github-repo-management
Create and manage GitHub repositories, branches, commits, and PRs via local git commands and GitHub MCP. Use when the user asks to create a repo, push code, get repo info, manage branches, open PRs, or work with GitHub repositories.
What this skill does
# GitHub Repository Management ## Rules - **Secrets**: Do not echo, log, or include any token or secret in output, commands, or file contents. GitHub MCP handles auth. - **Destructive actions**: Ask for confirmation before `git push --force`, `git branch -D`, deleting a repo, or overwriting remote history. - **Default branch**: Prefer `main`; use `master` only when the repo already uses it. - **Commits**: Use [Conventional Commits](https://www.conventionalcommits.org/) (e.g. `feat:`, `fix:`, `docs:`). ## Capabilities - Run git commands locally (init, add, commit, push, branch, checkout, etc.). - Operate on GitHub via **GitHub MCP** only: create repos, get repo info, list/create/merge PRs, manage branches. Do not use REST API or GITHUB_TOKEN directly. --- ## Create a repo When the user asks to "create a repo" or "create a GitHub repository": 1. **Create on GitHub** (GitHub MCP only): - Use GitHub MCP `create_repository` (or equivalent) with `name`, optional `description`, `private` (default from user intent). 2. **Set origin locally** (if already in a git repo): ```bash git remote add origin https://github.com/<owner>/<repo>.git ``` If `origin` exists and should point to the new repo, ask before changing it. 3. **If no local repo yet**: ```bash git init git remote add origin https://github.com/<owner>/<repo>.git ``` 4. **First push** (after at least one commit): ```bash git push -u origin main ``` Use `main` unless the GitHub repo was created with a different default branch. --- ## Push code When the user asks to "push code" or "push to GitHub": 1. **Ensure git repo exists**: Run `git status`. If not a repo, ask whether to `git init` and set remote. 2. **Check remote**: `git remote -v`. If no `origin`, ask for repo URL or create repo first. 3. **Commit cleanly**: - `git status` to see changes. - Stage: `git add <paths>` or `git add -A` if user intends all changes. - Commit with a conventional message: `git commit -m "type(scope): description"`. - If there are uncommitted changes and user said "push", offer to commit first; do not force-push without asking. 4. **Push**: `git push origin <branch>`. Default branch is `main`. If upstream not set: `git push -u origin main`. --- ## Get repo info When the user asks to "get repo info", "repo details", or "show repository": 1. **Identify repo**: From `git remote get-url origin` (owner/repo) or user-provided owner/name. 2. **Fetch via GitHub MCP**: Use MCP tools to get repository details (e.g. get repo, list branches, list PRs). Summarize: name, description, default branch, visibility, stars/forks if available, clone URL. --- ## Branches - **Create branch**: `git checkout -b <branch-name>` then push: `git push -u origin <branch-name>`. - **Switch branch**: `git checkout <branch>` or `git switch <branch>`. - **Delete branch**: Local `git branch -d <branch>`; remote delete only after user confirmation: `git push origin --delete <branch>`. --- ## Pull requests - **Open PR**: Use GitHub MCP to create a pull request (`head`, `base` default `main`, `title`, `body`). - **List PRs**: Use GitHub MCP to list PRs; summarize by number, title, state, author. - **Merge**: Use GitHub MCP to merge; confirm with user before merging. --- ## Conventional commit messages Use this format: `type(scope): short description`. | Type | Use for | |----------|----------------------------| | `feat` | New feature | | `fix` | Bug fix | | `docs` | Documentation only | | `style` | Formatting, no code change | | `refactor` | Code change, no feature/fix | | `test` | Adding or updating tests | | `chore` | Build, tooling, deps | Examples: - `feat(auth): add login endpoint` - `fix(api): correct date parsing` - `docs: update README setup steps` --- ## Summary checklist - GitHub operations: GitHub MCP only (no REST API, no GITHUB_TOKEN in commands). - Confirm before force push, branch delete, or repo delete. - Default branch: `main`. - All commits: conventional style.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.