BC caspian
Give an AI agent real communication channels — Slack, Discord, Telegram, email, X, SMS — behind one on_message handler via caspian-sdk. Free channels need no signup; the skill mints a sandbox API key itself.
Give an AI agent real communication channels — Slack, Discord, Telegram, email, X, SMS — behind one onmessage handler via caspian-sdk.
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Exfiltration
net-credential-useSKILL.md:94Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -X PUT https://api.trycaspianai.com/v1/billing/autopay -H "Authorization: Bearer $CASPIAN_API_KEY" \
security skill -
low Exfiltration
net-credential-useSKILL.md:173Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s -X POST https://api.trycaspianai.com/v1/test-emails -H "Authorization: Bearer $CASPIAN_API_KEY" \
security skill -
low Exfiltration
net-credential-useSKILL.md:181Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)curl -s "https://api.trycaspianai.com/v1/events?type=…" -H "Authorization: Bearer $CASPIAN_API_KEY"
security skill
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 6369 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6369 tokens
- 100Steps. 34 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (8 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
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 207: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 34 items
- +4Has examples (16 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.