Development
fix-lightning - Claude MCP Skill
Run /check-lightning, then fix the highest priority Lightning issue. Creates one fix per invocation. Invoke again for next issue. Use /log-lightning-issues to create issues without fixing.
SEO Guide: Enhance your AI agent with the fix-lightning tool. This Model Context Protocol (MCP) server allows Claude Desktop and other LLMs to run /check-lightning, then fix the highest priority lightning issue. creates one fix per invocation.... Download and configure this skill to unlock new capabilities for your AI workflow.
Documentation
SKILL.md# /fix-lightning Fix the highest priority Lightning issue. ## What This Does 1. Invoke `/check-lightning` to audit Lightning health 2. Identify highest priority issue 3. Fix that one issue 4. Verify the fix 5. Report what was done **This is a fixer.** It fixes one issue at a time. Run again for next issue. Use `/lightning` for full lifecycle. ## Process ### 1. Run Primitive Invoke `/check-lightning` skill to get prioritized findings. ### 2. Fix Priority Order Fix in this order: 1. **P0**: Node not synced, watchtower not configured 2. **P1**: Peer connectivity issues 3. **P2**: Low inbound liquidity, channel rebalancing needed 4. **P3**: Advanced routing/fees ### 3. Execute Fix **Node not synced (P0):** Confirm chain sync: ```bash lncli getinfo bitcoin-cli getblockchaininfo ``` If `synced_to_chain=false`, restart LND after backend is healthy: ```bash sudo systemctl restart lnd ``` **Watchtower not configured (P0):** Enable watchtower client and add a tower: ```bash # lnd.conf wtclient.active=1 lncli wtclient add --tower_addr=host:9911 ``` **Peer connectivity issues (P1):** Reconnect to peer: ```bash lncli listpeers lncli disconnect <pubkey> lncli connect <pubkey>@host:port ``` **Low inbound liquidity (P2):** Open a channel with pushed sats to create inbound: ```bash lncli openchannel --node_key=<pubkey> --local_amt=1000000 --push_amt=200000 ``` **Channel rebalancing needed (P2):** Move balance from outgoing-heavy to incoming-heavy channel: ```bash lncli listchannels lncli rebalancechannel --from_chan_id=<from> --to_chan_id=<to> --amount=50000 ``` ### 4. Verify After fix: ```bash lncli getinfo lncli listchannels lncli listpeers ``` ### 5. Report ``` Fixed: [P0] Node not synced Updated: lnd service - Restarted after chain backend healthy - Confirmed synced_to_chain=true Verified: lncli getinfo → synced_to_chain=true Next highest priority: [P0] Watchtower not configured Run /fix-lightning again to continue. ``` ## Branching Before making changes: ```bash git checkout -b fix/lightning-$(date +%Y%m%d) ``` ## Single-Issue Focus Lightning is sensitive. Fix one thing at a time: - Test each change thoroughly - Easy to rollback specific fixes - Clear audit trail for ops Run `/fix-lightning` repeatedly to work through the backlog. ## Related - `/check-lightning` - The primitive (audit only) - `/log-lightning-issues` - Create issues without fixing - `/lightning` - Full Lightning lifecycle
Signals
Information
- Repository
- phrazzld/claude-config
- Author
- phrazzld
- Last Sync
- 3/2/2026
- Repo Updated
- 3/1/2026
- Created
- 1/28/2026
Reviews (0)
No reviews yet. Be the first to review this skill!
Related Skills
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
remote-browser
Controls a cloud browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.
agent-builder
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration
troubleshooting
Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.
Related Guides
Mastering the Oracle CLI: A Complete Guide to the Claude Skill for Database Professionals
Learn how to use the oracle Claude skill. Complete guide with installation instructions and examples.
Python Django Best Practices: A Comprehensive Guide to the Claude Skill
Learn how to use the python django best practices Claude skill. Complete guide with installation instructions and examples.
Building Full-Stack Applications with Claude: The Node.js MongoDB JWT Express React Skill Guide
Learn how to use the nodejs mongodb jwt express react Claude skill. Complete guide with installation instructions and examples.