olddonkey-skills
SolidAgent skills distilled from real-world usage — codex-implementation-loop: delegate coding to Codex, keep review/gate/ship judgment in Claude's hands
Bundles
Everything this plugin ships — skills, agents, commands, hooks, and MCP servers it bundles.
Skills (6)
cursor-engineering-mode
Own goal-first engineering outcomes: investigate, find root cause, design, plan, then delegate implementation unit-by-unit to cursor-implementation-loop, this plugin's kernel skill, with verification and honest reporting. Use to fix, build, or own an outcome end to end; investigate-and-fix; "make X work"; or plan-then-execute in one request. A request with an approved plan or equivalently precise spec that needs nothing beyond implementation belongs directly to cursor-implementation-loop. Requires this plugin's cursor-implementation-loop skill; they ship together.
cursor-implementation-loop
Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).
codex-implementation-loop
Delegate implementation work to Codex (via the codex-companion runtime), then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex to write code, mentions handing off / delegating implementation to Codex, asks to work through a plan or spec unit-by-unit with Codex doing the coding, or wants a review-and-merge loop wrapped around Codex output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: Codex runs in the real environment with effectively read-only git, must not be pointed at a full test suite by default, accepts only specific --effort values, and its self-report is a claim rather than evidence.
engineering-mode
Own goal-first engineering outcomes: investigate, find root cause, design, plan, then delegate implementation unit-by-unit to implementation-loop with verification and honest reporting. Use to fix, build, or own an outcome end to end; investigate-and-fix; "make X work"; or plan-then-execute in one request. A request with an approved plan or equivalently precise spec that needs nothing beyond implementation belongs directly to implementation-loop. Requires implementation-loop and an authenticated backend CLI to execute.
implementation-loop
Delegate implementation to Codex, grok, or cursor-agent, then review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex, the grok 后端, or cursor-agent to write code, mentions handing off / delegating implementation to one of those backends, asks to work through a plan or spec unit-by-unit with an implementation backend doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer runs in the real environment behind backend-specific git and publication boundaries, must not be pointed at a full test suite by default, and its self-report is a claim rather than evidence. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the engineering-mode skill when it is installed.
web-slides
把素材 / 提纲 / 要点做成点击驱动的 16:9 HTML 幻灯片（slides / 演示文稿），用于现场放映或投屏 —— 不是视频，没有口播稿 / 音频合成 / 录屏。流程：原始素材 → 产出 outline 开发计划（章节切分 + 每步屏幕内容 + 可选每步演讲备注 + 信息池）→ 用户**一次对齐** 4 件事���outline / 主题 / 素材 / 开发模式）→ 网页开发（逐章 / 顺序 / 并行）。每次点击推进一个逻辑节拍，每一步独占整屏；进度条平时隐藏只在悬浮时出现；**按 P 开独立的演讲者窗口（口播稿 + 实时预览 + 计时器，与主窗口联动；投屏只共享主 slide 窗口即可对观众隐藏口播稿），按 N 是排练用的备注浮层**。内置 24 套主题 token + 反 AI 味设计方法论（内容驱动动画、逐步揭示、电影感留白）。适用场景：技术分享 / keynote / 产品演示 / pitch deck / 教学课件 / **面试项目复盘（project retro）** / 把文章或笔记变成可交互讲解。本 Skill 沉淀的是设计方法论 + 协作流程，不绑定任何特定样式 / 字体 / 颜色，可复用到任意主题与美学。
Quality Score: 59/100
Details
- Author
- olddonkey
- Repository
- olddonkey/olddonkey-skills
- Created
- 1 months ago
- Last Updated
- 2 days ago
- Language
- Shell
- License
- MIT