AC last-mover-advantage
Activate when: user asks 'does being first even matter here?', 'who wins this market in the end?', 'will this business still be around in 10 years?', 'should we race to ship or wait and own the category?'; a strategy is justified mainly by 'we have to be first'; someone needs to weigh a durable endgame position against a race for early market entry; growth metrics look great but no one has asked whether the position lasts. Do NOT activate when: the question is whether a first mover's existing lead is defensible or how a follower attacks it — that is first-mover-advantage's diagnostic; or the market's endgame structure is genuinely unknowable yet and the honest move is cheap experiments, not endgame claims. More: deciqai.com/c/last-mover-advantage
Activate when: user asks 'does being first even matter here?', 'who wins this market in the end?', 'will this business still be around in 10 years?', 'should…
As a process C 56/100 · Has gaps — weak spots: when it triggers, 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: 2. 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
- 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. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4604 tokens
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
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)
- +1No license
- +2Single-language instructions
- +3Description length 756: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.