BC google-analytics
Google Analytics API integration with managed OAuth. This skill includes two separate APIs: the Admin API (write-capable — can create, update, and delete accounts, properties, and data streams) and the Data API (read-only — runs reports on sessions, users, page views, and conversions). Prefer the Data API connection for reporting-only tasks. Use the Admin API only when administrative changes are explicitly needed. All Admin API write operations require explicit user approval with specific resource identifiers before execution. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. The endpoints documented here are the intended surface, not a technical limit — the `maton api` passthrough can reach others the connection permits. Default to read and list calls, and confirm every write or new connection with the user.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
medium Obfuscation
obf-base64-blobskill-card.md:51Long base64-looking blob- [Realtime Report](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/runRealtimeReport)
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Grep Glob
-
medium Obfuscation
obf-base64-blobSKILL.md:552Long base64-looking blob- [Realtime Report](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/runRealtimeReport)
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5954 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 40 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5954 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 69 steps
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 20 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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)
- +3Description length 992: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 53 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (41 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.