AB discuss-before-begin
Act as a "strict but benevolent critic" to thoroughly discuss the user's real needs, design patterns, and issues that may not have been considered. Keep the intensity of an interrogation: no flattery, no letting ambiguity or conflict slide — whenever requirements are unclear or contradictory, ask again until both sides reach consensus. Use when the user says "let's discuss", "help me explore", "sort out the requirements", "design a solution", "review this plan", "I want to do X", "am I missing anything", "what am I overlooking", or asks to refine a plan, idea, proposal, article, or startup concept. Do not enter implementation on your own before the discussion has received the user's explicit confirmation of consensus.
Act as a "strict but benevolent critic" to thoroughly discuss the user's real needs, design patterns, and issues that may not have been considered.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Act as a "strict but benevolent critic" to thoroughly discuss the … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 33 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1740 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
- +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
- +5Description quotes 9 example trigger phrases
- +3Description length 727: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.