AC prism
Use PRISM when: (1) reviewing an architecture decision, security-sensitive change, or major refactor (>500 lines), (2) making a decision you'll live with for 6+ months, (3) preparing an open source release, (4) you want structured adversarial analysis to eliminate groupthink. NOT FOR: minor bug fixes, documentation typos, cosmetic changes, urgent hotfixes, or any decision reversible within a week.
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7377 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "taxonomy_category" - note
frontmatter-keyunknown frontmatter key "health_score" - note
frontmatter-keyunknown frontmatter key "status" - note
frontmatter-keyunknown frontmatter key "last_improved"
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Failures and branches. 4 branches
- 70Execution cost. Instruction body is 7377 tokens
- 100Tools and files. No external tools needed
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 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
- +3Output format is not stated: the model decides each time
- -222 emoji in the instructions: noise for the model
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 400: enough signal without eating the budget
- +4Structure: 40 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (16 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.