New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Codexqa Requirement Analyzer

by openqa-cn in openqa-cn/codexqa

Full quality-and-risk analysis of requirement documents (single- or multi-source), producing one gap/conflict register with executable P0/P1 verification.

Apache-2.0Auto-check passedTesting & QA

Install Codexqa Requirement Analyzer

skills CLI
$ npx skills add openqa-cn/codexqa --skill codexqa-requirement-analyzer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openqa-cn/codexqa codexqa-requirement-analyzer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openqa-cn/codexqa.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codexqa-requirement-analyzer .claude/skills/codexqa-requirement-analyzer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
codexqa-requirement-analyzer
GitHub stars
152
Token cost
~1.6k tokens
SKILL.md length
735 words
Files
72 (incl. scripts, references)
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Full quality-and-risk analysis of requirement documents (single- or multi-source), producing one gap/conflict register with executable P0/P1 verification.

  • Works in 6 steps: Read and follow the main prompt listed… → Run the fixed pipeline: intake →… → Direct requirement materials remain… → …
  • Tasks that involve Code review
  • SKILL.md covers When to Use, Workflow, Core Constraints and Progressive Disclosure, plus 2 more sections
  • Calls npx

What it does

Codexqa Requirement Analyzer is an agent skill from openqa-cn/codexqa. 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.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 74 other files, including scripts and reference files (for example `.meta.json`, `CONTRIBUTING.md` and `HOW_IT_WORKS.md`).

It sits in Testing & QA, covering Code review and Test data and fixtures. The repository describes itself as: codexqa: 11 local-first Agent Skills for Cursor, Claude Code, Codex & OpenClaw — change impact analysis, AI code review, defect scan, testcase generation, browser replay & RCA. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Code review
  • Tasks that involve Test data and fixtures

Example prompts

  • “/codexqa-requirement-analyzer”

Requirements

  • Node.js

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  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…
  3. Direct requirement materials remain sufficient for standalone use. If the user supplies role reports with a declared source_role, treat…
  4. Add only project context that changes the result: scope, environment, constraints, risks, dependencies, expected deliverable.
  5. If input is incomplete, return a usable first draft and explicitly mark assumptions and gaps.
  6. Default to Markdown; switch formats only when the user asks.

What it can do on your machine

Read from SKILL.md and the folder at commit 7839542. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Codexqa Requirement Analyzer loads about 1.6k tokens when it runs, and up to ~5.3k if it reads all its reference files. Until then it costs about 127 tokens; SKILL.md has 735 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~127
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from openqa-cn/codexqa at commit 7839542, republished under its Apache-2.0 licence (© openqa-cn). 735 words, ~1,578 tokens.

Download SKILL.mdSave it as .claude/skills/codexqa-requirement-analyzer/SKILL.md (or your agent's skills folder). This skill also uses 71 other files; get the full folder from GitHub.
name
codexqa-requirement-analyzer
description
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.
license
Apache-2.0

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.
  3. Direct requirement materials remain sufficient for standalone use. If the user supplies role reports with a declared source_role, treat them as optional composition inputs and never require installing a role Skill.
  4. Add only project context that changes the result: scope, environment, constraints, risks, dependencies, expected deliverable.
  5. If input is incomplete, return a usable first draft and explicitly mark assumptions and gaps.
  6. Default to Markdown; switch formats only when the user asks.

Core Constraints

  • Produce exactly one gap and conflict register; do not also write “Gaps and Ambiguities”, “Cross-Source Conflicts”, or “Core Analysis Items”.
  • Audit credibility and comparability first; never mark stale or incomparable sources as aligned.
  • Prioritize by risk / business impact — do not treat everything equally.
  • Separate confirmed facts, role-report content, working assumptions, and hypotheses to verify.
  • Do not invent endpoints, fields, SLAs, environments, or root causes the user did not provide; unknowns become questions.
  • Do not fill business decisions for stakeholders, and do not judge whether the ask is worth building; keep both views and a suggested decider on conflicts. If an omission looks intentional, ask first.
  • When using a role report, preserve source_role item by item; never flatten into anonymous consensus or present a role view as a PRD fact.
  • Every P0/P1 item needs executable verification: preconditions, stimulus, expected result, required evidence, VerifyMethod, and RiskClass. Every P0 needs FailureMode.
  • Items with no observable failure condition are untestable and must not be executable P0. Do not emit a fake RPN, a 0–100 score, or a six-dimension traffic-light scorecard.
Show full SKILL.md (349 more words)Show less

