Troubleshoot Claude Code session issues. Use when encountering "No conversations found" errors, missing sessions, or session file corruption problems.
Diagnoses and fixes Claude Code session recovery issues including missing sessions and corrupted files.
/plugin marketplace add terrylica/cc-skills/plugin install devops-tools@cc-skillsThis skill is limited to using the following tools:
TROUBLESHOOTING.mdWhen to use this skill:
claude -r/tmp/ instead of ~/.claude/projects/)Standard Location: ~/.claude/projects/
Structure:
~/.claude/projects/
├── -home-username-my-project/ # Encoded absolute path
│ └── 364695f1-13e7-4cbb-ad4b-0eb416feb95d.jsonl
└── -tmp-another-project/
└── a8e39846-ceca-421d-b4bd-3ba0eb1b3145.jsonl
Format: One JSON event per line (JSONL), UUID-based filenames
Claude Code uses $HOME environment variable to determine session storage location. If $HOME is incorrect, sessions go to wrong directory or disappear.
claude -r shows "No conversations found to resume"/tmp/ or other unexpected paths/usr/bin/env bash << 'PREFLIGHT_EOF'
# Step 1: Check current HOME
echo "Current HOME: $HOME"
# Step 2: Check system expectation
echo "Expected HOME: $(getent passwd $(whoami) | cut -d: -f6)"
# Step 3: Find where Claude is actually writing
find /tmp -name "*.jsonl" -path "*/.claude/projects/*" 2>/dev/null
PREFLIGHT_EOF
For detailed diagnostic steps and solutions, see:
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.