CB feishu
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app open. Use when the user mentions 飞书, Lark, a 群, a 日程 or a 飞书文档, or wants a colleague told something.
Promises CLI control over Lark: calendar, contacts, messages, events, tasks, documents—all without opening the app. Useful if your agent needs to message a colleague or fetch data from 飞书.
Quality score sits at 69/100, process at 65. No critical issues found, single file, compact structure. Never ran on actual models, no sandbox testing. Supports many platforms: Claude, Cursor, DeepSeek, Qwen, and others.
Install if Lark is part of your workflow and you need integration. Caveat: no real model testing means behavior on complex queries is a guess. Should handle basic operations fine.
The user's 飞书 / Lark through its command-line tool (lark-cli): agenda, people and groups, reading and sending messages, events, tasks, documents, with no app…
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: The user's 飞书 / Lark through its command-line tool (lark-cli): age… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - note
frontmatter-keyunknown frontmatter key "channel"
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 14 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1048 tokens
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 258: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 14 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.