BC model-committee
Runs a deliberative two-model committee with GPT-6 Astra and Claude Opus under a selectable chair. Fable is the default chair. `/model-committee-astra` selects Astra with a Sol member, `/model-committee-opus` selects Opus, and `/model-committee-sol` retains the Sol chair with a Terra member. Use when a consequential decision has several defensible options and model families should independently propose, critique, revise, and cross-rank against a predeclared rubric before convergence. Fits architecture, research design, interpretation, manuscript strategy, ambiguous diagnosis, evaluation design, plan reconciliation, and policy or standards tradeoffs. Excludes factual lookups, independent-coder reliability, brainstorming, routine implementation, and final professional judgment.
Runs a deliberative two-model committee with GPT-6 Astra and Claude Opus under a selectable chair.
As a process C 56/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- 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: Read Write Edit Bash AskUserQuestion
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 55Failures and branches. 1 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 20 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2624 tokens
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 786: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.