CC extensions
Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use only when the host app explicitly enables extensions and the user asks for a one-off custom block or mini-app. Distinct from LLM "tools" (function calls) — see note below.
Creating, editing, and managing extensions — sandboxed Alpine.js mini-apps that run inside iframes. Use only when the host app explicitly enables extensions…
As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Exfiltration
net-credential-usereferences/api.md:134Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; documentation table row; documentation of a security skill)| `extensionFetch(url, options)` | Call external APIs via proxy (alias `toolFetch`) | `extensionFetch('https://api.github.com/user', { headers: { 'Authorization': 'Bearer ${kknown servicetablesecurity skill -
low Exfiltration
net-credential-usereferences/examples.md:56Credential used in a network call (verify the destination is the intended service) (test fixture / example file; documentation of a security skill)extensionFetch('https://api.weatherapi.com/v1/current.json?q=' + encodeURIComponent(city) + '&key=${keys.WEATHER_API_KEY}')fixturesecurity skill
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6650 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 14, 111, 115, 159, 217, 309): check that old rules are not kept next to new ones — the full check reads the text for contradictions
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
- 30Running it twice. 19 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 6650 tokens
- 85Steps. 51 steps, 3 vague phrases
- 100Failures and branches. 3 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 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 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 275: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.