跳到正文
cccskills
免费在 GitHub 公开

generate-testcase

Analyze new commits and generate related test cases.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md1.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Preparation

  1. Find all commits after this branch is forked.
  2. Compare two commits and extract all new files.
  3. Locate the test directory. The test file should be saved in this directory.
  4. Locate the spec directory, often ./specs/.

Generation

  1. Think about some user scenarios (From basic usage with default setting, to different formats and parameters). These scenarios MUST related to the new feature.
  2. Ask users to choose. Wait for users response.
  3. For each user scenario, create a test function to confirm.
  4. Build and run test cases. Fix problems until all test passed.

Test

  1. Check the installation test coverage packages, including fastcov and lcov.
  2. Build and run test cases. Note to enable ENABLE_GCOV and BUILD_TEST.
  3. Fix problems until all test passed.
  4. Report and analyze the coverage result. Highlight files that the function coverage rate is not 100%.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

codegraph

免费

Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection, auto-merge candidates, labeling). Also covers creating, inspecting, and repairing a CodeScope index. Use for: code structure, who calls what, why something changed, similar functions, module boundaries, bug tracing, class relationships, PR risk/conflicts, or any question benefiting from a code knowledge graph. Applies when a `.codegraph` index exists in the workspace, or when the user wants to create one.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

Submit a new issue to the project.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

create-pr

免费

Submit a new Pull Request to the project.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

Vulnerability audit and dataflow analysis built on the neug CPG engine. file_audit (default, recommended): first builds a function-level summary graph (tier1) over the entire project, then incrementally builds detailed CPGs (tier2) on demand for chosen functions; both tiers coexist in a single neug database (unified schema, cross-layer refines edges; C/Java/Python/Rust). All capabilities are exposed as CLI tool subcommands (audit/overview/build/query/methods/paths), so an agent can drive the audit step by step via shell; the audit subcommand can also run the built-in LLM loop. The same tooling also supports a dataflow analysis mode (Workflow C): no vulnerability hunting, only variable-level dataflow tracing for functions of interest, producing dataflow_analysis.json. repo_audit: multi-round LLM/Cypher audit over a full-repo CPG. Use when the user asks to audit a codebase/project for vulnerabilities, scan a project with CPG/neug, run repo_audit/file_audit, find source-to-sink taint paths, or analyze dataflow inside a function. Supports C, Java, Python, and Rust.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

Execute the implementation planning workflow using the plan template to generate design artifacts.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

Create or update the feature specification from a natural language feature description.

中文简介正在准备中。当前显示原文说明。

alibaba/neug1702026年10月19日 更新

查看 alibaba 的全部技能

报告此技能的问题