Progressive Disclosure

  • Before producing output, read and follow prompts/codexqa-requirement-analyzer.md (minimum coverage, output structure, quality bar).
  • When Excel/CSV/JSON/Word is requested: read output-formats.md and honor the format.
  • When a ready-made template fits: use matching files under output-templates/.
  • When the user wants examples or alignment with existing assets: read relevant examples/.
  • For register fields, troubleshooting, or FAQ: read references/register-fields.md, references/troubleshooting.md, or references/FAQ.md.
  • For quality-characteristic judgments: read references/quality-attributes.md.
  • For vague/optional/loophole wording: read references/requirement-smells.md.
  • For NFR completeness: read references/nfr-quality-grid.md.
  • For the structure inventory (present/thin/absent): read references/structure-inventory.md.
  • For success metrics / KPI: read references/success-metrics.md.
  • For upstream/downstream owner and ready dates: read references/dependency-grid.md.
  • For missing states/decisions/time/failure paths/UX states: read references/behavioral-completeness.md.
  • For P0–P3 ranking: read references/risk-scoring.md.
  • Do not load the whole references/ directory.
  • For format conversion or helper pre-parse: prefer existing TypeScript scripts in scripts/ (npx --yes tsx scripts/run_analysis.ts --input <file>); do not rewrite them in Python.
  • For evaluating/regressing this skill: use evals/ with skill-up.
  • For the shortest path: read quick-start.md.

Pre-delivery Checklist

  • Followed the main prompt's 7-section output structure; section 6 was not omitted
  • Produced one register only; questions were not restated in section 7
  • Covered the minimum checklist, or explained omissions
  • High-risk items have P0–P3 with impact / likelihood / detectability
  • Section 2 includes quality-characteristic hits, smell hits, the eight-cell NFR grid, structure inventory, success-metrics grid, and dependency grid
  • P0/P1 items include preconditions, stimulus, expected, evidence, VerifyMethod, and RiskClass; P0 includes FailureMode
  • Items without an oracle were not written as executable P0
  • Did not invent details the user did not provide
  • Assumptions and gaps are marked
  • Role-report findings retain source roles; no role Skill internal file was linked

Common Pitfalls

  • Concatenating three old analysis outlines and repeating gaps, risks, questions, and next steps.
  • Marking aligned when sources are stale or not comparable.
  • Pretending completeness when scope or context is missing.
  • Treating every item as equally important, or using filler (“improve communication”) instead of closable questions.
  • Listing checkpoints for P0 items without verification steps.
  • Writing a weak AC with no oracle as an executable P0, or using a score or traffic-light scorecard for false precision.
  • Labeling a missing KPI as NFR, or treating “out of this iteration” as missing.

© openqa-cn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 71 other files (scripts, references) in skills/codexqa-requirement-analyzer of openqa-cn/codexqa.

  • SKILL.md
  • .meta.json
  • CONTRIBUTING.md
  • HOW_IT_WORKS.md
  • HOW_IT_WORKS.zh-CN.md
  • KNOWN_LIMITATIONS.md
  • KNOWN_LIMITATIONS.zh-CN.md
  • README.md
  • README.zh-CN.md
  • agents/openai.yaml
  • evals/cases/basic-success.yaml
  • evals/cases/edge-cross-source-conflict.yaml
  • evals/cases/edge-dependency-grid.yaml
  • evals/cases/edge-incomplete-input.yaml
  • evals/cases/edge-nfr-grid.yaml
  • evals/cases/edge-no-oracle-p0.yaml
  • evals/cases/edge-p0-verification.yaml
  • evals/cases/edge-risk-priority.yaml
  • … and 54 more

Open the folder on GitHubat commit 7839542

Compare with similar skills

Codexqa Requirement Analyzer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Codexqa Requirement Analyzer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Codexqa Requirement Analyzer this skillopenqa-cn/codexqa152—~1.6kAutomated safety check: PassApache-2.0
RTK Filter TDD in Rustrtk-ai/rtk83k—~1.9kAutomated safety check: NotesApache-2.0
Evaluate PR Testsdotnet/maui23k—~2.9kAutomated safety check: PassMIT
Test GuardamElnagdy/guard-skills1.3k2 repos~2.1kAutomated safety check: PassMIT
Playwright Java QA ReviewTahanima/playwright-java-test-automation-architecture113—~561Automated safety check: PassMIT
Reviewatelier-fashion/adlc-toolkit171—~1.9kAutomated safety check: PassMIT

Similar skills

  • RTK Filter TDD in Rust

    rtk-ai/rtk

    Enforces red-green-refactor for new RTK output filters in Rust, using real captured fixtures, snapshot tests with insta and token-savings assertions.

    83k GitHub stars~1.9k tokensUpdated today
    Testing & QAAuto-check: notes

  • Evaluate PR Tests

    dotnet/maui

    Official

    Reviews the tests added in a pull request for fix coverage, quality, edge cases and test type, and recommends lighter test types where they would do.

    23k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

  • Test Guard

    amElnagdy/guard-skills

    Reviews newly written or edited tests against nine rules that cut test bloat, such as mock-heavy checks and near-duplicate cases, before they are committed.

