all publishers

openqa-cn

@openqa-cn source repo

22 published skills

  1. ▌
    Codexqa Testcase Generator · openqa-cn bundle
    Generate structured test plans and formal test cases from requirements or technical documentation to ensure comprehensive and consistent software quality assurance.
    237 repo stars
  2. ▌
    Slot Scaffolder 2 · openqa-cn bundle
    Generate a domain data-build slot from OpenAPI files: new business-domain pack, scaffold a data-build skill, or add an enterprise custom domain. Internal helper of the parent pack; reach this through codexqa-testdata-generator.
    237 repo stars
  3. ▌
    Case Data Material Planner 2 · openqa-cn bundle
    Prepares executable case preconditions and case-executable.md from a requirement or written cases. Internal case-material engine; enter through codexqa-testdata-generator so SKILL_DIR and adapters resolve.
    237 repo stars
  4. ▌
    Codexqa Testdata Generator · openqa-cn bundle
    Constructs test data against real backends and writes it back into test cases as executable preconditions. Use whenever the user wants test data built, case materials or preconditions prepared, a data-build skill or tool reused, an API discovered, a construction script written, or a proven method recorded — including Chinese phrasings such as 构造测试数据, 准备测试数据, 造数据, 用例数据, 用例物料, 用例数据准备, 用例前置数据, 测试数据回写, 测试物料清单, 数据需求分析. Also use it for concrete requests that never say "test data", like "create this account from the OpenAPI", "build a script from these change APIs", "publish that script as a tool", or "scaffold a new domain from this OpenAPI directory". Not for authoring test cases from a PRD (that is codexqa-testcase-generator) or finding defects in code (that is codexqa-defect-analyzer). Bundled slots and sub-skills here are internal; reach them through this skill. Former skill name: testdata-generation.
    237 repo stars
  5. ▌
    Codexqa Requirement Analyzer · openqa-cn bundle
    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.
    237 repo stars
  6. ▌
    Codexqa Change Analysis · openqa-cn bundle
    Change-impact analysis for one diff: use CodexQA diff indexing (`index --diff-base` tags nodes and files `add` / `change` / `delete`, then `change-groups` / `symbol-diff` / `file-base`) to write one HTML report (affected entries, changed methods, test plan, coverage verdict, sensitive paths) and add runnable test files in the analyzed repo for uncovered points (add only; do not edit existing test files). Use when the user mentions change impact, change analysis, blast radius, affected entries, added methods, changed methods, test plan, generate or recall tests, link existing tests, entry points, 变更分析, 变更代码分析, 影响面, 影响入口, 测试方案, or 召回测试用例. Requires the codexqa CLI. One change only. Whole-repo analysis with no diff, and general symbol-graph Q&A, are codexqa-code-analyzer, not this skill. Former skill name: change-impact-analysis.
    237 repo stars
  7. ▌
    Codexqa Defect Analyzer · openqa-cn bundle
    AI defect detection and code-risk scanning for engineering projects. Use when the user asks for AI defect detection, code-risk scan, review a diff/MR/PR/commit (incremental), baseline-scan a repository (full), OR upload/paste code snippets for adhoc defect detection. Combines two detection dimensions — (1) deterministic SAST/lint/secrets/SCA and (2) one-round Agent LLM Detection by the invoking agent's embedded model (no separate LLM API key) — then dedupes and merges them into the final report. Delivers structured findings ordered by severity (P0–P3) via report_scan.json / report_scan.md / report_scan.html. Do NOT use to apply or autofix code style/formatting — lint may still surface hygiene findings. Code-graph / call-chain MUST use CodexQA CLI for all languages (references/codexqa-cli.md) — never homemade analyzers. Not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), not structure/impact mapping (that is codexqa-code-analyzer), and not exception RCA (that is codexqa-rootcause-analyzer).
    237 repo stars
  8. ▌
    Codexqa Rootcause Analyzer · openqa-cn bundle
    Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis. Use when the user mentions codexqa-rootcause-analyzer, exception RCA, crash analysis, AI code diagnosis, stack diagnosis, 异常根因, 堆栈诊断, 崩溃分析, 异常诊断, or asks to turn an exception into a root-cause report. Not structure/impact analysis (that is codexqa-code-analyzer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer). Former skill name: root-cause-diagnosis.
