gautam-achieveai
gautam-achieveai/ClaudePlugins
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/gautam-achieveai/ClaudePlugins --skill gh-work-on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。
Internal helper. Load only when explicitly named by another skill or agent. Publishes goal-aligned, deduplicated PR feedback with clear blocker outcomes and stable closure criteria so reviews converge without repeated comment rounds.
Conduct goal-aligned code reviews of individual pull requests, analyzing correctness, solution fit, performance, code alignment, testing coverage, and code quality while helping authors converge quickly on a mergeable change. Provides prioritized, actionable feedback with stable closure criteria. Use when asked to "review PR #[number]", "code review pull request", "check PR for issues", or "analyze PR changes". Works on GitHub or Azure DevOps, with PR numbers, branch names, or GitHub/Azure DevOps PR URLs. NOT for developer performance reviews over time.
This skill should be used when the user asks to "babysit a PR", "babysit my pull request", "monitor my PR", "watch my pull request", "keep my PR green", "fix PR build failures automatically", "handle PR review comments", or wants autonomous Azure DevOps PR monitoring that fixes build breaks, test failures, code coverage gaps, and review comments on a polling loop.
基于 SOC 职业分类
正在显示 SKILL.md
| name | gh-work-on |
| description | Internal helper. Load only when explicitly named by another skill or agent. |
| user-invocable | true |
| disable-model-invocation | false |
This is a thin GitHub wrapper around the provider-agnostic development:work-on
skill. It pins the backend to GitHub and makes sure GitHub tooling is ready,
then hands the work item off to the shared autonomous workflow.
Ensure GitHub tooling is ready. Before the first GitHub operation, verify
the GitHub MCP tools are available. If the first call fails (connection error,
tool not found, missing write toolsets, or auth failure), follow the auto-setup
rule in gh/CLAUDE.md: automatically use the gh:setup-gh-mcp skill, then
retry. Fall back to the gh / gh api CLI when MCP coverage is insufficient.
Delegate to the shared workflow. Load and execute the development:work-on
skill with the provider set to GitHub (so it skips auto-detection) and pass
through $ARGUMENTS (the issue number). The shared skill runs the full GitHub
branch end to end: auto-detect plan vs execute mode, Part 1 (research, plan,
post to the issue, HITL feedback checkpoint), Part 1 revision mode, and Part 2
(worktree, implement, self-review, verify, publish via gh:gh-publish-pr,
update issue/Project state).
Re-runs. The same /gh-work-on <id> command resumes the workflow — the
shared skill reads the issue's comment history to decide whether to plan,
revise, or execute. To resume, re-run /gh-work-on <id>. On the next /gh-work-on <id> invocation, the shared workflow re-checks the latest issue comments before choosing the next phase.
gh:gh-mentions).gh/CLAUDE.md).