AF first-principles
Activate when: user says 'from first principles,' 'from scratch,' 'why do we even believe this,' 'tear this apart,' or 'the conventional answer seems wrong'; a decision is justified mainly by 'that's how it's done' or 'best practice says'; the conventional answer is expensive or hard to reverse and the user wants to pressure-test it. Do NOT activate when: the decision is routine and reversible (which linter, which date library) where convention is cheap and fine; the user has asked to just ship the conventional answer at speed. More: deciqai.com/c/first-principles
As a process F 40/100 · Will not run — References files that are not bundled: bedrock-packs/business-unit-economics.md, bedrock-packs/knowledge-domain-decomposition.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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: bedrock-packs/business-unit-economics.md - warning
missing-refreference to a missing file: bedrock-packs/knowledge-domain-decomposition.md
Process rating: all ten parameters 40/100
- 0Tools and files. 2 referenced file(s) missing: bedrock-packs/business-unit-economics.md, bedrock-packs/knowledge-domain-decomposition.md
- 0Result and completion. Does not say what the result is
- 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
- 70Failures and branches. 6 branches
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2587 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
- +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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 570: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 30 items
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.