BB dcc-mcp
Default DCC-MCP router for 37 released creative products and 1 current application routes. Use for a named supported app or explicit DCC-MCP request. Controls live apps, writes files, contacts gateways, and can install a CLI with setup authorization. Use typed DCC-MCP tools first. For application UI, including browsers and non-DCC apps, DCC-CUA and ui-control name the same project-owned route and explicit DCC-CUA requests never fall back to generic Computer Use providers.
Default DCC-MCP router for 37 released creative products and 1 current application routes.
As a process B 69/100 · Nearly there — weak spots: result and completion, when it triggers
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write Edit
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7266 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7266 tokens
- 85Steps. 21 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 2 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
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (13 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
- -31 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 476: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.