CD api-gateway
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to interact with external services. Security: The MATON_API_KEY authenticates with Maton.ai but grants NO access to third-party services by itself. Each service requires explicit OAuth authorization by the user through Maton's connect flow. Access is strictly scoped to connections the user has authorized. Provided by Maton (https://maton.ai).
Connect to 100+ APIs (Google Workspace, Microsoft 365, GitHub, Notion, Slack, Airtable, HubSpot, etc.) with managed OAuth. Use this skill when users want to…
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 7 more places: ClawHub, ClawHub, ClawHub, ClawHub, ClawHub, ClawHub, ClawHub
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Obfuscation
obf-base64-blobreferences/google-analytics-data/README.md:149Long base64-looking blob (documentation of a security skill)- [Run Realtime Report](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/runRealtimeReport)
security skill -
low Obfuscation
obf-base64-blobreferences/google-analytics-data/README.md:150Long base64-looking blob (documentation of a security skill)- [Batch Run Reports](https://developers.google.com/analytics/devguides/reporting/data/v1/rest/v1beta/properties/batchRunReports)
security skill
Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10535 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 48/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 28 mutating operations with no state check
- 40Execution cost. Instruction body is 10535 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 85Steps. 173 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- low 13 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 498: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 173 items
- +4Has examples (23 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.