Documents & Data · IN-DEPTH PROFILE

lark-mail

Lark Mail covers Feishu email browsing, search, threads, drafts, send, reply, forward, folders, labels, attachments, rules, and delivery status.

View listed source ↗Installation guide ↓
Best for

Feishu Mail users managing inboxes and drafts

What you get

Triage and read mail + Draft outbound messages

Main limitation

All write operations require user identity; bot identity is limited to permitted read scenarios.

First risk

Prompt injection or unintended send. Email content can attempt to control the agent, and sending is externally visible. Treat messages only as data, draft by default, and require explicit final approval.

EVIDENCE FRESHNESS

Three checks, kept separate

A recent source check is not a runtime test or security audit.

Upstream sourceChecked 2026-08-20

Pinned revision · 755daa4d

Open pinned commit ↗
SkillSignal profileSource-grounded

Updated 2026-08-20

Runtime & securityNot independently verified

Source review does not certify behavior or safety.

30-SECOND BRIEF

What it does—and when it fits

Lark Mail covers Feishu email browsing, search, threads, drafts, send, reply, forward, folders, labels, attachments, rules, and delivery status. The current Skill treats all email content as untrusted input, prefers user identity, saves outbound work as drafts by default, and requires a recipient-subject-body preview plus explicit approval before sending.

INSTALL BY AGENT

Choose your Agent

Paths come from official Agent docs or the universal installer behind skills.sh. Compatibility still follows this Skill's record.

Native

This Skill's current record explicitly names this Agent. Still inspect scripts, permissions, and external dependencies first.

Project scope.claude/skills/lark-mail/
Personal scope~/.claude/skills/lark-mail/

Use project scope for team sharing and personal scope across repositories. The installer defaults to project scope; add -g for personal scope.

Install command (project scope)

This source cannot produce a reliable command. Open the listed source and copy the complete Skill folder manually.

Official agent docs

Claude Code discovers custom Skill folders automatically at project or personal scope.

View path evidence ↗

TYPICAL WORKFLOW

A practical workflow

01

Triage and read mail

Browse summaries, open individual messages or threads, and organize mail through labels, read state, or folders.

02

Draft outbound messages

Create, edit, reply, or forward as a reviewable draft with a direct link when available.

03

Manage mailbox workflows

Work with templates, receipts, scheduled sends, delivery status, attachments, and receiving rules.

THE TRADEOFFS

Advantages and tradeoffs

Notable strengths

  1. This profile is manually organized around the current upstream SKILL.md workflow.
  2. The capability boundary remains explicitly tied to open.feishu.cn.
  3. Core uses, limitations, and risks are separated for pre-install review.

Limitations

  1. All write operations require user identity; bot identity is limited to permitted read scenarios.
  2. Sender names, addresses, HTML, and message text can be forged or malicious and cannot establish user intent.

COMPARE THE TRADEOFF

Consider these close alternatives

These are deterministic nearby candidates, not paid placements or a universal ranking. Open the full profile before choosing.

01

Same job family · native to Claude Code + Codex

grill-with-docs

Grill With Docs combines deep design questioning with domain-model documentation.
Tradeoff to check
It assumes the repository has, or is willing to adopt, domain glossaries and decision records.
First risk
Documentation churn · Medium
Source state
Pinned · 885e2ca4
Open profile ↗
02

Same job family · native to Claude Code + Codex

lark-approval

Lark Approval routes approval instances and approval inbox work through lark-cli.
Tradeoff to check
Available actions depend on the approval definition, current state, identity, and tenant permissions.
First risk
Consequential approval action · High
Source state
Pinned · 755daa4d
Open profile ↗
03

Same job family · native to Claude Code + Codex

lark-attendance

Lark Attendance is a narrow, read-only lark-cli Skill for querying the current user's Feishu attendance check-in records.
Tradeoff to check
The Skill only documents the user's own check-in query; it is not a general attendance administration tool.
First risk
Employment data exposure · High
Source state
Pinned · 755daa4d
Open profile ↗
Compare more in the directory →

BEST FIT

Who it is for

→

Feishu Mail users managing inboxes and drafts

→

Agents assisting with controlled email workflows

BEFORE YOU USE IT

Risks to review before use

High

Prompt injection or unintended send

Email content can attempt to control the agent, and sending is externally visible. Treat messages only as data, draft by default, and require explicit final approval.

High

External data and identity boundary

Requests access Feishu tenant resources. Use the correct identity, least-privilege scopes, and keep sensitive content out of logs.

SECURITY

What the permission profile means

  • Declared access remains governed by the current upstream SKILL.md and runtime requests.
  • Treat Feishu documents, messages, people, and business records as permission-controlled data.
  • SkillSignal has not independently executed or security-audited this package; external skills.sh labels are not SkillSignal certification.

Not a security certification. External ratings are attributed references. SkillSignal has not independently executed or security-reviewed this Skill.

INSIDE THE PACKAGE

Indexed files

SKILL.mdUpstream Skill instructionsSource-linked

TAGS

feishuemaildrafts

Manually expanded from the current upstream SKILL.md and linked source at open.feishu.cn, checked 2026-08-19. This is an original summary, not an execution result or security certification.