要用户的核心对象是审批单据 / 审批待办 / 审批实例，就优先使用 lark-approval，不要让渡给 lark-task。

明确归 `lark-approval` 的高优先级语义

出现以下任一语义时，优先走 lark-approval：

审批待办 / 审批单据 / 审批实例 / 审批意见 / 审批定义
同意 / 拒绝 / 转交 / 退回 / 撤回 / 催办 / 加签 / 抄送
待办列表 / 待办单据 / 已发起审批 / 已办审批 / 审批详情 / 同意可编辑

判定规则： 只要最终动作是对审批单据做同意、拒绝、转交、退回、撤回、催办、加签、抄送、查详情、查已发起/已办/待办，就归 lark-approval。只有当用户处理的是非审批类任务/待办时，才走 lark-task。

选哪个命令

想做什么	命令	按需读取 reference
搜可发起定义	`approvals search`	`lark-approval-approvals-search.md`
看审批定义详情/提单前确认表单与流程	`approvals get`	`lark-approval-approvals-get.md`
发起原生审批实例/提交请假审批/提交报销审批/创建审批实例	`instances create`	`lark-approval-initiate.md`
查待办/已办	`tasks query`（`topic`：1待办 2已办 17未读 18已读）	`lark-approval-tasks-query.md`
看表单/进度/当前节点	`instances get`	`lark-approval-instances-get.md`
同意审批	`tasks approve`	`lark-approval-tasks-approve.md`
拒绝审批	`tasks reject`	`lark-approval-tasks-reject.md`
转交审批	`tasks transfer`	`lark-approval-tasks-transfer.md`
加签审批	`tasks add_sign`	`lark-approval-tasks-add-sign.md`
退回审批	`tasks rollback`	`lark-approval-tasks-rollback.md`
催办审批	`tasks remind`	`lark-approval-tasks-remind.md`
撤回已发起审批	`instances cancel`	`lark-approval-instances-cancel.md`
给审批实例追加抄送	`instances cc`	`lark-approval-instances-cc.md`
按定义查已发起审批	`instances initiated`	`lark-approval-instances-initiated.md`

处理链：

发起审批：approvals search -> approvals get -> instances create
处理审批：tasks query 拿 instance_code + task_id（操作必须成对带上）→ 只有用户明确需要查看详情、当前节点、表单内容、或流程进度时，再 instances get → 执行操作

执行原则（减少误路由、误重试和无效消耗）

1) 先拿最小必要信息，再执行

目标只是处理待办时，优先 tasks query 获取 instance_code + task_id
只有用户明确要看详情、当前节点、表单内容、流程进度时，才调用 instances get
用户已经明确给出 instance_code / task_id 时，不要先查列表再过滤

2) 已知对象时直达动作

已拿到 instance_code + task_id 后，优先直接执行 tasks approve/reject/transfer/add_sign/rollback/remind
同一轮里如果已有足够的新鲜查询结果，不要重复 tasks query
不要默认走 list -> filter -> detail -> write 全链路；对象已明确时应压缩步骤

3) 错误码驱动，而不是盲目重试

写操作失败后，先看错误码和报错语义，再决定是否补查或结束
除非错误明确提示可恢复或需要补充参数，否则不要重复刷同一个写操作
同一个失败原因不要连续多次重试，避免 token 和耗时失控，最多重试1次

写操作失败处理：1395001 决策树

当拒绝 / 转交 / 退回 / 撤回 / 同意等写操作返回 1395001（任务状态异常 / 写前置校验失败）时，按下面规则处理：

先停止盲目重试，不要连续重复提交相同写操作，最多重试1次
优先从以下角度解释：
- 任务可能已被他人处理
- 单据状态已变化，当前动作已不再允许
- 当前用户已不具备该任务的操作资格
- 当前节点或单据状态不支持该操作
如需确认，只补一次状态查询（tasks query 或 instances get），不要陷入 query/write 循环
最终给用户明确结论和下一步建议，而不是继续无意义重试

特别注意： 对拒绝 / 转交 / 撤回场景更要严格执行上述规则；这些场景最容易因状态切换而失败。

bash

lark-cli approval approvals search --data '{"keyword":"请假"}' --as user
lark-cli approval approvals get --params '{"approval_code":"<code>"}' --as user
lark-cli approval instances create --data '{"approval_code":"<code>","form":"[...]"}' --yes --as user
lark-cli approval tasks query --params '{"topic":"1"}' --as user
lark-cli approval tasks approve --data '{"instance_code":"<ic>","task_id":"<tid>","comment":"同意"}' --as user

不在本 skill 范围

创建审批定义（走飞书客户端或审批管理后台）；三方定义发起（返回 create_link，引导用户通过链接发起）；非审批类待办 → lark-task

Files

SKILL.md and 16 other files (references) in MCPs/feishu/skills/lark-approval of rongxinzy/RongxinAI.

