AF dunbars-number
Activate when: team headcount is approaching or crossing 150 (or 50, or 500); someone says "coordination is getting harder," "we lost the startup feel," or "we don't know who does what anymore"; deciding whether to split a team, open a new office, or add a management layer. Do NOT activate when: group is well below 50 and problems are clearly interpersonal; core issue is incentive misalignment rather than group size (use principal-agent instead). More: deciqai.com/c/dunbars-number
Activate when: team headcount is approaching or crossing 150 (or 50, or 500); someone says "coordination is getting harder," "we lost the startup feel," or…
As a process F 45/100 · Will not run — References files that are not bundled: examples/dunbar-1992-wl-gore-associates.md, examples/ai-native-startup-scaling-2023-2026.md, references/sources.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/dunbar-1992-wl-gore-associates.md - warning
missing-refreference to a missing file: examples/ai-native-startup-scaling-2023-2026.md - warning
missing-refreference to a missing file: references/sources.md
Process rating: all ten parameters 45/100
- 0Tools and files. 3 referenced file(s) missing: examples/dunbar-1992-wl-gore-associates.md, examples/ai-native-startup-scaling-2023-2026.md, references/sources.md
- 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
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1861 tokens
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
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 485: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.