AC google-drive-skill
Use when the user wants to interact with a public Google Drive — listing, reading, creating, updating, or deleting files and folders. Handles both read-only access (API key only) and write access (service account or OAuth2). Covers folder navigation, file upload/download, permissions, MIME types, and error handling. USE FOR: integrating Google Drive into scripts or applications; reading publicly shared files; CRUD on service-account-owned drives; automating Drive folder structures. DO NOT USE FOR: Google Workspace Admin tasks; Google Docs/Sheets API-specific operations beyond Drive metadata.
As a process C 56/100 · Has gaps — 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Secrets in code
secret-private-keyassets/service_account_template.json:5Private key material (placeholder value)"private_key": "-----BEGIN PRIVATE KEY----- …\n",
placeholder
Files scanned: 14. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 85Steps. 20 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3357 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 598: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (27 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 8 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.