kkkkhazix/khazix-skills
5 skills11.4k installs95.6k starsGitHub
Install
npx skills add https://github.com/kkkkhazix/khazix-skillsSkills in this repo
1Neat Freakneat-freak acts as a knowledge base editor that audits agent memory, CLAUDE.md or AGENTS.md, and docs folders after development milestones. It distinguishes three audiences: agent memory for cross-session facts, project root markdown for AI conventions, and docs plus README for humans and downstream teams. A promote mechanism moves stable lessons into docs or CLAUDE.md and deletes or shrinks memory files when knowledge belongs in authoritative documentation rather than append-only memory indexes capped at 200 lines and 25KB. Step zero measures file sizes and flags unhealthy memory thicker than docs, then step one mechanically lists every memory and markdown file before judging changes. Updates follow a change-impact matrix for routes, environment variables, database tables, and cross-project dependencies, applying edits with merge-over-append and absolute dates. The workflow ends with a checklist for contradictions, missing API docs, and relative-time phrases plus a concise change summary grouped by project.2.9kinstalls2Khazix WriterThe khazix-writer skill drafts long-form Chinese WeChat public account articles in the voice of digital life Khazix, a three-year AI content creator. It is for articles, continuations, and expansions from PDFs, briefs, news links, or voice transcripts, not short social posts or title-only generation. The workflow starts with material review and HKR topic quality checks for Happy, Knowledge, and Resonance, then clarifies AI versus human boundaries for evidence, analogies, and firsthand experience. Writing follows article archetypes such as investigation, product experience, phenomenon interpretation, tool sharing, and methodology essays with oral rhythm, deliberate breaks, cultural elevation, and strict banned AI phrases and punctuation rules. A four-layer self-check covers hard bans, style consistency, content depth, and live-person feel before output. The skill expects human-provided experiences and angles with AI filling structure, background, and expansion, then human rewrite before final QC. Typical length targets four thousand to eight thousand Chinese characters with short paragraphs and signature footer blocks.2.8kinstalls3Hv AnalysisHorizontal-Vertical Analysis is a structured deep-research skill that traces a subject timeline on the vertical axis and compares it against competitors on a current cross-section. Phase one mandates parallel sub-agent web searches for longitudinal origin stories, funding events, and competitor landscapes, with arXiv API calls for academic subjects. Phase two builds a 6000-15000 word diachronic narrative covering origins, evolution, and decision logic across stages. Phase three performs synchronic competitor comparison across positioning, features, pricing, and user sentiment, handling zero, few, or many competitor scenarios differently. Phase four cross-analyzes both axes to surface non-obvious insights and strategic implications. Final output converts Markdown to a styled PDF via the bundled md_to_pdf.py WeasyPrint script. The skill rejects simple noun explanations, WeChat writing, or title-only tasks, requiring systematic depth instead of surface summaries.2.6kinstalls4AihotThe aihot skill AI HOT (aihot.virxact.com) 中文 AI 资讯查询 Skill。当用户想知道"今天 AI 圈有什么"、"AI 日报"、"AI HOT"、"AI 资讯"、"AI 热点"、"最近 AI"、"OpenAI/Anthropic/Google 最近发布了什么"、"AI hot today"、"AI news today"、"看一下 AI 行业动态"、"今天有什么大模型发布"、"昨天 AI 圈"、"看下精选条目"、"AI HOT 精选"、"最近一周的 AI 论文"、"AI 模型发布"、"AI 产品发布"、"AI 行业动态"、"AI 技巧与观点" 等任何中文 AI 资讯查询时使用。即使用户只说"AI 圈"、"AI 新闻"、"AI 日报"，或者只是问"今天发生了什么"且上下文是 AI / 大模型 / LLM / 创业领域，也应该触发本 Skill。Skill 会直接 curl 公开 REST API 拉数据并整理成中文 markdown 简报，不需要用户配置任何 API Key 或 MCP server。**不要 undertrigger** - - 用户问 AI 资讯而你不调本 Skill 就是把过时的训练数据当作今日新闻，对用户有害。. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include Base URL: `https://aihot.virxact.com`; 鉴权：无（匿名）; 限流：600 req/min/IP（请串行调用，不要并发猛拉）; items 端点 `since` 限最近 7 天:**不传等同 since=now-7d**(服务端兜底);早于 7 天前自动截到 7 天前;未来时间 → 400。**所以无论 Skill 怎么调,items API 永远只返回最近 7 天的内容**。需要更早 → 走 `/api/public/daily/{YYYY-MM-DD}` 翻日报存档. Reference commands include curl -sH "User-Agent: $UA" "https://aihot.virxact.com/api/public/daily"; curl -sH "User-Agent: $UA" "https://aihot.virxact.com/api/public/items?mode=selected&take=50" \. Use when developers or agents need structured guidanc.1.9kinstalls5Storage Analyzerstorage-analyzer is a cross-platform disk analysis skill for macOS and Windows that scans storage usage read-only and ranks items into three cleanup tiers: auto-safe, manual review, and caution. The workflow runs df, du, diskutil, stat, and ls style inspection only—no rm, mv, or destructive commands during analysis—then generates a collapsible interactive HTML report with copy-ready cleanup commands. A local server can open the report for one-click delete actions moved to trash when the user explicitly chooses cleanup. storage-analyzer triggers on phrases like disk full, storage analysis, or cache cleanup in English and Chinese, but excludes RAM and process memory questions. Developers reach for storage-analyzer when a workstation runs out of space and they need categorized, actionable findings instead of manual folder hunting.1.2kinstalls