菜单
Complete GitHub workflow — repos, branches, commits, PRs, issues, code review, and releases. Use when the user mentions GitHub, git, pull requests, issues, or repository management.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/amanning3390/hermeshub --skill github-workflow命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | github-workflow |
| description | Complete GitHub workflow — repos, branches, commits, PRs, issues, code review, and releases. Use when the user mentions GitHub, git, pull requests, issues, or repository management. |
| version | 1.0.0 |
| license | MIT |
| compatibility | Requires git and gh CLI. Run gh auth login for authentication. |
| metadata | {"author":"hermeshub","hermes":{"tags":["github","git","pull-requests","issues","code-review"],"category":"development","requires_tools":["terminal"]}} |
| allowed-tools | Bash(git:*) Bash(gh:*) |
Full GitHub lifecycle management through the gh CLI.
gh repo clone owner/repogh repo create name --public/--privategh repo fork owner/repogit checkout -b feature/namegit add -Agit commit -m "type: description"git push -u origin feature/namegh pr create --title "..." --body "..." --base maingh pr listgh pr review <number> --approve/--request-changesgh pr merge <number> --squashgh issue create --title "..." --body "..." --label buggh issue list --state opengh issue close <number>gh issue edit <number> --add-assignee @megit tag -a v1.0.0 -m "Release v1.0.0"git push --tagsgh release create v1.0.0 --generate-notesgh pr view <number>gh pr statusgh run listAccess and search Telegram message history using AI. Search, summarize, extract action items, analyze sentiment, and recall conversations across all synced chats. Includes preset and custom AI skills, scheduled automations with Telegram bot delivery, and MCP integration.
ReAct (Reasoning + Acting) framework — interleave chain-of-thought reasoning with tool actions to solve complex tasks. Eliminates hallucination by grounding every reasoning step in real observations. Use when the agent needs multi-step reasoning with external tool use: question answering, fact verification, web navigation, interactive decision making, or any task where pure reasoning hallucinates and pure acting fails to plan.
Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.
基于 SOC 职业分类