    237 repo stars
  9. ▌
    Codexqa Code Analyzer · openqa-cn bundle
    Queries a local CodexQA symbol graph for change review, regression scope, test gaps, error location, and entry risk. Use when the user mentions codexqa-code-analyzer, code-analyzer, codexqa, 符号图, 代码知识图谱, 建索引, 查调用, 影响面, --diff-base, 变更审查, 回归范围, 测试缺口, or asks to install / run the codexqa CLI (index, query). Former skill name: code-analyzer. Not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), not SAST + Agent LLM Detection code-risk scan reports (that is codexqa-defect-analyzer), and not architecture wiki reports (that is codexqa-code-wiki), and not full exception RCA reports (that is codexqa-rootcause-analyzer).
    237 repo stars
  10. ▌
    Codexqa Code Reviewer · openqa-cn bundle
    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 order-16 Agent LLM judgment pass by the host agent's embedded model with deterministic dedupe/merge against heuristic findings. Use when the user asks for codexqa-code-reviewer (former name ai-code-reviewer), code review, PR review, 代码评审, impact analysis, 影响面, regression scope, test gaps, full-repo health review, 全仓评审, CodexQA evidence-pack, 证据包, graph-backed review, or LLM semantic CR on a pack. Requires codexqa CLI for every language; never embeds CodexQA source; never substitutes git-diff-only analysis. Not SAST+agent scan reports (that is codexqa-defect-analyzer), not structure/impact mapping alone (that is codexqa-code-analyzer), and not exception RCA (that is codexqa-rootcause-analyzer).
    237 repo stars
  11. ▌
    Codexqa Code Wiki · openqa-cn bundle
    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. Use when the user mentions codexqa-code-wiki, code-wiki, wiki, knowledge graph, architecture wiki, module map, reading guide, 代码知识图谱, 架构 Wiki, 模块地图, 阅读导览, wiki inputs, --no-llm, community detection, 社区检测, HTML 报告, or asks to map modules / generate a repo wiki without an LLM. Not change review (that is codexqa-code-analyzer), not CodexQA evidence-pack HTML review (that is codexqa-code-reviewer), and not SAST+agent code-risk scan reports (that is codexqa-defect-analyzer). Former skill name: code-wiki.
    237 repo stars
  12. ▌
    Codexqa Jev Browser · openqa-cn bundle
    Jev browser automation with indexed actions. Replay YAML/Markdown/API cases, run goal-driven flows, generate cases, and explore sites in a real browser. Use when the user mentions Jev, browser automation, UI automation, E2E replay, test case generation, exploratory crawl, or YAML/MD/API test cases. Not a fork of browser-use/jev-ultrafast.
    237 repo stars
  13. ▌
    Codexqa Skill Router · openqa-cn bundle
    Auto-routes a user request to the matching codexqa skill, then ensures that skill is on disk and follows its SKILL.md. Use whenever the user is unsure which skill to run, says 帮我选 skill、自动路由、选哪个 skill、不知道用哪个、 route this request、pick the right skill、codexqa 该用哪个, installs only codexqa-skill-router and still needs a worker skill, or describes a verification / QA / testing / review / RCA / requirements / cases / testdata task without naming a skill. Former skill name: skill-router. Matches against live siblings plus a bundled catalog so newly published pack skills remain routable; if the winner is not installed, fetch it beside this router (ask once, then ensure_skill.py --yes) and hand off — do not invent a parallel workflow. Not a replacement for any target skill.
    237 repo stars
  14. ▌
    Code Reviewer · openqa-cn bundle
    Review Git branch, PR, or commit changes for quality, security, and maintainability (CR / 代码审查 / 审查 / pre-commit / risk assessment). Frontend: React, TypeScript, JavaScript, React Native, mini-program. Backend: Java, Kotlin, Go, Python, C, C++, Groovy, SQL / service-layer. Requires a local Git checkout — not a pasted snippet. Do not use for how-to questions, debugging a known bug, explaining or rewriting code, method-level requirement defect hunting with write-back gates (that is defect-detection), writing test cases (testcase-generation), or constructing test data (testdata-generation).