SKILL.md
references/lark-approval-approvals-get.md
references/lark-approval-approvals-search.md
references/lark-approval-initiate.md
references/lark-approval-instance-form-control-parameters.md
references/lark-approval-instance-value-sourcing.md
references/lark-approval-instances-cancel.md
references/lark-approval-instances-cc.md
references/lark-approval-instances-get.md
references/lark-approval-instances-initiated.md
references/lark-approval-tasks-add-sign.md
references/lark-approval-tasks-approve.md
references/lark-approval-tasks-query.md
references/lark-approval-tasks-reject.md
references/lark-approval-tasks-remind.md
references/lark-approval-tasks-rollback.md
references/lark-approval-tasks-transfer.md

Open the folder on GitHubat commit 9c64865

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in rongxinzy/RongxinAI, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Lark Approval 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.

Lark Approval compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Lark Approval this skillrongxinzy/RongxinAI	154	3 repos	~1.1k	Automated safety check: Pass	AGPL-3.0	yesterday
Feishu Docopenclaw/openclaw	392k	—	~516	Automated safety check: Pass	MIT	today
She Love Me863401402/she-love-me	931	1 repos	~1.3k	Automated safety check: Pass	MIT	9 days ago
Feishu Docraucvr/Group-Goki	112	3 repos	~592	Automated safety check: Pass	MIT	4 mo ago
Wechat Article Extractorfreestylefly/wechat-article-extractor-skill	136	1 repos	~1k	Automated safety check: Pass	None	7 mo ago
Wechat Miniprogram Builderchenjin-cmd/wechat-miniprogram-builder	356	—	~634	Automated safety check: Pass	MIT	2 mo ago

Similar skills

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
She Love Me
863401402/she-love-me
Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…
931 GitHub starsUsed in 1 repo~1.3k tokens
Productivity & AutomationAuto-check passed
Feishu Doc
raucvr/Group-Goki
Feishu document read/write operations. An agent skill from raucvr/Group-Goki.
112 GitHub starsUsed in 3 repos~592 tokens
Productivity & AutomationAuto-check passed
Wechat Article Extractor
freestylefly/wechat-article-extractor-skill
Extract metadata and content from WeChat Official Account articles.
136 GitHub starsUsed in 1 repo~1k tokens
Productivity & AutomationAuto-check passed
Wechat Miniprogram Builder
chenjin-cmd/wechat-miniprogram-builder
This skill should be used when the user wants to build, launch, monetize, or promote a WeChat mini-program with AI (vibe coding) — including topic selection, account registration & ICP filing…
356 GitHub stars~634 tokensUpdated 2 mo ago
Productivity & AutomationAuto-check passed
Slack
huangruiteng/CS-Notes
A skill your agent uses when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
4k GitHub starsUsed in 10 repos~578 tokens
Productivity & AutomationAuto-check passed

Questions about Lark Approval

What does Lark Approval do?

飞书审批：查询和处理审批待办/已办/实例，搜索可发起审批定义、查看定义详情并发起原生审批实例。当用户要处理审批任务、查看审批实例、搜索或发起审批时使用。审批待办不是飞书任务；非审批类待办走 lark-task。不负责创建审批定义；三方审批定义不走原生提单。. Lark Approval is an agent skill from rongxinzy/RongxinAI.

When should I use Lark Approval?

Lark Approval fits situations like: tasks that involve Messaging and chat bots.

How do I install Lark Approval in Claude Code?

Run `npx skills add rongxinzy/RongxinAI --skill lark-approval -a claude-code`. Or copy the skill folder (MCPs/feishu/skills/lark-approval in rongxinzy/RongxinAI) into .claude/skills/lark-approval in your project. Claude Code loads it when a task matches its description.

How do I install Lark Approval in Codex?

Run `npx skills add rongxinzy/RongxinAI --skill lark-approval -a codex`. Or copy the skill folder (MCPs/feishu/skills/lark-approval in rongxinzy/RongxinAI) into .agents/skills/lark-approval in your project. Codex loads it when a task matches its description.

Can I use Lark Approval 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 rongxinzy/RongxinAI --skill lark-approval -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lark-approval, .gemini/skills/lark-approval, .github/skills/lark-approval and .opencode/skills/lark-approval in your project.

What does Lark Approval need to run?

SKILL.md names no scripts, command-line tools or credentials: Lark Approval is instructions for the agent only.

Does Lark Approval 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 Lark Approval safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Lark Approval use?

Lark Approval is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lark Approval use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 26k tokens, read only when the agent opens those files.

What are the alternatives to Lark Approval?

Skills that share tags, products or a category with Lark Approval: Feishu Doc (openclaw/openclaw, 392k stars), She Love Me (863401402/she-love-me, 931 stars), Feishu Doc (raucvr/Group-Goki, 112 stars) and Wechat Article Extractor (freestylefly/wechat-article-extractor-skill, 136 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lark Approval?

rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.

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

Install Lark Approval

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

路由优先级（先判断是不是审批，再选命令）

明确归 lark-approval 的高优先级语义

选哪个命令

执行原则（减少误路由、误重试和无效消耗）

1) 先拿最小必要信息，再执行

2) 已知对象时直达动作

3) 错误码驱动，而不是盲目重试

写操作失败处理：1395001 决策树

不在本 skill 范围

Files

Used in 3 other repositories

Compare with similar skills

Similar skills

More from rongxinzy/RongxinAI

Related

Questions about Lark Approval

明确归 `lark-approval` 的高优先级语义