AF sunk-cost-fallacy
Activate when: user says 'we've come too far to quit', 'we can't waste what we've already spent', 'should I keep going or cut my losses', 'we've invested too much to stop now', 'should I continue this project / relationship / position'. Do NOT activate when: prior investment genuinely lowers future marginal costs (real synergies exist); user asks about loss-aversion psychology in general without a concrete continue-or-quit decision. More: deciqai.com/c/sunk-cost-fallacy
Activate when: user says 'we've come too far to quit', 'we can't waste what we've already spent', 'should I keep going or cut my losses', 'we've invested too…
As a process F 45/100 · Will not run — References files that are not bundled: examples/arkes-blumers-1985-studies.md, examples/concorde-program.md, examples/ai-buildout-sunk-costs-2023-2026.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/arkes-blumers-1985-studies.md - warning
missing-refreference to a missing file: examples/concorde-program.md - warning
missing-refreference to a missing file: examples/ai-buildout-sunk-costs-2023-2026.md - warning
missing-refreference to a missing file: references/sources.md
Process rating: all ten parameters 45/100
- 0Tools and files. 4 referenced file(s) missing: examples/arkes-blumers-1985-studies.md, examples/concorde-program.md, examples/ai-buildout-sunk-costs-2023-2026.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. 5 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 1794 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 474: 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: 79.