Agent Skillsrorkai/App-Store-Connect-CLI › triage-asc-issue

triage-asc-issue

GitHub

用于审查、复现和分类 App Store Connect CLI 的 GitHub Issue。通过验证代码、API 文档及实际行为,判定问题类型(Bug/增强/疑问等),并依据权限推荐或应用标签,为后续开发提供明确指引。

.agents/skills/triage-asc-issue/SKILL.md rorkai/App-Store-Connect-CLI

Trigger Scenarios

用户要求审计或分类 ASC CLI 的 Issue 需要复现 CLI 行为并验证 API 支持情况 决定 Issue 是否应被修复或实现

Install

npx skills add rorkai/App-Store-Connect-CLI --skill triage-asc-issue -g -y
More Options

Non-standard path

npx skills add https://github.com/rorkai/App-Store-Connect-CLI/tree/main/.agents/skills/triage-asc-issue -g -y

Use without installing

npx skills use rorkai/App-Store-Connect-CLI@triage-asc-issue

指定 Agent (Claude Code)

npx skills add rorkai/App-Store-Connect-CLI --skill triage-asc-issue -a claude-code -g -y

安装 repo 全部 skill

npx skills add rorkai/App-Store-Connect-CLI --all -g -y

预览 repo 内 skill

npx skills add rorkai/App-Store-Connect-CLI --list

SKILL.md

Frontmatter
{
    "name": "triage-asc-issue",
    "description": "Triage App-Store-Connect-CLI GitHub issues against current code, CLI behavior, and App Store Connect API support. Use when the user asks to audit, reproduce, classify, label, scope, prioritize, or decide whether an ASC CLI issue should be fixed or implemented."
}

Triage an ASC CLI issue

Produce a current, evidence-backed verdict and proposed repository labels. Apply label changes only when authorized under AGENTS.md; a read-only triage ends with recommendations.

Read current evidence

  1. Fetch the live issue body, comments, labels, linked PRs, and referenced documentation.
  2. Resolve the affected command through current --help, source, tests, and recent history. Do not infer support from an old command name.
  3. Reproduce reported behavior with the current built or installed CLI when safe.
  4. For API claims, verify the exact method and endpoint in docs/openapi/latest.json; use the sosumi.ai documentation mirror for explanatory context.
  5. Check whether the report is already fixed on current origin/main, duplicated, unsupported by the public API, or blocked by Apple/platform behavior.

Follow AGENTS.md for parallel reads and serialized writes. Live reproductions require authority for mutations and cleanup, even on disposable resources; confirm dry runs are side-effect-free.

Classify the outcome

Choose one primary verdict:

  • Confirmed bug with a reproducible expected-versus-actual mismatch.
  • Valid enhancement with a supported and coherent API or client-side design.
  • Question requiring clarification or support guidance.
  • Already fixed, duplicate, not reproducible, unsupported, or platform-limited.

Separate urgency from implementation size. Explain user impact, blast radius, workaround, compatibility risk, and the smallest proof needed for completion.

Recommend or apply labels

Recommend one type, priority, and difficulty from AGENTS.md's buckets using the meanings in CONTRIBUTING.md. Apply them only when authorized.

For authorized label updates, remove conflicting labels and add the selected replacements, then verify the resulting buckets. If evidence is incomplete, mark the recommendation provisional and identify the missing evidence; uncertainty alone does not establish low urgency or easy implementation.

Define implementation readiness

When the issue is actionable, provide:

  1. Proposed command and UX shape.
  2. API endpoint or explicit client-side behavior.
  3. Files and shared surfaces likely affected.
  4. RED-GREEN test plan and black-box exit/output cases.
  5. Safe live verification and cleanup plan.
  6. Compatibility or deprecation requirements.

If implementation is requested, continue with $develop-asc-change in an isolated branch or worktree. Report the requested implementation and validation as complete when finished, with PR and merge gates separately. Do not close the issue or claim it resolved until merged and verified; closure still requires authority.

Automation contract

A recurring issue-triage automation may classify new or incompletely labeled issues and report actionable findings. Apply labels or post comments only within its persisted write authority. It must not implement code or close issues without explicit authorization, and labels must follow evidence.

Version History

  • 5.1.0 Current 2026-09-09 10:53

    明确了指令执行权限与完成边界,移除重复的工作流指导,澄清了 Agent 授权及完成规则。

  • 4.10.0 2026-08-28 14:16

    收紧并行审查安全性,优化维护者工作流程速度

  • 3.1.1 2026-07-25 09:42

Same Skill Collection

.agents/skills/audit-asc-pr/SKILL.md
.agents/skills/develop-asc-change/SKILL.md
.agents/skills/release-asc-cli/SKILL.md
.agents/skills/review-wall-of-apps-prs/SKILL.md
.agents/skills/sync-asc-skills/SKILL.md
.agents/skills/watch-asc-pr/SKILL.md

Metadata

Files
0
Version
5.1.0
Hash
28f516fc
Indexed
2026-07-25 09:42

trang chủ - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-09-15 20:43
浙ICP备14020137号-1 $bản đồ khách truy cập$