Skip to content
cccskills
FreePublished on GitHub

wjs-evaling-voicedrop-prompts

Use when 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts".

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (2)

  • SKILL.md2.8 KB
  • references/judge-rubric.md1.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

VoiceDrop 挖矿 prompt 评估

harness = 本 skill(协议)+ jianshuo.dev agent/eval/(脚本/数据)。运行时 = 本地 Claude Code。 被测对象 = agent/src/prompts/mine.js 的 MINE_SYSTEM(git 即版本库)。

何时用

用户改了挖矿 prompt(MINE_SYSTEM),想用数据判断改好了还是改坏了,而不是凭感觉看一两次。

流程(按序)

  1. 拿候选 prompt:把候选版 MINE_SYSTEM 文本写到一个临时文件(如 /tmp/cand-prompt.txt);冠军 = 当前 mine.js 的 MINE_SYSTEM(脚本自动读)。
  2. 跑产出:cd ~/code/jianshuo.dev/agent && CLAUDE_API_KEY=$CLAUDE_API_KEY node eval/run-eval.mjs /tmp/cand-prompt.txt <runId>。产出落 eval/runs/<runId>/。先看终端有没有「确定性回退」警告——有就先停,多半是候选 prompt 破坏了 JSON 输出。
  3. 成对盲评:对每条 fixture,dispatch 一个 subagent,喂 references/judge-rubric.md + 该 fixture 的 transcript + 两份产出。A/B 顺序随机(一半 fixture 把 candidate 放 A、一半放 B,记录映射,收到结果后还原成 champion/candidate)。裁判模型用与生成(opus)不同家族的模型。收每条的 {winner, dims, reason}。
  4. 聚合:把还原后的 verdicts(winner ∈ candidate/champion/tie)+ 候选 proxyFails 喂 aggregate(),渲染 renderReport() → 写 eval/runs/<runId>/report.md。
  5. 人工终审:把胜负最接近、分歧最大的 1–2 条产出并排摆给用户。机器只筛掉明显更差的,文风最后一票是用户。
  6. 晋级:仅当 decision==="promote"(胜率 ≥70% 且无回退)且用户点「认可」——把候选写回 agent/src/prompts/mine.js 的 MINE_SYSTEM,commit(message 附 runId 与胜率),并跑 npm test 确认没破坏。否则保留报告、不动生产版。

边界

  • 只评挖矿 prompt(MINE_SYSTEM/MINE_SYSTEM_FORCE)。审核/语音编辑 prompt 是不同 eval 模式,不在本 skill。
  • 不测成本/缓存/延迟(本地缓存行为≠生产);不做无人值守。
  • 真实金标集要 ≥10 条才可信(见 agent/eval/fixtures/README.md 的补充流程);种子 2 条只够自测流程。

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

王建硕的思维框架与表达方式。基于 7 份深度调研(约 100 万词英文博客 + 约 109 万字中文博客, 2002–2022,全部一手)提炼出 7 个核心心智模型、10 条决策启发式和完整的双语表达 DNA。 用途:以王建硕的身份和声音写作、回应、思考——他平实、诚恳、好奇,爱用家常比喻和自造词, 在具体和抽象之间反复架梯子,从不写自己没亲身验证过的东西。 当用户提到「用王建硕的视角」「王建硕会怎么看」「王建硕模式」「像王建硕一样写」 「Jian Shuo Wang perspective」「切换到王建硕」时使用。 即使用户只是说「帮我用王建硕的角度想想」「如果是王建硕会怎么写这篇」也应触发。 一旦激活,本次对话后续所有回应都保持王建硕身份,直到用户明确说「退出」—— 不需要每轮重新点名。 不适用:用户要的是关于王建硕本人的客观介绍 / 事实查询(「王建硕是谁」「他哪年创业的」), 那种问题正常回答即可,不要进入角色扮演。

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

Use when the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store", "为什么没新build", or wants a holistic state-of-the-project check covering unmerged branches, stalled PRs, failed GitHub Actions, stale builds, plan drift (TODOS.md / ROADMAP), unreleased commits, and log errors. Runs read-only investigation, presents a grouped checklist, fixes only after explicit user confirmation. Aware of the Cathier iOS app workflow (Xcode + fastlane + auto-merge @claude PRs from in-app feedback).

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

Use when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or soft-muxed as a togglable track. Also handles the final composite step for the localization pipeline — burn subs, mix a dub track, and keep the original audio as a low-volume bed, all in ONE ffmpeg encode (no cascade). Verifies libass availability and auto-downloads a static evermeet ffmpeg build when Homebrew's stripped binary lacks it. Triggers — "烧字幕", "硬字幕", "burn subtitles", "burn-in subs", "embed subtitle", "soft mux SRT", "把字幕烧进视频", "做最终合成".

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

Use when the user complains about spam on his X/Twitter posts — 同城面付 / 寻固炮 / 线下上门 / 免费破处 这类引流号在他推文下刷的 emoji 垃圾回复 — and wants them removed. Covers the last 7 days (X recent-search window). Triggers — "把这些spam删掉", "清理X垃圾回复", "推文下面好多引流号", "clean spam replies", "/wjs-cleaning-spam".

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

Use when the user wants a 王建硕-style WeChat article (article.md) turned into a narrated short MP4 video — TTS voiceover via 火山引擎 Volcano TTS, HyperFrames CSS/GSAP animation per scene, subtle SFX, abstract watercolor background, full pipeline rendering to 1080×1920 portrait MP4 (30-90s). Triggers — "把这篇文章做成视频", "做一个解说视频", "讲解视频", "/wjs-converting-text-to-video".

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

Use when migrating a WordPress site to a Hugo static site on GitHub Pages from a WXR export (.xml) plus the wp-content/uploads folder — preserving /archives/<id>/ URLs, localizing images, and deploying via GitHub Actions. Triggers — "把 WordPress 迁成 Hugo", "wordpress 转静态站", "migrate WordPress to Hugo", "WXR to Hugo", "publish WordPress to GitHub Pages", "/wjs-converting-wp-to-hugo".

The English summary is being prepared. Showing the original description.

jianshuo/claude-skills137Updated Oct 16, 2026

See all skills by jianshuo

Report a problem with this skill