[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-74864":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":35,"readmeContent":36,"aiSummary":37,"trendingCount":16,"starSnapshotCount":16,"syncStatus":15,"lastSyncTime":38,"discoverSource":39},74864,"Waza","tw93\u002FWaza","tw93","🥷 Engineering habits you already know, turned into skills Claude can run.","https:\u002F\u002Fx.com\u002FHiTw93\u002Fstatus\u002F2041312649510822103",null,"Python",5658,341,13,2,0,106,208,978,318,38.6,"MIT License",false,"main",[26,27,28,29,30,31,32,33,34],"claude","claude-code","des","design","engineer","lear","skil","skills","superpowers","2026-06-12 02:03:29","\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgw.alipayobjects.com\u002Fzos\u002Fk\u002F2h\u002Fwaza.svg\" width=\"120\" \u002F>\n  \u003Ch1>Waza\u003C\u002Fh1>\n  \u003Cp>\u003Cb>Engineering habits you already know, turned into skills AI agents can run.\u003C\u002Fb>\u003C\u002Fp>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza\u002Factions\u002Fworkflows\u002Ftest.yml\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Ftw93\u002FWaza\u002Ftest.yml?branch=main&style=flat-square&label=tests\" alt=\"Tests\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Ftw93\u002FWaza?style=flat-square\" alt=\"Stars\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza\u002Freleases\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Ftag\u002Ftw93\u002FWaza?label=version&style=flat-square\" alt=\"Version\">\u003C\u002Fa>\n  \u003Ca href=\"LICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-blue.svg?style=flat-square\" alt=\"License\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Ftwitter.com\u002FHiTw93\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Ffollow-Tw93-red?style=flat-square&logo=Twitter\" alt=\"Twitter\">\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cbr\u002F>\n\n## Why\n\nWaza (技, わざ) is a Japanese martial arts term for technique: a move practiced until it becomes instinct.\n\nA good engineer does not just write code. They think through requirements, review their own work, debug systematically, design interfaces that feel intentional, and read primary sources. They write clearly, and learn new domains by producing output, not consuming content.\n\nAI is more capable than most engineers at raw output. But without structure, that capability drifts into generic, imprecise work. Waza channels it into precision: eight skills that set clear goals and constraints, then let the model do what it does best.\n\nPart of a trilogy: [Kaku](https:\u002F\u002Fgithub.com\u002Ftw93\u002FKaku) (書く) writes code, [Waza](https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza) (技) drills habits, [Kami](https:\u002F\u002Fgithub.com\u002Ftw93\u002FKami) (紙) ships documents. Think of them as a family: Kaku is the dad, Waza the big sister, Kami the little sister.\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgw.alipayobjects.com\u002Fzos\u002Fk\u002Fqa\u002Fwaza_repaired_v4.svg\" width=\"1000\" \u002F>\n\u003C\u002Fdiv>\n\n## Skills\n\nEach engineering habit gets an installed skill. In Claude Code, type the slash command. In Codex, invoke the installed skill by name and follow the same playbook.\n\n| Skill | When | What it does |\n| :--- | :--- | :--- |\n| [`\u002Fthink`](skills\u002Fthink\u002FSKILL.md) | Before building anything new | Challenges the problem, pressure-tests the design, and produces a decision-complete plan another agent can implement. |\n| [`\u002Fdesign`](skills\u002Fdesign\u002FSKILL.md) | Building frontend interfaces | Produces distinctive UI, including screenshot-driven aesthetic iteration, with a committed direction rather than generic defaults. |\n| [`\u002Fcheck`](skills\u002Fcheck\u002FSKILL.md) | After a task, before merging or release | Reviews the diff, extracts project-specific constraints, handles approved release\u002Fpublish\u002Fpush\u002Freaction follow-through, and verifies with evidence. |\n| [`\u002Fhunt`](skills\u002Fhunt\u002FSKILL.md) | Any bug, regression, or unexpected behavior | Systematic debugging. Root cause confirmed before any fix is applied, especially when something used to work. |\n| [`\u002Fwrite`](skills\u002Fwrite\u002FSKILL.md) | Writing or editing prose | Rewrites prose to sound natural in Chinese and English. Cuts stiff, formulaic phrasing. |\n| [`\u002Flearn`](skills\u002Flearn\u002FSKILL.md) | Diving into an unfamiliar domain | Six-phase research workflow: collect, digest, outline, fill in, refine, then self-review and publish. |\n| [`\u002Fread`](skills\u002Fread\u002FSKILL.md) | Any URL or PDF | Fetches content as clean Markdown with platform-specific routing. Special handling for GitHub, PDFs, WeChat, and Feishu. |\n| [`\u002Fhealth`](skills\u002Fhealth\u002FSKILL.md) | Auditing Agent Health | Checks Codex, Claude Code, project instructions, verifier output, and AI maintainability with a budget-aware summary pass before deep inspection. |\n\nEach skill is a folder with reference docs, helper scripts, and gotchas from real failures.