By george4data
Author and validate HTML-first, agent-readable documentation following The Source-Complete Standard (source-complete, no view-time JS, faceted data-* tags, data-source/data-verified provenance, CSS-only tabs, front-door index).
An installable Agent Skill for authoring and validating HTML-first, agent-readable documentation: one static HTML file that serves AI agents first and humans second — no view-time JavaScript, no content duplication.
skills/agentdocs/STANDARD.mdstandard.htmlSTANDARD.md §10).Two workflows: Author a conforming doc (architecture overview, subsystem contract, API reference, data model, UI/wireframe spec, runbook, or front-door index), and Validate an existing doc against an 8-gate conformance checklist.
The five conformance rules in brief: (1) agents read the raw source; (2) source-complete, no
view-time JS; (3) content inline, CSS free; (4) faceted multi-axis data-* tags; (5) one
data-source + data-verified provenance primitive — plus one shared toolkit + one construct
per doc type.
Pick the path that fits your tool. The skill lives at skills/agentdocs/ — that's the only
folder you ever copy.
curl -fsSL https://raw.githubusercontent.com/george4data/agentic_html_doc/main/install.sh | bash
Personal install → ~/.claude/skills/agentdocs. Add --project (when running a local clone's
./install.sh --project) to install into the current repo's ./.claude/skills/ instead.
/plugin updates)/plugin marketplace add george4data/agentic_html_doc
/plugin install agentdocs@agentic-html-doc
gemini extensions install https://github.com/george4data/agentic_html_doc
Loads GEMINI.md, which routes the agent to the skill's operating manual.
git clone --depth 1 https://github.com/george4data/agentic_html_doc.git
cp -R agentic_html_doc/skills/agentdocs ~/.claude/skills/agentdocs
No GitHub auto-install in the web apps:
skills/agentdocs/ folder in the Skills UI.SKILL.md as instructions, attach the
reference/ and templates/ files as knowledge.If you'd rather just tell Claude / Antigravity / another agent to do it, give it the exact path so it doesn't have to explore:
"Install the skill at
https://github.com/george4data/agentic_html_doc— clone it and copyskills/agentdocs/into~/.claude/skills/agentdocs/. Or just run itsinstall.sh."
Ask the agent:
"Use agentdocs to validate
templates/standard.htmlagainst the Source-Complete Standard."
A correct install runs the validation workflow and returns an 8-gate table ending in CONFORMS — the bundled exemplar is conformant by construction.
agentdocs is model-invoked, not a slash command. Describe your task in natural language
("write agent-readable docs for the auth service", "validate these HTML docs") and the agent
loads the skill when it matches. To force it, name it: "use the agentdocs skill to…".
agentic_html_doc/
├── .claude-plugin/
│ ├── marketplace.json ← Claude Code marketplace index (plugin source: ".")
│ └── plugin.json ← Claude Code plugin manifest
├── gemini-extension.json ← Gemini CLI extension manifest
├── GEMINI.md ← Gemini context file
├── install.sh ← one-command installer
├── README.md
├── LICENSE
└── skills/
└── agentdocs/ ← the skill (this is the only folder you copy)
├── SKILL.md ← operating manual (author + validate)
├── reference/ ← STANDARD.md, facet-ontology, constructs, checklist
└── templates/standard.html ← conforming exemplar
MIT — free to use, modify, and redistribute.
Draft v0.1. The base facet vocabulary, a reference author-time (Pandoc) build, and a
docs-specific conformance benchmark are open items — see STANDARD.md §10.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub george4data/agentic_html_doc --plugin agentdocsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.