AB premortem
Activate when: user says 'let's check what could go wrong before we commit', 'I want to stress-test this plan', 'we're about to launch and I'm worried we're missing something', 'premortem', or is about to make a hard-to-reverse decision with a team that has converged on one plan. Do NOT activate when: the decision is small and easily reversible (overhead exceeds value); the situation is time-critical and analysis would prevent timely response. More: deciqai.com/c/premortem
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityexamples/klein-2007-mitchell-russo-pennington-1989-foundation.md:39Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file; quoted — discussed, not commanded)**Military planning.** U.S. Army and U.K. Defence Forces include premortem-style exercises in operations planning. The Army's "Red Team University" trains officers in structured devil's-advocacy and p
fixturequoted
Files scanned: 5. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1764 tokens
- 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 477: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 24 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.