Agent skill
claude-skills-troubleshooting
Diagnose and resolve Claude Code plugin and skill issues. This skill should be used when plugins are installed but not showing in available skills list, skills are not activating as expected, or when troubleshooting enabledPlugins configuration in settings.json. Triggers include "plugin not working", "skill not showing", "installed but disabled", or "enabledPlugins" issues.
Install this agent skill to your Project
npx add-skill https://github.com/daymade/claude-code-skills/tree/main/claude-skills-troubleshooting
SKILL.md
Claude Skills Troubleshooting
Overview
Diagnose and resolve common Claude Code plugin and skill configuration issues. This skill provides systematic debugging workflows for plugin installation, enablement, and activation problems.
Quick Diagnosis
Run the diagnostic script to identify common issues:
python3 scripts/diagnose_plugins.py
The script checks:
- Installed vs enabled plugins mismatch
- Missing enabledPlugins entries in settings.json
- Stale marketplace cache
- Invalid plugin configurations
Common Issues
Issue 1: Plugin Installed But Not Showing in Available Skills
Symptoms:
/pluginshows plugin as installed- Skill not appearing in Skill tool's available list
- Plugin metadata exists in
installed_plugins.json
Root Cause: Known bug (GitHub #17832) - plugins are added to installed_plugins.json but NOT automatically added to enabledPlugins in settings.json.
Diagnosis:
# Check if plugin is in installed_plugins.json
cat ~/.claude/plugins/installed_plugins.json | grep "plugin-name"
# Check if plugin is enabled in settings.json
cat ~/.claude/settings.json | grep "plugin-name"
Solution:
# Option 1: Use CLI to enable
claude plugin enable plugin-name@marketplace-name
# Option 2: Manually edit settings.json
# Add to enabledPlugins section:
# "plugin-name@marketplace-name": true
Issue 2: Understanding Plugin State Architecture
Key files:
| File | Purpose |
|---|---|
~/.claude/plugins/installed_plugins.json |
Registry of ALL plugins (installed + disabled) |
~/.claude/settings.json → enabledPlugins |
Controls which plugins are ACTIVE |
~/.claude/plugins/known_marketplaces.json |
Registered marketplace sources |
~/.claude/plugins/cache/ |
Actual plugin files |
A plugin is active ONLY when:
- Exists in
installed_plugins.json(registered) - Listed in
settings.json→enabledPluginswith valuetrue
Issue 3: Marketplace Cache Stale
Symptoms:
- GitHub has latest changes
- Install finds plugin but gets old version
- Newly added plugins not visible
Solution:
# Update marketplace cache
claude plugin marketplace update marketplace-name
# Or clear and re-fetch
rm -rf ~/.claude/plugins/cache/marketplace-name
claude plugin marketplace update marketplace-name
Issue 4: Plugin Not Found in Marketplace
Common causes (in order of likelihood):
-
Local changes not pushed to GitHub - Most common!
bashgit status git push claude plugin marketplace update marketplace-name -
marketplace.json configuration error
bashpython3 -m json.tool .claude-plugin/marketplace.json -
Skill directory missing
bashls -la skill-name/SKILL.md
Diagnostic Commands Reference
| Purpose | Command |
|---|---|
| List marketplaces | claude plugin marketplace list |
| Update marketplace | claude plugin marketplace update {name} |
| Install plugin | claude plugin install {plugin}@{marketplace} |
| Enable plugin | claude plugin enable {plugin}@{marketplace} |
| Disable plugin | claude plugin disable {plugin}@{marketplace} |
| Uninstall plugin | claude plugin uninstall {plugin}@{marketplace} |
| Check installed | cat ~/.claude/plugins/installed_plugins.json | jq '.plugins | keys' |
| Check enabled | cat ~/.claude/settings.json | jq '.enabledPlugins' |
Batch Enable Missing Plugins
To enable all installed but disabled plugins from a marketplace:
python3 scripts/enable_all_plugins.py marketplace-name
Skills vs Commands Architecture
Claude Code has two types of user-invocable extensions:
-
Skills (in
skills/directory)- Auto-activated based on description matching
- Loaded when user request matches skill description
-
Commands (in
commands/directory)- Explicitly invocable via
/command-name - Appears in Skill tool's available list
- Requires command file (e.g.,
commands/seer.md)
- Explicitly invocable via
If a skill should be explicitly invocable, add a corresponding command file.
References
- See
references/known_issues.mdfor GitHub issue tracking - See
references/architecture.mdfor detailed plugin architecture
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
excel-automation
Create, parse, and control Excel files on macOS. Professional formatting with openpyxl, complex xlsm parsing with stdlib zipfile+xml for investment bank financial models, and Excel window control via AppleScript. Use when creating formatted Excel reports, parsing financial models that openpyxl cannot handle, or automating Excel on macOS.
claude-code-history-files-finder
Finds and recovers content from Claude Code session history files. This skill should be used when searching for deleted files, tracking changes across sessions, analyzing conversation history, or recovering code from previous Claude interactions. Triggers include mentions of "session history", "recover deleted", "find in history", "previous conversation", or ".claude/projects".
fixing-claude-export-conversations
Fixes broken line wrapping in Claude Code exported conversation files (.txt), reconstructing tables, paragraphs, paths, and tool calls that were hard-wrapped at fixed column widths. Includes an automated validation suite (generic, file-agnostic checks). Triggers when the user has a Claude Code export file with broken formatting, mentions "fix export", "fix conversation", "exported conversation", "make export readable", references a file matching YYYY-MM-DD-HHMMSS-*.txt, or has a .txt file with broken tables, split paths, or mangled tool output from Claude Code.
continue-claude-work
Recover actionable context from local `.claude` session artifacts and continue interrupted work without running `claude --resume`. This skill should be used when the user provides a Claude session ID, asks to continue prior work from local history, or wants to inspect `.claude` files before resuming implementation.
promptfoo-evaluation
Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like "promptfoo", "eval", "LLM evaluation", "prompt testing", or "model comparison".
fact-checker
Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements.
Didn't find tool you were looking for?