BC chatart-skill
Use when user wants to generate videos, create images from text prompts, edit existing images with AI, or replace characters in videos. Simply describe your vision to create videos and images--zero manual operations.
Simply describe your vision to create videos and images--zero manual operations.
As a process C 61/100 · Has gaps — weak spots: result and completion, execution cost, 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 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Broad scope
meta-agent-memory-dumpreferences/user.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensreferences/user.md
-
low Secrets in code
secret-password-literalscripts/auth.py:201Hard-coded password / key literal (may be an example)api_key = api_keys[0] if api_keys else "(none)"
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8767 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "agent_created"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 8 mutating operations with no state check
- 40Execution cost. Instruction body is 8767 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 124 steps, 2 vague phrases
- 100Failures and branches. 4 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 The response is described with custom markup (22 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
- -231 emoji in the instructions: noise for the model
- -31 of 6 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 216: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 124 items
- +4Has examples (29 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.