Lark
Lark and Feishu operations using lark-cli. Use for Lark, Feishu, or lark-cli tasks.
Install
$ agentstack add skill-andthezhang-lark-simple-skill-lark ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-andthezhang-lark-simple-skill-lark) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Lark / Feishu
Use this as the single entry point for Lark/Feishu work.
Setup
When the user invokes $lark setup, /lark setup, or otherwise asks to set up, consolidate, refresh, or update this skill:
- Resolve this skill's directory as the directory containing this
SKILL.md. - Run
node /scripts/setup.js. - Report the moved skill count, generated metadata count, and any error. Do not
continue past a failed setup.
The script moves sibling top-level lark-* skills into this skill's skills/ directory. It preserves the unified lark skill and unrelated skills. It also removes stale top-level lark-* entries from the Vercel Skills lockfile while preserving the lark entry.
After moving them, setup renames every nested SKILL.md to GUIDE.md and updates links between those guides. This keeps the domain instructions available without exposing them as separately discoverable skills.
Every setup run rebuilds the generated metadata section below from the actual nested lark-*/GUIDE.md frontmatter, even if there are no new skills to move. After a successful lark-cli update, run setup again because the updater may recreate top-level skills or change their descriptions.
Route a Lark request
- If
skills/lark-shared/GUIDE.mdis missing or the metadata section is still
a placeholder, run setup first.
- Read
skills/lark-shared/GUIDE.mdcompletely before usinglark-cli. - Match the request against the metadata map below and read the complete
GUIDE.md for the smallest relevant domain. Read every referenced file that domain marks as required.
- Use multiple domain skills only when the request genuinely crosses domains.
- If nothing matches or the CLI lacks the required operation, read
skills/lark-openapi-explorer/GUIDE.md.
Do not guess commands, parameters, identity, or permissions. Follow the nested skill's instructions and use lark-cli --help, domain help, and lark-cli schema when required.
Domain metadata map
Setup replaces the marked placeholder with a YAML map copied from the nested skill frontmatter. Do not manually edit the generated section.
Run $lark setup or /lark setup to generate this map.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: andthezhang
- Source: andthezhang/lark-simple-skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.