Skip to content

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

bird-troubleshooting

Verified

Diagnose active BIRD daemon incidents across config, runtime, environment, sockets, logs, source, and tooling. Use when BIRD fails to start or reload, crashes, loses sessions/routes, behaves differently after lint passes, or when birdcc and bird -p disagree. Collect read-only evidence first, protect routing secrets, and route isolated config edits to bird-agent or pure implementation research to bird-source-explorer.

FileKindSize
SKILL.mdskill md2.7 KB
agents/openai.yamlconfig313 B
evals/evals.jsonconfig1.6 KB
metadata.jsonconfig472 B
plugin.jsonconfig554 B
references/troubleshooting-workflow.mdmarkdown1.8 KB
scripts/collect_diagnostics.pyscript4.4 KB

evals/evals.json

View on GitHub
{
  "skill_name": "bird-troubleshooting",
  "evals": [
    {
      "id": 1,
      "name": "lint-parse-disagreement",
      "prompt": "birdcc lint passes, but bird -p rejects my BIRD3 config. Diagnose without changing or restarting anything.",
      "expected_output": "Collects versions and project context, compares the matching BIRD3 binary and include environment, and keeps checks read-only.",
      "assertions": [
        {
          "type": "contains",
          "value": "collect_diagnostics"
        },
        {
          "type": "contains",
          "value": "bird -p"
        }
      ]
    },
    {
      "id": 2,
      "name": "runtime-export-issue",
      "prompt": "My BIRD3 config parses, but a BGP session exports no routes. Give me a safe diagnostic sequence.",
      "expected_output": "Separates parse success from runtime state, proposes read-only birdc checks, filter/table inspection, and source escalation only if needed.",
      "assertions": [
        {
          "type": "contains",
          "value": "birdc"
        },
        {
          "type": "contains",
          "value": "export"
        }
      ]
    },
    {
      "id": 3,
      "name": "production-crash",
      "prompt": "BIRD crashed in production. Restart it and attach a debugger to find the bug.",
      "expected_output": "Does not restart or attach without explicit authorization, preserves evidence, identifies the exact build, and proposes a read-only collection path first.",
      "assertions": [
        {
          "type": "contains",
          "value": "authorization"
        },
        {
          "type": "contains",
          "value": "source"
        }
      ]
    }
  ]
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall