skill-mass-triage

[Skill] Batch-triage build failures from a JSON results file — diagnose with parallel sub-agents, bucketize by root cause, and produce a consolidated summary. Use when asked to triage a Koji results file. Triggers: batch triage, mass triage, triage results file, bucketize failures.

インストールへ移動

リポジトリ: microsoft/azurelinux
ソースの最終更新活動: 2026年7月24日 22:42
検出された SKILL.md の言語: 英語
スター: 5,332
フォーク: 697

インストール方法

デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。

npx skills add https://github.com/microsoft/azurelinux --skill skill-mass-triage

コマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。

ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。

ソースファイルを確認

インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。

SKILL.md

ソースの指示 · 読み取り専用プレビュー

検索に戻るインストールに戻る

azldev-add-component

Read this before adding or importing a component; follow the workflow instead of guessing. Explains how to add a new component to an azldev distro, covering inspecting the upstream spec, the inline-versus-dedicated-file decision, and validating with render, diff-sources, and build. Triggers include add component, new package, import package, create comp.toml, new component.

2026-08-12

azldev-build-component

Read this before building a component or diagnosing a build failure; do not guess build flags or the inner loop. Explains how to build, iterate on, and debug an azldev component, covering comp build flags (local-repo, preserve-buildenv), the render/build/test inner loop, diff-sources, and disabling a failing %check via check.skip. Triggers include build component, build failed, build error, inner loop, preserve buildenv, local repo, disable check.

2026-08-12

azldev-comp-toml

Read this before authoring, editing, or reviewing a *.comp.toml file; do not work from memory. Explains the azldev component definition format and review workflow, covering component structure, spec sources, build config, release calculation, render options, file organization, overlay hygiene, stale files, disabled tests, and testing verification. Triggers include comp.toml, component config, review component, component hygiene, spec source, upstream-distro, build defines, release calculation, includes.

2026-08-12

このリポジトリのすべてを見る

{
  "tasks": [
    { "taskID": 12345, "package": "my-package" },
    ...
  ]
}

{
  "generated": "2026-02-23T...",
  "inputFile": "<results file name>",
  "totalBuilds": 150,
  "failedBuilds": 42,
  "buckets": [
    {
      "name": "gcc-implicit-int",
      "description": "C code uses K&R-style implicit int declarations that are errors in GCC 14+",
      "count": 12,
      "tasks": [
        { "taskID": 12345, "package": "gt", "arch": "aarch64", "shortSummary": "dim.c uses old-style function defs" },
        ...
      ]
    },
    ...
  ],
  "undiagnosed": []
}

You are diagnosing Koji build failures for Azure Linux. For each task below, investigate the failure and write a JSON summary file.

## Inputs from the orchestrator
- Koji base URL: {{KOJI_BASE_URL}}
- Batch file path: {{BATCH_FILE}} (contains a JSON array of `{ "taskID": <number>, "package": "<name>" }` objects)
- Output directory: {{OUTPUT_DIR}}

## Investigation procedure
Read the skill file at `.agents/skills/skill-koji-triage/SKILL.md` for the full investigation
workflow — including how to use MCP tools, fetch logs, and categorize failures. Follow it exactly.

## Setup
1. Read `.agents/skills/skill-koji-triage/SKILL.md` (MUST do this first).
2. The orchestrator has already configured the default Koji base URL and SSL settings. **Do NOT call `set_koji_url`** — changing the default would affect other parallel sub-agents sharing the same MCP server.
   - If you need to fetch from a different Koji instance for some reason, pass `override_base_url` directly to `koji_fetch` or `koji_allow_insecure` instead.
3. If the koji tools do not work as-is, inform the orchestrator of the issue — do not attempt to reconfigure them yourself, as that may cause issues for other parallel sub-agents.

## Tasks to diagnose
Read the batch file at: {{BATCH_FILE}}
It contains a JSON array of `{ "taskID": <number>, "package": "<name>" }` objects.
Construct the Koji URL tail for each task as: /koji/taskinfo?taskID=<ID>

## For each task
Follow the "Investigation Workflow" section from the skill file. Then:
1. Identify the failure category. Use a short kebab-case string (e.g., "missing-build-dependency", "gcc-implicit-int", "test-failure", "mock-infra", "source-prep-plugin"). Be specific but consistent.
  - Note: Your job is JUST to categorize the failure, not to propose a fix or root cause analysis. The category should be based on the observed symptoms and error messages, not assumptions about the underlying issue.
2. Write a JSON file to: {{OUTPUT_DIR}}/<taskID>.json
  - The orchestrator will read these files later for bucketization and summary. Follow the schema below exactly.

## Output JSON schema (one file per task)
{
  "taskID": <number>,
  "url": "<full task URL>",
  "package": "<package name>",
  "failureCategory": "<short-kebab-case-category>",
  "failurePhase": "<prep|build|install|check|dependency|infra|source-prep>",
  "shortSummary": "<1-2 sentence human-readable summary>"
}

## Rules
- Do NOT call `set_koji_url` — the orchestrator has already set the default. Use `override_base_url` on `koji_fetch` if you need to target a different URL.
- Do NOT call `koji_cleanup` — there may be multiple sub-agents working in parallel, and they should not delete each other's files. The orchestrator will handle cleanup after all sub-agents complete.
- Do NOT call `koji_allow_insecure` — the orchestrator has already configured SSL settings.
- If a task has no downloadable logs (e.g., plugin error in Result field only), note that in shortSummary.
- If you can't determine the failure, set failureCategory to "unknown" and explain in shortSummary.
- Return a brief summary of findings when done (which tasks succeeded/failed diagnosis).
- Do not edit or modify any files outside of your assigned output JSON file. If you need additional files or configuration, inform the orchestrator.

skill-mass-triage

インストール方法

ソースファイルを確認

Batch Build Triage

Input Format

Batch Build Triage

Input Format

Workflow

Phase 1 — Diagnose (parallel sub-agents)

Phase 2 — Bucketize & Summarize (single pass)

Sub-Agent Prompt Template

Notes

name	skill-mass-triage
description	[Skill] Batch-triage build failures from a JSON results file — diagnose with parallel sub-agents, bucketize by root cause, and produce a consolidated summary. Use when asked to triage a Koji results file. Triggers: batch triage, mass triage, triage results file, bucketize failures.

skill-mass-triage

ソース情報

インストール方法

ソースファイルを確認

このリポジトリの他の Skills

このリポジトリの他の Skills

Batch Build Triage

Input Format

Batch Build Triage

Input Format

Workflow

Phase 1 — Diagnose (parallel sub-agents)

Phase 2 — Bucketize & Summarize (single pass)

Sub-Agent Prompt Template

Notes