跳到正文
cccskills
免费在 GitHub 公开

dotnet-mcaf-source-control

Apply MCAF source-control guidance for repository structure, branch naming, merge strategy, commit hygiene, and secrets-in-git discipline. Use when bootstrapping a repo, tightening PR flow, or documenting branch and release policy.

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(4)

  • SKILL.md3.7 KB
  • manifest.json47 B
  • references/naming-branches.md414 B
  • references/source-control.md934 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

MCAF: Source Control

Trigger On

  • bootstrapping source-control policy
  • tightening branch, merge, or PR rules
  • documenting commit or release hygiene
  • dealing with secrets-in-git or repository structure issues

Value

  • produce a concrete project delta: code, docs, config, tests, CI, or review artifact
  • reduce ambiguity through explicit planning, verification, and final validation skills
  • leave reusable project context so future tasks are faster and safer

Do Not Use For

  • CI/CD workflow design with no source-control policy change
  • one-off git commands that do not alter repo policy

Inputs

  • current branching and merge flow
  • release strategy and versioning expectations
  • secret-handling and repository-structure constraints

Quick Start

  1. Read the nearest AGENTS.md and confirm scope and constraints.
  2. Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
  3. Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

  1. Agree on merge and release strategy before scaling implementation.
  2. Keep branch and PR rules explicit in-repo.
  3. Treat secrets in git history as a critical incident, not cleanup noise.
  4. Use concrete policy language, not hand-waving.

Deliver

  • clear branch and merge strategy
  • updated contribution or governance docs
  • safer repository hygiene around commits, PRs, and secrets

Validate

  • naming and merge rules are explicit
  • release/versioning implications are documented where needed
  • secret hygiene is treated as policy, not tribal knowledge

Ralph Loop

Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

  1. Brainstorm first (mandatory):
    • analyze current state
    • define the problem, target outcome, constraints, and risks
    • generate options and think through trade-offs before committing
    • capture the recommended direction and open questions
  2. Plan second (mandatory):
    • write a detailed execution plan from the chosen direction
    • list final validation skills to run at the end, with order and reason
  3. Execute one planned step and produce a concrete delta.
  4. Review the result and capture findings with actionable next fixes.
  5. Apply fixes in small batches and rerun the relevant checks or review steps.
  6. Update the plan after each iteration.
  7. Repeat until outcomes are acceptable or only explicit exceptions remain.
  8. If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.

Required Result Format

  • status: complete | clean | improved | configured | not_applicable | blocked
  • plan: concise plan and current iteration step
  • actions_taken: concrete changes made
  • validation_skills: final skills run, or skipped with reasons
  • verification: commands, checks, or review evidence summary
  • remaining: top unresolved items or none

For setup-only requests with no execution, return status: configured and exact next commands.

Load References

  • read references/source-control.md first
  • open references/naming-branches.md only when the task is specifically about branch naming

Example Requests

  • "Define branch naming and merge rules for this repo."
  • "Document how releases and component versions should work."
  • "Tighten our source-control policy after a secrets leak."

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

dotnet

免费

Primary router skill for broad .NET work. Classify the repo by app model and cross-cutting concern first, then switch to the narrowest matching .NET skill instead of staying at a generic layer.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

Use a repo-root `.editorconfig` to configure free .NET analyzer and style rules. Use when a .NET repo needs rule severity, code-style options, section layout, or analyzer ownership made explicit. Nested `.editorconfig` files are allowed when they serve a clear subtree-specific purpose.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

Use Biome in .NET repositories that ship Node-based frontend assets and want a fast combined formatter-linter-import organizer for JavaScript, TypeScript, CSS, JSON, GraphQL, or HTML. Use when a repo prefers a modern all-in-one CLI over a larger ESLint plus Prettier style stack.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

Build and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

Use the free built-in .NET SDK analyzers and analysis levels with gradual Roslyn warning promotion. Use when a .NET repo needs first-party code analysis, `EnableNETAnalyzers`, `AnalysisLevel`, or warning-as-error policy wired into build and CI.

中文简介正在准备中。当前显示原文说明。

managedcode/PrompterOne452026年5月9日 更新

查看 managedcode 的全部技能

报告此技能的问题