CC heartbeat
Ambient fleet-health check that surfaces anything worth attention (default), or an on-demand priority brief - the 3 things to focus on, why now, and what moved (var=brief)
Ambient fleet-health check that surfaces anything worth attention (default), or an on-demand priority brief - the 3 things to focus on, why now, and what…
As a process C 61/100 · Has gaps — References files that are not bundled: /memory/
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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.
- The text references files that are not there: add them or drop the references.
- 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
-
medium Exfiltration
net-credential-useSKILL.md:312Credential used in a network call (verify the destination is the intended service)Applies to both branches. `curl` works — there is no network sandbox. Use **WebFetch** as a fallback for a flaky public GET. For GitHub queries (both branches use `gh pr list` / `gh issue list`), use
Files scanned: 1. 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 ≈ 5534 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: /memory/ - note
frontmatter-keyunknown frontmatter key "scorable"
Process rating: all ten parameters 61/100
- 0Tools and files. 1 referenced file(s) missing: /memory/
- 30Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5534 tokens
- 100Steps. 72 steps
- 100Failures and branches. 6 branches, has a failure section
- 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
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)
- -226 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 171: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.