AB coding-contract
Generate language-agnostic coding contracts (spec.md) from requirements. Outputs interface signatures, behavioral constraints, and verification checklists — never implementation code. Designed for the "strong model writes spec, weak model writes code" workflow. Spec files are reusable knowledge artifacts: write once, implement in any language. Use when the user wants to create a coding spec, define interfaces before implementation, or build a reusable engineering contract. Triggers on: "写规范", "生成 spec", "定义接口", "做实现蓝图", "coding contract", "implementation spec", "technical specification", or when a brainstorming design document needs to be converted into an actionable engineering plan.
As a process B 73/100 · 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 Secrets in code
secret-password-literalreferences/examples.md:170Hard-coded password / key literal (may be an example) (test fixture / example file; quoted — discussed, not commanded)- [ ] `createUser` — valid input `{email: "ne…@….com", password: "secu…123"}`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 73/100
- 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
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 53 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1709 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 693: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.