AC recursive-swarm
Bounded recursive orchestration for complex tasks that are too large for one agent turn but cleanly decompose into a few independent subproblems. Use for multi-angle research, audits, mixed research+synthesis, or coding projects that benefit from explicit planning, task-tree state, artifact folders, and controlled parallel execution. Keep recursion tight: default max depth 2, hard cap 3, preferred fan-out 2-4, and modest concurrency. Use git worktrees only for coding leaves inside git repos. Do not use for simple one-shot tasks, destructive workflows, or open-ended exploration.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 13. 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
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 85Steps. 104 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1843 tokens
- 100Progress reporting. Reports progress
- 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
- +3Output format is not stated: the model decides each time
- -31 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 584: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 104 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.