    1.3k GitHub starsUsed in 2 repos~2.1k tokens
    Testing & QAAuto-check passed

  • Playwright Java QA Review

    Tahanima/playwright-java-test-automation-architecture

    Reviews Playwright-Java test code in phases, checking page-object architecture, then using a Playwright MCP tool to verify shaky locators live.

    113 GitHub stars~561 tokensUpdated 7 mo ago
    Testing & QAAuto-check passed

  • Review

    atelier-fashion/adlc-toolkit

    Multi-agent code review covering correctness, quality, architecture, test coverage, and security

    171 GitHub stars~1.9k tokensUpdated 9 days ago
    Testing & QAAuto-check passed

  • Config

    idavidov13/agentic-playwright

    Configuration and environment variable conventions for the Playwright scaffold — env file layout (env/.env.), dotenv loading via playwright.config.ts and the ENVIRONMENT variable, config objects in…

    223 GitHub stars~2.8k tokensUpdated 7 days ago
    Testing & QAAuto-check: notes

More from openqa-cn/codexqa

All 14 skills in this repo

  • Codexqa Code Wiki

    openqa-cn/codexqa

    Builds a local architecture wiki for a repository from the CodexQA symbol graph (no model needed): modules, who calls whom and how often, reading paths, and one self-contained HTML page.

    152 GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Rootcause Analyzer

    openqa-cn/codexqa

    Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

    152 GitHub stars~2.6k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Skill Router

    openqa-cn/codexqa

    Auto-routes a user request to the matching codexqa skill, then ensures that skill is on disk and follows its SKILL.md.

    152 GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • Codexqa Testdata Generator

    openqa-cn/codexqa

    Constructs test data against real backends and writes it back into test cases as executable preconditions.

    152 GitHub stars~4.8k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Testcase Generator

    openqa-cn/codexqa

    Generates test plans and test cases from local requirements for APP, Web, and server.

    152 GitHub stars~3.6k tokensUpdated 5 days ago
    Auto-check passed

  • Codexqa Code Reviewer

    openqa-cn/codexqa

    Graph-evidence AI code review (codexqa-code-reviewer) for ANY language repo using ONLY the CodexQA CLI symbol graph (call chains, classes, methods, configs, blast radius, test edges), then an…

    152 GitHub starsUsed in 1 repo~7.2k tokens
    Auto-check: warnings

Categories

Questions about Codexqa Requirement Analyzer

What does Codexqa Requirement Analyzer do?

Full quality-and-risk analysis of requirement documents (single- or multi-source), producing one gap/conflict register with executable P0/P1 verification. Codexqa Requirement Analyzer is an agent skill from openqa-cn/codexqa. Full quality-and-risk analysis of requirement documents (single- or multi-source), producing one gap/conflict register with executable P0/P1 verification.

When should I use Codexqa Requirement Analyzer?

Codexqa Requirement Analyzer fits situations like: tasks that involve Code review; tasks that involve Test data and fixtures.

How do I install Codexqa Requirement Analyzer in Claude Code?

Run `npx skills add openqa-cn/codexqa --skill codexqa-requirement-analyzer -a claude-code`. Or copy the skill folder (skills/codexqa-requirement-analyzer in openqa-cn/codexqa) into .claude/skills/codexqa-requirement-analyzer in your project. Claude Code loads it when a task matches its description.

How do I install Codexqa Requirement Analyzer in Codex?

Run `npx skills add openqa-cn/codexqa --skill codexqa-requirement-analyzer -a codex`. Or copy the skill folder (skills/codexqa-requirement-analyzer in openqa-cn/codexqa) into .agents/skills/codexqa-requirement-analyzer in your project. Codex loads it when a task matches its description.

Can I use Codexqa Requirement Analyzer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openqa-cn/codexqa --skill codexqa-requirement-analyzer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codexqa-requirement-analyzer, .gemini/skills/codexqa-requirement-analyzer, .github/skills/codexqa-requirement-analyzer and .opencode/skills/codexqa-requirement-analyzer in your project.

What does Codexqa Requirement Analyzer need to run?

Going by SKILL.md and its folder, Codexqa Requirement Analyzer needs the command-line tools its instructions call (npx). Our summary lists: Node.js.

Does Codexqa Requirement Analyzer access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Codexqa Requirement Analyzer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Codexqa Requirement Analyzer use?

Codexqa Requirement Analyzer is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Codexqa Requirement Analyzer use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.

What are the alternatives to Codexqa Requirement Analyzer?

Skills that share tags, products or a category with Codexqa Requirement Analyzer: RTK Filter TDD in Rust (rtk-ai/rtk, 83k stars), Evaluate PR Tests (dotnet/maui, 23k stars), Test Guard (amElnagdy/guard-skills, 1.3k stars) and Playwright Java QA Review (Tahanima/playwright-java-test-automation-architecture, 113 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Codexqa Requirement Analyzer?

openqa-cn (a GitHub organization) maintains it in openqa-cn/codexqa, which has 152 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 3, 2026.

Source: openqa-cn/codexqa on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.