\n\n## Install and Update\n\nMost users should install Waza globally, so the same skills are available in every project.\n\n**Claude Code**\n\n```bash\nnpx skills add tw93\u002FWaza -a claude-code -g -y\n```\n\nThis installs `\u002Fthink`, `\u002Fdesign`, `\u002Fcheck`, `\u002Fhunt`, `\u002Fwrite`, `\u002Flearn`, `\u002Fread`, and `\u002Fhealth`. Install just one with `npx skills add tw93\u002FWaza --skill think -a claude-code -g -y`.\n\n**Codex**\n\n```bash\nnpx skills add tw93\u002FWaza -a codex -g -y\n```\n\nInstall just one with `npx skills add tw93\u002FWaza --skill think -a codex -g -y`. Codex sessions can invoke installed skills by name or link to the installed `SKILL.md` path shown by `npx skills path tw93\u002FWaza`.\n\n**Claude Code plugin marketplace**\n\n```bash\n\u002Fplugin marketplace add tw93\u002FWaza\n\u002Fplugin install waza@waza\n```\n\nUse the bundle for now. Per-skill marketplace entries like `waza-think@waza` are temporarily affected by a Claude Code v2.1.136+ path-validation regression; until upstream fixes it, install one skill with the `npx skills add ... --skill` path above.\n\n**Claude Desktop**\n\nDownload [waza.zip](https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza\u002Freleases\u002Flatest\u002Fdownload\u002Fwaza.zip), open Customize > Skills > \"+\" > Create skill, and upload the ZIP.\n\n**Update**\n\n```bash\nnpx skills update -g -y\n```\n\nMarketplace installs use `claude plugin update \u003Cskill>`. Claude Desktop users can replace the old skill with the latest [waza.zip](https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza\u002Freleases\u002Flatest\u002Fdownload\u002Fwaza.zip).\n\n**Compatibility**\n\n`\u002Fhealth` now supports Agent Health for both Claude Code and Codex. It understands `AGENTS.md`, `CLAUDE.md`, Copilot\u002FGemini instruction files, Codex config summaries, Claude hooks\u002FMCP when present, verifier logs, and AI maintainability signals. It defaults to summary mode and only deepens when you ask for a deep\u002Ffull audit or when the summary pass cannot classify the risk.\n\n## Project Context\n\nWaza keeps the generic programmer habits inside the public skill. `\u002Fcheck` becomes project-aware by reading the target repository's public context and the user's task constraints.\n\n- Project commands come from README files, package manifests, Makefiles, CI workflows, and explicit user instructions.\n- Project hard stops include generated artifacts, protected files, version synchronization, release assets, and domain-specific safety risks.\n- Public docs and examples must not include credentials, certificate paths, private key filenames, tokens, or personal machine details.\n\nSee [`skills\u002Fcheck\u002Freferences\u002Fproject-context.md`](skills\u002Fcheck\u002Freferences\u002Fproject-context.md) for the review context template.\n\n## Chaining Skills\n\nSkills are designed to be chained together, but transitions are manual. Each skill stops after completing its task and waits for you to decide the next step.\n\n**Common workflows:**\n\n- **Design a feature**: `\u002Fthink` → approve → say \"implement X\" → `\u002Fcheck` → merge\n- **Ship a fix**: `\u002Fhunt` → fix → `\u002Fcheck` → release\u002Fpublish\u002Fpush\u002Fissue follow-through\n- **Research and write**: `\u002Fread` (fetch sources) → `\u002Flearn` (synthesize) → `\u002Fwrite` (polish)\n- **Debug and verify**: `\u002Fhunt` (find root cause) → fix → `\u002Fcheck` (review changes)\n\nEach arrow represents a manual user action. Skills don't automatically trigger each other.\n\n## Extras\n\n### Statusline\n\nA minimal statusline for Claude Code: context window, 5-hour quota, and 7-day quota.\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgw.alipayobjects.com\u002Fzos\u002Fk\u002Fy9\u002FRUgevg.png\" width=\"1000\" \u002F>\n\u003C\u002Fdiv>\n\nColor coding: green below 70%, yellow at 70-85%, red above 85% for context; blue, magenta, red for quota thresholds. No progress bars, no noise.