AC agent-collaboration-control
Establish, actively monitor, and operate project-agnostic collaboration control for multi-agent programmes, research campaigns, live experiments, long-running automation, consequential artifact production, incident recovery, evidence promotion, and cross-agent handoffs. Use when work needs ongoing agent support, a recurring independent watch, proactive anomaly or ambiguity reporting, explicit human authority, one writer per mutable surface, risk-scaled Agent Orchestra topology, transition journals, liveness proof, adversarial review, provenance, succession rules, or calibrated claim states across any project.
Establish, actively monitor, and operate project-agnostic collaboration control for multi-agent programmes, research campaigns, live experiments, long-running…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 0
✓ No critical or high findings
Files scanned: 11. 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 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 53 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2556 tokens
- 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 10 top-level sections: this looks like several domains in one skill
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
- +2Single-language instructions
- +3Description length 616: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.