hikariming
- 8 skills
- 0 followers
- 6 hours ago last updated
- ▌ Generate Mindmap · hikariming bundleGenerate an evidence-grounded article-level mind map as strict JSON.
- ▌ Ghfind CLI · hikarimingDrive the ghfind CLI to score, scan, roast, and compare GitHub accounts and to browse ghfind.com leaderboards and developer directories from the terminal. Use when the ghfind CLI is installed (or the user wants it installed) and asks to vet, rate, roast, or compare a GitHub user, check if an account is farmed, generate a score badge, or discover developers by language/org/repo. For no-install REST/MCP access to the same engine, prefer the ghfind-score skill.
- ▌ Ghfind Score · hikarimingScore any GitHub account 0-100 for real contribution value and trustworthiness, detect bot/farmed activity, compare two developers, and discover top developers by language/org/project. Use when asked to vet, rate, or judge a GitHub user, check if an account is real or farmed, or find strong developers. Backed by ghfind.com's deterministic open-source engine via a public no-auth REST API and MCP server.
- ▌ Ghfind Project Evaluator · hikariming bundleEvaluate a public GitHub repository as an open-source product for GHFind. Use when a versioned GHFIND_PROJECT_ANALYSIS task requires repository classification, source or runtime verification, evidence-backed product scoring, exposure assessment, and validated JSON/Markdown artifacts.
- ▌ Refresh Site · hikariming跑一整轮站点数据刷新并上线:GitHub 同步(新插件/star)→ 头部插件下载量 → 头部插件安装方式 → 静态快照(首页三条 rail、插件库、排名)→ 构建验证 → 只提交生成物 → 推送触发 Cloudflare 部署。用于「好几天没更新了,把数据刷一遍」,也用于排查某一步为什么没生效。
- ▌ Score Plugins · hikariming对 DSH 插件生态跑一轮综合评分(0-100 + S/A/B/C)。流程:同步 Turso → 采集证据 → AI 按量表评工程规范 → 合成入库 → 重生成静态数据并推送。用于批量评新插件、按 star 阈值扩大覆盖或定期重评。
- ▌ Desktop Market · hikariming维护发给 DSH 桌面端插件市场的安装契约(/market/v1/plugins)——探测插件的安装方式与 npm 最新版本、排查某个插件为什么在桌面端市场里装不了或装到旧版本、核对某个包是否满足桌面端 preview 的七项复核。
- ▌ Track Downloads · hikariming采集头部 DSH 插件的累计下载量(npm + npmmirror 镜像 + GitHub Release 三渠道)写入 Turso。用于定期刷新下载数据、按 star 阈值扩大覆盖、排查某个仓库为什么没有下载数,或在做下载量徽章/排序前确认数据口径。