AC self-critique
Improve output quality through structured self-review before finalizing. Based on Constitutional AI and self-reflection research, this skill creates a feedback loop where you critique your own work against quality criteria, identify issues, and revise. Use for any output where quality matters—code, writing, analysis, decisions. Critical for catching errors, improving clarity, and ensuring completeness before shipping.
As a process C 61/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitySKILL.md:370Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)### Pattern 3: The Red Team
detector -
low Risky intent
intent-offensive-securitySKILL.md:375Offensive-security / dual-use content (legitimate for authorised testing; review intended use)RED TEAM QUESTIONS:
Files scanned: 3. 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 61/100
- 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. 4 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3232 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 421: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (23 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.