By quadralay
Remove signs of AI-generated writing from text. Detects and fixes 25 common AI writing patterns based on Wikipedia's Signs of AI writing guide.
AI agent skills for WebWorks ePublisher and Markdown++ authoring.

In Claude Code:
/plugin marketplace add quadralay/webworks-agent-skills
/plugin install webworks-agent-skills@webworks-agent-skills
Migrating from
webworks-claude-skills? This repo was renamed in 3.0.0. Uninstall the old plugin (/plugin uninstall webworks-claude-skills) before installing the new one. Any skill invocations or permission entries in your.claude/settings.local.jsonreferencingwebworks-claude-skills:*must be updated towebworks-agent-skills:*.
All skills activate automatically based on your project context.
| Skill | What It Does |
|---|---|
| epublisher | ePublisher project knowledge, file resolver hierarchy, customization patterns |
| markdown-integration | ePublisher integration patterns for Markdown++ sources (variable resolution, style mapping to Stationery, per-target conditions) |
| automap | Automated publishing with AutoMap CLI |
| reverb2 | Reverb 2.0 output testing, CSH analysis, SCSS theming |
| customization-audit | Audit advanced customizations (overrides) on upgrade — drift detection, fork-point discovery, and removal of retired/orphan/cruft/redundant overrides |
| claude-md-audit | Audit and shrink CLAUDE.md / AGENTS.md / GEMINI.md to behaviorally-focused entries the agent can't self-discover |
| humanizer | Remove signs of AI-generated writing from text — vendored from blader/humanizer with planned divergence for agent-readable input |
For Markdown++ format syntax, validation, and authoring best practices, install the companion plugin quadralay/markdown-plus-plus. The markdown-integration skill in this plugin defers to it for format-level concerns and focuses on the ePublisher integration layer.
Publishing:
You: "Publish the project with all targets"
Claude: Detects AutoMap, runs publish, reports results
Testing:
You: "Test the Reverb output for JavaScript errors"
Claude: Launches browser, checks console, reports issues
Markdown++ integration:
You: "Why does $product_name; render as literal text in the PDF target?"
Claude: Walks the variable resolution hierarchy (Stationery → project → target → job file)
and identifies which level is missing the value
Theming:
You: "Change the primary color to #2563eb"
Claude: Guides you through SCSS variable overrides with proper cascade mappings
Agent context file audit:
You: "Audit our CLAUDE.md — it's gotten bloated"
Claude: Backs up to CLAUDE.md.bak, then reduces to entries that prevent
real agent mistakes (removes discoverable architecture, tech lists,
directory layouts)
| Skill | Platform | Requirements |
|---|---|---|
| epublisher | Windows | ePublisher 2024.1+ |
| markdown-integration | Windows | ePublisher 2024.1+ (paired with quadralay/markdown-plus-plus for format syntax) |
| automap | Windows | ePublisher + AutoMap |
| reverb2 | Windows | ePublisher + browser |
| customization-audit | Windows | ePublisher 2024.1+ (multiple installed versions enable 3-way) |
| claude-md-audit | Any | Claude Code |
| humanizer | Any | Claude Code or Claude Desktop |
See CONTRIBUTING.md for guidelines.
MIT License - see LICENSE.
🛠️ Built for WebWorks ePublisher | 🤖 Powered by Claude Code
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 quadralay/webworks-agent-skills --plugin humanizerComplete skills suite for WebWorks ePublisher platform including Markdown++ authoring, project management, AutoMap publishing automation, and Reverb output testing
Complete skills suite for WebWorks ePublisher platform including project management, Markdown++ source integration, AutoMap publishing automation, and Reverb output testing
Authoritative reference for Markdown++ syntax including variables, conditions, custom styles, file includes, markers, multiline tables, and combined commands. Includes validation and alias generation scripts.
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.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
Connect to Atlassian products including Jira and Confluence. Search and create issues, access documentation, manage sprints, and integrate your development workflow with Atlassian's collaboration tools.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).