\n\n```bash\ncurl -sL https:\u002F\u002Fraw.githubusercontent.com\u002Ftw93\u002FWaza\u002Fmain\u002Fscripts\u002Fsetup-statusline.sh | bash\n```\n\n**Codex**\n\nCodex has native statusline items. Add to `~\u002F.codex\u002Fconfig.toml`:\n\n```toml\n[tui]\nstatus_line = [\"model-with-reasoning\", \"current-dir\", \"context-used\", \"five-hour-limit\", \"weekly-limit\"]\nstatus_line_use_colors = true\n```\n\nNote: Codex shows remaining quota, while the Claude Code statusline above shows used percentage. Upstream does not yet offer used-percentage items (e.g. `five-hour-used` \u002F `weekly-used`).\n\n### English Coaching\n\nOptional rule for English practice. When your prompt contains an English mistake, the agent appends a short 😇 correction; Chinese-only prompts stay untouched.\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fgw.alipayobjects.com\u002Fzos\u002Fk\u002F24\u002FvfkGOi.png\" width=\"1000\" \u002F>\n\u003C\u002Fdiv>\n\n```bash\n# Claude Code\ncurl -sL https:\u002F\u002Fraw.githubusercontent.com\u002Ftw93\u002FWaza\u002Fmain\u002Fscripts\u002Fsetup-english-coaching.sh | bash -s -- claude-code\n\n# Codex\ncurl -sL https:\u002F\u002Fraw.githubusercontent.com\u002Ftw93\u002FWaza\u002Fmain\u002Fscripts\u002Fsetup-english-coaching.sh | bash -s -- codex\n```\n\n### Anti-Patterns\n\nOptional always-on guardrails for cross-skill behaviors: stop acting before reading, no hallucinated paths, no scope creep, no unsolicited summaries. Skill-agnostic, applies in every session.\n\n```bash\ncurl -sL https:\u002F\u002Fraw.githubusercontent.com\u002Ftw93\u002FWaza\u002Fmain\u002Fscripts\u002Fsetup-anti-patterns.sh | bash -s -- claude-code\n```\n\nUse `codex` instead of `claude-code` for Codex.\n\n## Uninstall\n\n```bash\nnpx skills remove tw93\u002FWaza -g\nrm -f ~\u002F.claude\u002Fstatusline.sh\nrm -f ~\u002F.claude\u002Frules\u002Fenglish.md\nrm -f ~\u002F.claude\u002Frules\u002Fanti-patterns.md\n```\n\nFor Claude Desktop, delete Waza from Customize > Skills. For Codex rule installs, remove the marked Waza block from `~\u002F.codex\u002FAGENTS.md`.\n\n## Background\n\nTools like Superpowers and gstack are impressive, but they are heavy. Too many skills, too much configuration, too steep a learning curve for engineers who just want to get things done.\n\nThere's also a subtler problem. Every rule the author writes becomes a ceiling. The model can only do what the instructions say and can't go further. Waza goes the other direction. Each skill sets a clear goal and the constraints that matter, then steps back. As models improve, that restraint pays compound interest.\n\nEight skills for the habits that actually matter. Each does one thing, has a clear trigger, and stays out of the way. Not complete by design, just the right amount done well.\n\nBuilt from patterns across real projects, refined through actual use. Every gotcha traces to a real failure: a wrong code path that took four rounds to find, a release posted before artifacts were uploaded, a server restarted eight times without reading the error. 30 days, 300+ sessions, 7 projects, 500 hours.\n\nThe `\u002Fhealth` skill grew from the six-layer Claude Code framework described in [this post](https:\u002F\u002Ftw93.fun\u002Fen\u002F2026-03-12\u002Fclaude.html), and now extends it into Agent Health for Codex, Claude Code, verifier surfaces, and AI maintainability.\n\n## Support\n\n- If Waza helped you, [share it](https:\u002F\u002Ftwitter.com\u002Fintent\u002Ftweet?url=https:\u002F\u002Fgithub.com\u002Ftw93\u002FWaza&text=Waza%20-%20AI%20coding%20skills%20for%20the%20complete%20engineer.) with friends or give it a star.\n- Got ideas or bugs? Open an issue or PR, feel free to contribute your best AI model.\n- I have two cats, TangYuan and Coke. If you think Waza delights your life, you can feed them \u003Ca href=\"https:\u002F\u002Fcats.tw93.fun?name=Waza\" target=\"_blank\">canned food 🥩\u003C\u002Fa>.\n\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fcats.tw93.fun?name=Waza\">\u003Cimg src=\"https:\u002F\u002Fcdn.jsdelivr.net\u002Fgh\u002Ftw93\u002Fsponsors@main\u002Fassets\u002Fsponsors.svg\" width=\"1000\" loading=\"lazy\" \u002F>\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n## License\n\nMIT License. Feel free to use Waza and contribute.\n","Waza 是一个将工程师已知的习惯转化为AI可执行技能的项目。它通过Shell脚本定义了一系列能够帮助提高工程质量和效率的技能，如问题思考、界面设计、代码审查和系统调试等，这些技能旨在为AI代理设置明确的目标和约束条件，从而使其生成更加精准的结果。特别适用于需要提升软件开发流程质量、加强团队协作以及希望利用AI辅助完成复杂任务的场景。该项目采用MIT许可证开放源码，并拥有活跃的社区支持。","2026-06-11 03:51:10","high_star"]