debug

Name: debug
Author: KhanUzeb

Systematic debugging of failing tests, stack traces, or unexpected behavior.

by KhanUzeb(0) 0 installs

Free

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

See reviews

About

Imported from KhanUzeb/kite (src/kite/data/skills/debug/SKILL.md). Install upstream with npx skills add KhanUzeb/kite --skill debug. Copyright stays with the author.

Debug skill

Use when something is broken and the cause is unclear.

Steps

Reproduce: capture the exact command and full error output. Use set_cwd if the failure is in a subdirectory or monorepo package.
Localize: identify the failing file/function from the stack trace.
Hypothesize: list 1–3 likely causes; pick the cheapest check first.
Instrument: read relevant code; add temporary prints only if needed.
Fix the root cause with a minimal edit.
Re-run the original failing command and one nearby regression check.
Remove temporary debug instrumentation.

Rules

Do not shotgun-rewrite large files
Prefer failing tests as the reproduction harness
Stop and summarize if blocked after a few cycles

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}'

Manifest

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

khanuzeb-kite-debug.ocm.jsonjson

{
  "ocm": "1",
  "id": "khanuzeb-kite-debug",
  "kind": "skill",
  "name": "debug",
  "description": "Systematic debugging of failing tests, stack traces, or unexpected behavior.",
  "publisher": "KhanUzeb",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Systematic debugging of failing tests, stack traces, or unexpected behavior."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/KhanUzeb/kite",
      "path": "src/kite/data/skills/debug/SKILL.md",
      "ref": "2b68c4a5c590d99b4e2fcd5dd8b5115bee03a228",
      "url": "https://github.com/KhanUzeb/kite/blob/2b68c4a5c590d99b4e2fcd5dd8b5115bee03a228/src/kite/data/skills/debug/SKILL.md",
      "key": "KhanUzeb/kite/src/kite/data/skills/debug/SKILL.md"
    }
  },
  "instructions": "# Debug skill\n\nUse when something is broken and the cause is unclear.\n\n## Steps\n1. Reproduce: capture the exact command and full error output. Use `set_cwd` if the failure is in a subdirectory or monorepo package.\n2. Localize: identify the failing file/function from the stack trace.\n3. Hypothesize: list 1–3 likely causes; pick the cheapest check first.\n4. Instrument: read relevant code; add temporary prints only if needed.\n5. Fix the root cause with a minimal edit.\n6. Re-run the original failing command and one nearby regression check.\n7. Remove temporary debug instrumentation.\n\n## Rules\n- Do ",
  "cost": {
    "context_tokens": 183
  }
}

Fetch it by URL: GET /api/v1/registry/khanuzeb-kite-debug/manifest?version=1.0.0