Individual skill

codexqa-requirement-analyzer

Full quality-and-risk analysis of requirement documents (single- or multi-source), producing one gap/conflict register with executable P0/P1 verification. Triggers: requirements analyzer, requirement quality, gap register, 需求分析, 需求分析器, 需求评审, 需求缺口. Not for writing a case library (that is codexqa-testcase-generator), constructing test data (codexqa-testdata-generator), or reviewing code (codexqa-defect-analyzer / codexqa-code-reviewer). Former skill name: requirements-analyzer.

skills/codexqa-requirement-analyzer/SKILL.md

Read pinned source

Source commit 783954281fc4898a9fac66a575363f419d4683e4

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Local scripts
Last checked: Nov 5, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 236
Repository last updated: Nov 6, 2026
License: Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

software-testing Repository topic
agent-skills Repository topic
ai-testing Repository topic
code-review Repository topic
coding-agent Repository topic
quality-assurance Repository topic
static-analysis Repository topic
ai-code-review Repository topic
claude-code Repository topic
cursor Repository topic
writing Derived category
data Derived category
testing Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

.meta.jsonasset · 1,291 bytes
CONTRIBUTING.mddoc · 922 bytes
HOW_IT_WORKS.mddoc · 4,141 bytes
HOW_IT_WORKS.zh-CN.mddoc · 3,892 bytes
KNOWN_LIMITATIONS.mddoc · 1,679 bytes
KNOWN_LIMITATIONS.zh-CN.mddoc · 1,555 bytes
README.mddoc · 3,263 bytes
README.zh-CN.mddoc · 3,075 bytes
SKILL.mdcore · 6,400 bytes
SKILL.mdcore · 6,400 bytes
SKILL.mdcore · 6,400 bytes
agents/openai.yamlasset · 527 bytes
evals/cases/basic-success.yamlasset · 1,075 bytes
evals/cases/edge-cross-source-conflict.yamlasset · 959 bytes
evals/cases/edge-dependency-grid.yamlasset · 919 bytes
evals/cases/edge-incomplete-input.yamlasset · 901 bytes
evals/cases/edge-nfr-grid.yamlasset · 956 bytes
evals/cases/edge-no-oracle-p0.yamlasset · 824 bytes
evals/cases/edge-p0-verification.yamlasset · 848 bytes
evals/cases/edge-risk-priority.yamlasset · 716 bytes
evals/cases/edge-role-artifact-input.yamlasset · 1,589 bytes
evals/cases/edge-singular-compound.yamlasset · 859 bytes
evals/cases/edge-success-metrics.yamlasset · 951 bytes
evals/eval.yamlasset · 794 bytes
examples/inventory-conflict.analysis.mddoc · 5,285 bytes
examples/requirements-sample.jsonasset · 587 bytes
examples/requirements-sample.mddoc · 664 bytes
output-formats.mddoc · 780 bytes
output-templates/template-csv.csvasset · 315 bytes
output-templates/template-excel.tsvasset · 244 bytes
output-templates/template-json.jsonasset · 2,611 bytes
output-templates/template-markdown.mddoc · 1,667 bytes
output-templates/template-word.mddoc · 697 bytes
output-templates/template-xmind.mddoc · 429 bytes
prompts/codexqa-requirement-analyzer.mddoc · 14,454 bytes
quick-start.mddoc · 1,318 bytes
references/FAQ.mddoc · 900 bytes
references/behavioral-completeness.mddoc · 1,170 bytes
references/dependency-grid.mddoc · 971 bytes
references/nfr-quality-grid.mddoc · 1,290 bytes
references/quality-attributes.mddoc · 1,958 bytes
references/register-fields.mddoc · 1,979 bytes
references/requirement-smells.mddoc · 1,357 bytes
references/risk-scoring.mddoc · 1,925 bytes
references/structure-inventory.mddoc · 1,408 bytes
references/success-metrics.mddoc · 1,139 bytes
references/troubleshooting.mddoc · 703 bytes
scripts/batch_convert_templates.tsruns · 2,502 bytes
scripts/common_parser.tsruns · 2,435 bytes
scripts/convert_formats.tsruns · 10,204 bytes
scripts/convert_output_formats.tsruns · 308 bytes
scripts/convert_to_csv.tsruns · 328 bytes
scripts/convert_to_excel.tsruns · 330 bytes
scripts/convert_to_json.tsruns · 329 bytes
scripts/convert_to_markdown.tsruns · 333 bytes
scripts/convert_to_word.tsruns · 329 bytes
scripts/convert_to_xmind.tsruns · 330 bytes
scripts/office_io.tsruns · 10,205 bytes
scripts/parse_csv.tsruns · 368 bytes
scripts/parse_excel.tsruns · 516 bytes
scripts/parse_formats.tsruns · 8,040 bytes
scripts/parse_html.tsruns · 513 bytes
scripts/parse_json.tsruns · 513 bytes
scripts/parse_markdown.tsruns · 525 bytes
scripts/parse_output_formats.tsruns · 344 bytes
scripts/parse_pdf.tsruns · 368 bytes
scripts/parse_word.tsruns · 513 bytes
scripts/parse_xmind.tsruns · 370 bytes
scripts/run_analysis.tsruns · 8,884 bytes

Read excerpt


# Requirements Analyzer

Human-facing install and method docs: `README.md`, `HOW_IT_WORKS.md`, `KNOWN_LIMITATIONS.md` (and `.zh-CN.md`). Do not load those at runtime.

## When to Use

- Need a complete quality and risk analysis of requirement documents, not just a scope scan or a gap list.
- Materials may be a single PRD or a multi-source pack (stories, APIs, plans, role reports).
- Need one reviewable, assignable, verifiable gap register that can hand off to strategy or case writing.

## Workflow

1. Read and follow the main prompt listed under Progressive disclosure (coverage, structure, quality bar).
2. Run the fixed pipeline: intake → short-input gate → structure inventory → input audit → quality/smell/NFR → success metrics → behavior plus UX states → trace and goal-feature alignment → dependency grid → single register → risk algorithm → testability and oracles → blockers and next actions. Do not write risks or a “TOP 3” list first.