tcsenpai

Specification Website Skill — Testing skill for Claude Code

Testing community

Offline agent skill bundling specification.website (128 topics) for Claude Code and other SKILL.md-compatible agents.

How to install Specification Website Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tcsenpai/specification-website-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Specification Website Skill does

Offline agent skill bundling specification.website (128 topics) for Claude Code and other SKILL.md-compatible agents. Spec content CC BY 4.0 by Joost de Valk.

Alternatives in Testing

Flow Spec — NLSpec authoring — use when you need a structured specification from multi-AI research and consensus 2.8k ★
Agent Plugins Spec — Agent Plugins Specification v1.0.0 — A minimal standard for packaging agent extensions into distributable plug 1.2k ★
Skill Spec — SKILL.md specification 248 ★

README

specification-website skill

[![skills.sh](https://skills.sh/b/tcsenpai/specification-website-skill)](https://skills.sh/tcsenpai/specification-website-skill)

An agent skill that bundles the full content of [specification.website](https://specification.website) — the platform-agnostic specification of what a good website does — for offline use by Claude Code and any other agent that follows the SKILL.md convention.

All 128 topic pages across 10 categories ship inside this repo as plain Markdown, so an agent can answer questions about web foundations, SEO, accessibility, security, well-known URIs, agent readiness, performance, privacy, resilience, and internationalisation without a network round-trip.

What's inside

SKILL.md                          entry point with frontmatter — agents read this first
references/
├── checklist.md                  full required / recommended / avoid checklist
├── topics-index.md               all 128 topics, grouped by category, with status + summary
├── categories/.md          per-category index, topics sorted by status
├── topics//.md   the full text of every spec page (128 files)
├── llms-index.txt                upstream llms.txt index
├── llms-full.txt                 every topic concatenated (≈ 9k lines)
└── mcp-and-fetch.md              how to query the live MCP server / HTTP endpoints

Each topic file carries the upstream YAML frontmatter — `title`, `slug`, `category`, `status` (`required` / `recommended` / `optional` / `avoid`), `summary`, `updated`, and a list of `sources` pointing at primary standards (WHATWG, W3C, IETF RFCs, IANA, WCAG, schema.org). Cite the sources, not the spec page.

Installation

Via the `skills` CLI (recommended)

The skill is listed in the open [skills.sh](https://skills.sh) ecosystem and installs with one command — no manual clone, no path fiddling. The CLI supports Claude Code, OpenCode, Codex, Cursor, Windsurf, and ~50 other agents.