    237 repo stars
  15. ▌
    Defect Detection · openqa-cn bundle
    Reviews code changes for defects before release. Given a git repository and branch (optionally a PR, test plan, or a previous report to continue), it clones the repo, diffs the base branch, extracts changed methods, runs static rules, cross-checks requirements, test cases, and known defects, and writes back findings with line numbers, fix suggestions, and an HTML report. Language-aware for Java, Kotlin, Scala, JavaScript, TypeScript, Python, Go, C, C++ and C#: method extraction, trivial-method filter, Semgrep seed packs, and write-back conventions; polyglot diffs keep each language's rules. Optional overlays add secret / SCA / native-analyzer findings. Use when the user asks to find bugs in a branch or PR, review change or regression risk, recheck before release, scan a test plan, or resume a detection task. Not a P0/P1/P2 style CR (that is code-reviewer).
    237 repo stars
  16. ▌
    Testcase Generation · openqa-cn bundle
    Turns a PRD, technical design, API spec, or knowledge base into a reviewable library of structured manual test cases. Every case gets a stable UUID, a business-semantic name, and engineering info (interface name, request parameters, DB / cache / MQ assertions), behind requirement, design, and coverage review gates. Also maintains that library: it diffs the PRD and the code under test against the last baseline and updates only the affected cases. Use this whenever the user wants test cases written, a case library initialized, coverage designed, cases refreshed after a PRD or code change, or an interrupted run resumed from pending entries — including Chinese phrasings such as 生成测试用例, 写用例, 用例设计, 用例库, 根据 PRD 出用例, 补充测试场景, 用例更新, and requests that never say "test case", like asking which scenarios a requirement needs covered. Not for unit-test or automation code, not for building the data that fills case placeholders (use testdata-generation), not for reviewing requirement quality or writing a gap register (use requ
    237 repo stars
  17. ▌
    Testdata Generation · openqa-cn bundle
    Constructs test data against real backends and writes it back into test cases as executable preconditions. Use whenever the user wants test data built, case materials or preconditions prepared, a data-build skill or tool reused, an API discovered, a construction script written, or a proven method recorded — including Chinese phrasings such as 构造测试数据, 准备测试数据, 造数据, 用例数据, 用例物料, 用例数据准备, 用例前置数据, 测试数据回写, 测试物料清单, 数据需求分析. Also use it for concrete requests that never say "test data", like "create this account from the OpenAPI", "build a script from these change APIs", "publish that script as a tool", or "scaffold a new domain from this OpenAPI directory". Not for authoring test cases from a PRD (that is testcase-generation) or finding defects in code (that is defect-detection). Bundled slots and sub-skills here are internal; reach them through this skill.
    237 repo stars
  18. ▌
    Requirements Analyzer · openqa-cn bundle
    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 testcase-generation), constructing test data (testdata-generation), or reviewing code (defect-detection / code-reviewer).
    237 repo stars
  19. ▌
    Catalog · openqa-cn bundle
    Constructs catalog products (standard or limited), catalog orders, and account-credit enrollment, including product-then-credit scenes. Internal catalog slot of the parent pack; do not invoke independently.
    237 repo stars
  20. ▌
    Slot Scaffolder · openqa-cn bundle
    Generate a domain data-build slot from OpenAPI files: new business-domain pack, scaffold a data-build skill, or add an enterprise custom domain. Internal helper of the parent pack; reach this through testdata-generation.
    237 repo stars
  21. ▌
    Distribution · openqa-cn bundle
    Constructs distributor accounts, inventory binds, commission or markup, and browse-and-quote, including the ready-to-sell scene. Internal distribution slot of the parent pack; do not invoke independently.
    237 repo stars
  22. ▌
    Case Data Material Planner · openqa-cn bundle
    Prepares executable case preconditions and case-executable.md from a requirement or written cases. Internal case-material engine; enter through testdata-generation so SKILL_DIR and adapters resolve.
    237 repo stars