AC multi-agent-team
Spawn and orchestrate multiple coordinated AI sub-agents to work in parallel on a single complex task. Use when: (1) a task is too large for one agent and should be decomposed into parallel subtasks, (2) you need multiple specialized agents researcher coder reviewer etc working together, (3) running agent councils or debates for decision-making, (4) parallel web research data processing or content generation across multiple workers, (5) any multi-agent orchestration pattern one-shot teams persistent squads or hierarchical agent trees. Triggers on phrases like spin up agents, spawn a team, parallel agents, agent council, multi-agent, coordinated agents.
As a process C 51/100 · 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: 3. 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 51/100
- 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
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (multi-agent-team) differs from the folder (fuzzy-multi-agent-team)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 12 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1272 tokens
- 100Running it twice. No mutating operations
- 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
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 660: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.