investigate

Name: investigate
Author: YokoyamaRyota

Root-cause-first debugging workflow. Use for bugs, regressions, stack traces, production issues, or any case where the real failure path must be understood before edits are proposed.

by YokoyamaRyota(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from YokoyamaRyota/ryota_project (.github/skills/investigate/SKILL.md). Install upstream with npx skills add YokoyamaRyota/ryota_project --skill investigate. Copyright stays with the author.

Investigate

Rules

no speculative fixes
gather evidence before changing code
separate observations, hypotheses, and fixes

Workflow

Reproduce the issue and capture exact symptoms.
Trace the real execution path.
Form the smallest plausible root-cause hypothesis.
Verify the hypothesis against code or runtime evidence.
Only then propose or implement a fix.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Installed into a catalogue, chosen by a router

Install investigate and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

Photo: RDNE Stock project

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

yokoyamaryota-ryota-project-investigate.ocm.jsonjson

{
  "ocm": "1",
  "id": "yokoyamaryota-ryota-project-investigate",
  "kind": "skill",
  "name": "investigate",
  "description": "Root-cause-first debugging workflow. Use for bugs, regressions, stack traces, production issues, or any case where the real failure path must be understood before edits are proposed.",
  "publisher": "YokoyamaRyota",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Root-cause-first debugging workflow. Use for bugs, regressions, stack traces, production issues, or any case where the real failure path must be understood before edits are proposed."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/YokoyamaRyota/ryota_project",
      "path": ".github/skills/investigate/SKILL.md",
      "ref": "798a7d32ab9a7209b10e40a90eae07a62d875224",
      "url": "https://github.com/YokoyamaRyota/ryota_project/blob/798a7d32ab9a7209b10e40a90eae07a62d875224/.github/skills/investigate/SKILL.md",
      "key": "YokoyamaRyota/ryota_project/.github/skills/investigate/SKILL.md"
    }
  },
  "instructions": "# Investigate\n\n## Rules\n\n- no speculative fixes\n- gather evidence before changing code\n- separate observations, hypotheses, and fixes\n\n## Workflow\n\n1. Reproduce the issue and capture exact symptoms.\n2. Trace the real execution path.\n3. Form the smallest plausible root-cause hypothesis.\n4. Verify the hypothesis against code or runtime evidence.\n5. Only then propose or implement a fix.",
  "cost": {
    "context_tokens": 96
  }
}

Fetch it by URL: GET /api/v1/registry/yokoyamaryota-ryota-project-investigate/manifest?version=1.0.0