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.
What this skill does
# 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:
```bash
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:**
- `/plugin` shows 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](https://github.com/anthropics/claude-code/issues/17832)) - plugins are added to `installed_plugins.json` but NOT automatically added to `enabledPlugins` in `settings.json`.
**Diagnosis:**
```bash
# 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:**
```bash
# 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:**
1. Exists in `installed_plugins.json` (registered)
2. Listed in `settings.json` → `enabledPlugins` with value `true`
### Issue 3: Marketplace Cache Stale
**Symptoms:**
- GitHub has latest changes
- Install finds plugin but gets old version
- Newly added plugins not visible
**Solution:**
```bash
# 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):**
1. **Local changes not pushed to GitHub** - Most common!
```bash
git status
git push
claude plugin marketplace update marketplace-name
```
2. **marketplace.json configuration error**
```bash
python3 -m json.tool .claude-plugin/marketplace.json
```
3. **Skill directory missing**
```bash
ls -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:
```bash
python3 scripts/enable_all_plugins.py marketplace-name
```
## Skills vs Commands Architecture
Claude Code has two types of user-invocable extensions:
1. **Skills** (in `skills/` directory)
- Auto-activated based on description matching
- Loaded when user request matches skill description
2. **Commands** (in `commands/` directory)
- Explicitly invocable via `/command-name`
- Appears in Skill tool's available list
- Requires command file (e.g., `commands/seer.md`)
If a skill should be explicitly invocable, add a corresponding command file.
## References
- See `references/known_issues.md` for GitHub issue tracking
- See `references/architecture.md` for detailed plugin architecture
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.