{"slug": "show-hn-vanilla-web-skill-to-replace-all-javascript-frameworks", "title": "Show HN: Vanilla-web skill to replace all JavaScript frameworks", "summary": "A developer released a publicly reviewed \"skill\" for coding agents that prescribes building web apps with only HTML, CSS and JavaScript — no framework, no bundler and no server logic. The skill was produced agentically: a coordinating agent ran five parallel research agents, a report writer and five reference writers, with a human reviewing and steering between rounds, and every rule in its references carries the link it was derived from. Verification against the example app with both HTML validators, ESLint, Prettier, tsc, a shell test, and axe plus element tests in Chromium, Firefox and WebKit surfaced defects that were corrected, including lazy-loaded island sheets shifting layout, an inline style breaking a strict CSP, a full list re-render dropping keyboard focus, and a form submitted before upgrade losing its input in 4 of 16 runs.", "body_md": "A styleguide skill for building web apps with HTML, CSS and JavaScript only: no framework, no bundler, no server logic. It targets coding agents, but the conventions are the same ones a human team would adopt.\n\n**This skill was developed agentically.** A coordinating agent ran five\nparallel research agents, a report writer, and five reference writers,\nwith a human reviewing and steering between rounds. The chain of evidence\nis kept: every rule in `references/` carries the link it was derived from.\n\nIt was manually reviewed though. Look here is a speling error as proof.\n\n1. **Research.** Five agents each took one subtopic: semantic HTML and\naccessibility, custom elements, module architecture, lazy loading and\nfetching, and state, events, routing and security. They wrote notes\nwith inline citations and flagged gaps and conflicting sources\ninstead of resolving them silently.\n2. **Synthesis.** One agent merged the notes into a report, keeping only\nsourced claims. The human read a summary and challenged it.\n3. **Decisions.** The human set the premises below. The coordinating\nagent recorded them so later drafting could not re-argue them.\n4. **Style study.** The coordinator read the Agent Skills specification,\nAnthropic's skill-authoring guide and this repository's`prompting` standard. It distilled them into rules: one imperative rule per line\nwith its reason, one term per concept, a default plus an escape\nhatch, no dates in the body, and references one level deep.\n5. **Writing.** The coordinator wrote`SKILL.md` , this README and the\ndocument-head reference. Five agents wrote the other references from\nthe notes, under a shared terms table.\n6. **Verification.** The coordinator built the example app and ran every\ngate the skill prescribes: both HTML validators, ESLint, Prettier,\ntsc, the shell test, and axe plus element tests in Chromium, Firefox\nand WebKit. The run found defects in the first draft, and the skill\nwas corrected:\n - Island sheets shipped with lazy modules shifted layout.\n - An inline `