AC software-requirements-engineering
Book-aligned enterprise software requirements engineering based on Wiegers & Beatty, Software Requirements, 3rd Edition. Use when Codex must act like a professional requirements engineering team for full-lifecycle or phase-specific work: business requirements and vision/scope, customer-development partnership, stakeholder/user-class analysis, product champions, requirements elicitation/需求获取, use cases, user stories, business rules, requirements analysis/modeling/需求分析建模, prototypes, prioritization, SRS drafting or review/需求规格说明, excellent requirement writing, quality attributes/NFRs, requirements validation/需求验证, acceptance criteria, requirements reuse, baselines, version/status tracking, change control, impact analysis, traceability, requirements management/需求管理, agile/enhancement/packaged/outsourced/BPA/analytics/embedded project tailoring, enterprise governance, process improvement, risk management, or production-quality requirements documentation.
As a process C 60/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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: 14. 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 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (software-requirements-engineering) differs from the folder (software-requirements-engineering-skill)
- 85Steps. 80 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 2978 tokens
- 100Progress reporting. Reports progress
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)
- +3Description length 964: 120–800 characters recommended
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 80 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.