Validate and enforce standard YAML frontmatter on research documents with JD-aware path resolution. Use when creating, editing, or validating research files, when user mentions "research metadata", "research frontmatter", "research staleness", "validate research", "RD-rules", or "research docs validation".
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Enforce standard YAML frontmatter on research documents so GitHub renders metadata as a table and readers can judge staleness.
# Validate all research documents
uv run ${CLAUDE_SKILL_DIR}/scripts/validate_research_docs.py --format text
# Check staleness only
uv run ${CLAUDE_SKILL_DIR}/scripts/validate_research_docs.py --staleness-only
# Resolve research path (JD-aware)
uv run ${CLAUDE_SKILL_DIR}/scripts/resolve_research_path.py --format json
# Override research directory
uv run ${CLAUDE_SKILL_DIR}/scripts/validate_research_docs.py --research-dir docs/30-research
Every research file MUST have these 5 fields:
---
title: "Human-readable title"
version: "1.0.0"
status: Published # Published | Draft | Living Document
created: YYYY-MM-DD
last_updated: YYYY-MM-DD
---
Optional fields (slug, tags, aliases, promoted_at, last_refreshed, sources) MAY follow.
The skill auto-detects Johnny.Decimal structure:
.jd-config.json at project root30){root}/{prefix}-{name}/ (e.g. docs/30-research/)docs/research/ if no JD configThis applies to both validation and the deep-research promote workflow.
| Rule | Severity | Check |
|---|---|---|
| RD001 | ERROR | Missing YAML frontmatter |
| RD002-006 | ERROR | Missing required field (title, version, status, created, last_updated) |
| RD007 | ERROR | Invalid status value |
| RD008-009 | WARNING | Invalid date format |
| RD010 | WARNING | Invalid version format |
| RD011 | WARNING | Missing Executive Summary section |
| RD012 | WARNING | Missing References section |
| RD013 | ERROR | Research doc not in README.md index |
| RD014 | WARNING | README index metadata mismatch |
| RD015 | WARNING | Index references missing file |
| RD016 | WARNING | Stale last_updated vs git history |
The research README.md MUST use these columns:
| Topic | Version | Status | Created | Last Updated |
last_updated qualify for deep scanning30-research is the default research home in JD structureNew research files should follow the TEMPLATE.md in the research directory.
See WORKFLOW.md for detailed procedures. See EXAMPLES.md for usage examples. See TROUBLESHOOTING.md for common issues.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.
The English summary is being prepared. Showing the original description.
Analyze system architecture, module structure, API contracts, data models, and code patterns. Use when designing systems, reviewing module boundaries, evaluating API designs, analyzing data models, checking pattern conformance, tracing decisions, or reviewing frontend architecture. Triggers: "architecture", "module design", "API design", "data model", "boundaries", "patterns", "decisions", "frontend architecture".
The English summary is being prepared. Showing the original description.
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.
The English summary is being prepared. Showing the original description.
Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.
The English summary is being prepared. Showing the original description.
Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.
The English summary is being prepared. Showing the original description.
Interactive Claude Code environment setup wizard. Detects existing configuration, guides through best-practice setup for Global CLAUDE.md, project scaffolding, MCP servers, hooks, custom agents, keybindings, and settings. Use when user runs /devtools:code-env-setup, mentions "setup claude code", "configure claude", "claude code setup", "environment setup", or "initialize claude code".
The English summary is being prepared. Showing the original description.