mirror of
https://github.com/jnMetaCode/superpowers-zh.git
synced 2026-09-03 07:23:56 +08:00
eadc83b64b
版本号：7 份声明文件 1.7.3 -> 1.7.4（只动 "version" 行，已 diff 确认）。 包内文件 106 -> 107（新增 re-review-prompt.md）。 内容见 RELEASE-NOTES.zh.md v1.7.4 条目。 按 CLAUDE.md「改 skill 需要 eval 证据」的要求，本次补了两层行为验证 —— 结构性核对不足以证明译文真的传达了新规则： 1) 新机制 7 个场景 eval：7/7 正确 考察第 2 轮该唤回还是换新、第 4 轮模型档位、第 5 轮能否再开一轮、 承重发现该搁置还是停下、Minor 走哪条路、遇到别的计划的账本怎么办、 控制者能否自己修。连「运行环境无法唤回时才改派全新实现者」都答出。 2) 集成 eval：用 tests/subagent-driven-dev/go-fractals 脚手架跑真实 执行的准备阶段，验证 agent 是否按新签名调脚本（旧习惯可能省掉 PLAN_FILE） - 实际调用 sdd-workspace plan.md，带上了 PLAN_FILE - 同时检查了 plan 作用域账本和旧扁平路径的游离账本 - 账本第一行为正确的身份行；工作区落在 .superpowers/sdd/plan/ - 起飞前冲突扫描产出 5 条打包成一次的提问，而非逐条打断 - 建 10 条待办并按指令在分派实现者前停下 回归：audit.sh 150 pass / 0 fail、verify-release.sh 82 pass / 0 fail dry-run：1.7.4 / 107 文件 / 464.0 kB
42 lines
3.3 KiB
JSON
42 lines
3.3 KiB
JSON
{
|
||
"name": "superpowers-zh",
|
||
"version": "1.7.4",
|
||
"description": "AI 编程超能力中文增强版：头脑风暴、subagent 驱动开发、规划、TDD、调试、代码审查、收尾工作流，附 4 个中文 skills 沉淀。",
|
||
"author": {
|
||
"name": "jnMetaCode",
|
||
"url": "https://github.com/jnMetaCode"
|
||
},
|
||
"homepage": "https://github.com/jnMetaCode/superpowers-zh",
|
||
"repository": "https://github.com/jnMetaCode/superpowers-zh",
|
||
"license": "MIT",
|
||
"keywords": [
|
||
"brainstorming",
|
||
"subagent-driven-development",
|
||
"skills",
|
||
"planning",
|
||
"tdd",
|
||
"debugging",
|
||
"code-review",
|
||
"workflow",
|
||
"chinese",
|
||
"中文"
|
||
],
|
||
"skills": "./skills/",
|
||
"sessionStart": {
|
||
"skill": "using-superpowers"
|
||
},
|
||
"skillInstructions": "Kimi Code tool mapping for Superpowers skills:\n\n- When a Superpowers skill says to ask the user, ask clarifying questions, ask one question at a time, present multiple-choice options, use the terminal for a question, or wait for the user's choice, call Kimi Code's `AskUserQuestion` tool. Do not render those choices as plain assistant text unless `AskUserQuestion` is unavailable or the session is in auto permission mode.\n- For `AskUserQuestion`, provide 1 question with 2-4 concrete options when possible. Put the recommended option first and suffix its label with `(Recommended)`.\n- When a Superpowers skill refers to `TodoWrite`, use Kimi Code's `TodoList` tool.\n- When a Superpowers skill says `Task tool (general-purpose)` or asks you to dispatch an implementer/reviewer subagent, use Kimi Code's `Agent` tool with a Kimi subagent type. Do not pass `general-purpose` as `subagent_type`.\n- For implementation, code review, spec review, quality review, and filled Superpowers subagent prompt templates, call `Agent` with `subagent_type: \"coder\"`, paste the fully filled prompt into `prompt`, and provide a short `description`.\n- For read-only codebase exploration that would take several searches, use `Agent` with `subagent_type: \"explore\"`.\n- For read-only planning or architecture design, use `Agent` with `subagent_type: \"plan\"`.\n- Keep dependent Superpowers subagent steps sequential. Use multiple `Agent` calls, or `run_in_background: true` only when the work is independent and background agents are available.\n- When a Superpowers skill refers to the `Skill` tool, use Kimi Code's native `Skill` tool.\n- Use Kimi Code's `Read`, `Write`, `Edit`, `Bash`, `Grep`, `Glob`, `FetchURL`, `WebSearch`, and MCP tools by their actual exposed names.\n- When a skill asks to search file contents, use `Grep`; when it asks to find files by path or pattern, use `Glob`; when it asks to fetch a URL, use `FetchURL`; when it asks to search the web, use `WebSearch`.",
|
||
"interface": {
|
||
"displayName": "Superpowers 中文版",
|
||
"shortDescription": "面向编程 agent 的规划、TDD、调试、交付工作流（中文增强版）",
|
||
"longDescription": "用 Superpowers 中文版引导 agent 完成头脑风暴、实现规划、测试驱动开发、系统化调试、并行执行、代码审查与分支收尾。在上游 obra/superpowers 之上叠加 4 个中国原创 skill 与多工具适配。",
|
||
"developerName": "jnMetaCode",
|
||
"capabilities": [
|
||
"Interactive",
|
||
"Read",
|
||
"Write"
|
||
],
|
||
"websiteURL": "https://github.com/jnMetaCode/superpowers-zh"
|
||
}
|
||
}
|