agentsclimarketplace

Bird troubleshooting

Skill bird-chinese-community/BIRD.skills/bird-troubleshooting

BIRDCC agent skills registry

Install
npx -y skills add bird-chinese-community/BIRD.skills --skill bird-troubleshooting

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Diagnose complex BIRD routing-daemon problems that cross configuration, source-code, and tooling boundaries. Use when the daemon fails to start, crashes at runtime, logs a confusing error, or behaves differently from the documented semantics after lint passes. For simple config syntax or formatting issues, use bird-agent; for source-level questions, use bird-source-explorer.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, as published. Nobody here has run it

BIRD Troubleshooting

Orchestrate diagnostics across the BIRD tool chain to resolve complex runtime and configuration problems.

When to use this skill

  • The bird daemon fails to start or crashes.
  • Logs contain an error that is not explained by a simple syntax fix.
  • The config passes birdcc lint / bird -p but the observed behavior differs from the documentation.
  • The problem may involve BIRD internals and requires source-level evidence.
  • The user is unsure whether the issue is config, environment, tooling, or an upstream bug.

Do not use this skill for:

  • Plain config editing or linting (use bird-agent).
  • Installation of birdcc or editor plugins (use birdcc-installer).
  • Pure source-code archaeology without a runtime symptom (use bird-source-explorer).

Core principles

  1. Collect first. Run uv run scripts/collect_diagnostics.py --root . to gather versions, detected configs, and tool availability before guessing.
  2. Start with config/docs. Route configuration and documented-behavior questions to bird-agent and its query_bird_docs MCP tool.
  3. Escalate to source when needed. If the config looks correct but the behavior is unexpected, use bird-source-explorer to inspect the relevant C implementation.
  4. Fix environment gaps. If birdcc or bird is missing, route to birdcc-installer.
  5. Synthesize, don't dump. Give the user a prioritized list of hypotheses and the next verification step for each.

Workflow

  1. Run uv run scripts/collect_diagnostics.py --root . to collect baseline info.
  2. Ask for (or read) the relevant log snippet / error message / crash trace.
  3. If the error points to a config issue, invoke bird-agent workflow.
  4. If the config is correct but behavior is wrong, invoke bird-source-explorer to find the implementation.
  5. If tooling is missing, invoke birdcc-installer.
  6. Summarize findings as:
    • Most likely cause
    • Other plausible causes
    • Next verification command or source file to inspect

Available scripts

Completion criteria

  • Diagnostics were collected and shared with the user.
  • At least one hypothesis has supporting evidence (log line, source location, or config line).
  • The user has a clear next step to verify or fix the issue.
  • Sensitive data (peer IPs, ASNs, passwords) was redacted before quoting logs or configs.

⭐ If the BIRD tooling here saves you time, consider starring the main monorepo: bird-chinese-community/BIRD-LSP.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.