skills/25-HosungYou-Diverga/skills/doctor/SKILL.md
System diagnostics and health checks for Diverga plugin. OpenClaw-style Check-Report-Fix pattern with 5-layer diagnostics. Triggers: /diverga:doctor, diverga doctor, system check, diagnose, 진단
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research doctorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Version: 11.1.0
Trigger: /diverga:doctor
System diagnostics for the Diverga plugin. Checks plugin health, skill sync, hook enforcement, configuration validity, API keys, and project state. Reports issues with actionable fix commands.
Follows OpenClaw Check-Report-Fix pattern: every detected issue includes a fix recommendation.
When user invokes /diverga:doctor, execute all 7 diagnostic layers sequentially and display results.
Check plugin registration:
~/.claude/plugins/installed_plugins.jsondiverga@diverga entry existsCheck config JSON validity:
~/.claude/plugins/diverga/config/diverga-config.jsonversion, human_checkpoints, languageReport format:
PLUGIN HEALTH
Registration: [PASS - diverga@diverga v11.1.0 | FAIL - not found in installed_plugins.json]
Config file: [PASS - valid JSON | FAIL - missing or invalid]
Config fields: [PASS - all required fields present | WARN - missing: field1, field2]
Fix if FAIL:
Check skill counts match between plugin and local cache:
~/.claude/plugins/diverga/skills/*/SKILL.md~/.claude/skills/diverga-*/SKILL.md (exclude diverga-diverga prefix duplication — count unique skill names)Check for missing skills in local cache:
diverga-{name} exists in local skillsReport format:
SKILL SYNC
Plugin skills: [count] skills in plugin directory
Local skills: [count] skills in local cache
Sync status: [PASS - all synced | WARN - X skills missing locally]
Missing: [list of missing skill names, if any]
Fix if WARN:
Check that the plugin cache matches the installed version:
~/.claude/plugins/diverga/plugin.json → extract version~/.claude/plugins/cache/diverga/diverga/*/plugin.json → list cached versionshooks/hooks.jsonReport format:
PLUGIN CACHE
Installed version: [11.1.0 | FAIL - plugin.json missing]
Cached version: [11.1.0 | WARN - stale cache: 8.0.1 | FAIL - no cache found]
Cache has hooks: [PASS - hooks.json present | FAIL - hooks missing from cache]
Cache has agents: [PASS - agents/ present | WARN - agents/ missing]
Fix if WARN/FAIL:
REPO="/Volumes/External SSD/Projects/Diverga/Diverga-core"
CACHE="$HOME/.claude/plugins/cache/diverga/diverga/11.1.0"
rm -rf "$HOME/.claude/plugins/cache/diverga/diverga/8.0.1"
mkdir -p "$CACHE"
cp -R "$REPO"/{skills,agents,config,hooks,mcp,CLAUDE.md,AGENTS.md,README.md} "$CACHE/"
cp "$REPO/.claude-plugin/plugin.json" "$CACHE/"
Check hook configuration:
~/.claude/plugins/diverga/hooks/hooks.json → verify it exists and has PreToolUse entries~/.claude/settings.json → check if hooks are also configured at global levelecho '{"tool_name":"Skill","tool_input":{"skill":"diverga:c1"}}' | node ~/.claude/plugins/diverga/hooks/prereq-enforcer.mjs → verify it returns valid JSON with continue fieldReport format:
HOOK ENFORCEMENT
Plugin hooks.json: [PASS - exists with Agent+Skill matchers | FAIL - missing or wrong matchers]
Global hooks: [PASS - configured in settings.json | WARN - not in settings.json (relies on plugin)]
Hook executable: [PASS - returns valid JSON | FAIL - execution error]
Matcher check: [PASS - uses "Agent" | FAIL - uses stale "Task" matcher]
Fix if issues found:
Deep validation of diverga-config.json:
~/.claude/plugins/diverga/config/diverga-config.jsonversion field matches "11.1.0"human_checkpoints object exists and has enabled (boolean) and required (array)language is one of: "en", "ko", "auto"model_routing has high, medium, low keys if presentReport format:
CONFIG VALIDITY
Version field: [PASS - 11.1.0 | WARN - version mismatch: found X.Y.Z]
Checkpoints: [PASS - configured | FAIL - missing or malformed]
Language: [PASS - "en" | WARN - unexpected value: "XX"]
Model routing: [PASS - configured | SKIP - not set (using defaults)]
Fix if issues found:
Check 8 environment variables using Bash tool (echo $VAR_NAME):
| Variable | Purpose | Required? |
|----------|---------|-----------|
| GROQ_API_KEY | LLM screening (recommended) | Recommended |
| ANTHROPIC_API_KEY | Claude API | Recommended |
| OPENAI_API_KEY | OpenAI screening | Optional |
| GEMINI_API_KEY | Gemini visualization | Optional |
| SEMANTIC_SCHOLAR_API_KEY | Paper retrieval | Optional |
| OPENALEX_EMAIL | OpenAlex polite pool | Optional |
| SCOPUS_API_KEY | Scopus access | Optional |
| WOS_API_KEY | Web of Science | Optional |
For each variable, use Bash: echo "${VAR_NAME:+configured}" — if output is "configured", it's set; if empty, it's not set.
Report format:
API STATUS
Groq: [configured | NOT SET -> export GROQ_API_KEY=your_key]
Anthropic: [configured | NOT SET -> export ANTHROPIC_API_KEY=your_key]
OpenAI: [configured | not set (optional)]
Gemini: [configured | not set (optional)]
Semantic Scholar: [configured | not set (optional)]
OpenAlex: [configured | not set (optional)]
Scopus: [configured | not set (optional)]
Web of Science: [configured | not set (optional)]
Fix if NOT SET (recommended keys):
export VAR_NAME=your_key_here for each missing recommended keyCheck for active research project:
.research/project-state.yaml exists in current working directoryproject_name, current_stage).research/ directory exists with expected subdirectoriesReport format:
PROJECT STATE
Active project: [project name | No active project]
State file: [PASS - valid | WARN - invalid YAML | SKIP - no project]
Research dir: [PASS - structure intact | WARN - missing subdirs | SKIP - no project]
Fix if issues:
After all 7 layers, display overall status:
══════════════════════════════════════════════
DIVERGA SYSTEM DIAGNOSTICS v11.1.0
══════════════════════════════════════════════
[Layer 1-7 results as shown above]
------------------------------------------
OVERALL: [HEALTHY | X WARNING(S) | X ERROR(S)]
[If issues found, numbered list:]
1. [Issue description] -> [Fix command]
2. [Issue description] -> [Fix command]
...
[If healthy:]
All systems operational. Diverga is ready to use.
Run /diverga:help to see all 24 agents and commands.
══════════════════════════════════════════════
tools
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.