AC zoom-meeting-admin
List, create, delete, and query Zoom meetings, cloud recordings, and account users via a fixed CLI (scripts/zoom-s2s.py, 7 whitelisted actions) using Server-to-Server OAuth. Use when the user asks to schedule, reschedule, cancel, find, or look up a Zoom meeting; set up a recurring Zoom; pull cloud recordings or past meeting metadata; or look up account users. Triggers on phrases like "Zoom meeting", "zoom 会议", "约 Zoom", "取消 Zoom", "录像", "schedule a Zoom", "cancel the meeting", "who's on the call", "云录制". create_meeting requires explicit confirmation of topic, start_time, duration; delete_meeting requires --yes and visible confirmation. Agent must only invoke the 7 whitelisted CLI actions and must not modify the script, import internals, or call Zoom REST directly. Requires .env with ACCOUNT_ID/CLIENT_ID/CLIENT_SECRET/USER_ID. Documentation is in Chinese; outputs follow.
List, create, delete, and query Zoom meetings, cloud recordings, and account users via a fixed CLI (scripts/zoom-s2s.py, 7 whitelisted actions) using…
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 40 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2275 tokens
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 882: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 40 items
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.