Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tao12345666333/ankaloop --skill gh-ci-analyzergit clone --depth 1 https://github.com/tao12345666333/ankaloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tao12345666333/ankaloop/gh-ci-analyzer)<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/gh-ci-analyzer"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/gh-ci-analyzer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tao12345666333/ankaloop/gh-ci-analyzer"><img src="https://agentmods.dev/badge/skills/tao12345666333/ankaloop/gh-ci-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.01674 |
| Opus 5 | $0.00014 | $0.00837 |
| Sonnet 5 | $0.00005 | $0.00335 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
gh-ci-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Actions CI 分析器
这个 skill 指导 agent 如何使用 GitHub CLI (gh) 来分析 GitHub Actions CI/CD 日志，诊断失败原因，并提供结构化的分析报告。
前置条件
确保已安装并认证 GitHub CLI：
gh auth login
gh auth status
核心命令
1. 查看 Workflow Runs
# 列出最近的 workflow runs
gh run list
# 列出特定 workflow 的 runs
gh run list --workflow "CI.yml"
# 限制显示数量
gh run list --limit 10
# 按状态过滤
gh run list --status failed
gh run list --status completed
2. 查看 Run 详情
# 查看特定 run 的基本信息
gh run view <run-id>
# 查看特定 workflow 的最新 run
gh run view --workflow "CI.yml"
# 查看特定分支的最新 run
gh run view --branch main
3. 查看失败日志
# 查看失败 job 的日志
gh run view <run-id> --log-failed
# 查看特定 job 的日志
gh run view <run-id> --job <job-id>
# 查看完整日志（包括成功的）
gh run view <run-id> --log
4. 查看 PR 检查状态
# 查看当前 PR 的检查状态
gh pr checks
# 查看特定 PR 的检查状态
gh pr checks <pr-number>
# 查看 PR 的详细状态
gh pr view <pr-number> --json statusCheckRollup
分析流程
步骤 1: 识别失败的 Run
# 查看最近的失败 runs
gh run list --status failed --limit 5
记录失败的 run ID 和 workflow 名称。
步骤 2: 获取失败详情
# 查看失败 run 的概览
gh run view <run-id>
# 查看失败日志
gh run view <run-id> --log-failed
步骤 3: 分析失败模式
在日志中寻找以下关键信息：
- 错误消息: 直接的 error 或 exception 信息
- 失败步骤: 哪个具体的 job 或 step 失败
- 时间戳: 失败发生的时间点
- 环境信息: OS、Python 版本、依赖版本等
- 资源限制: 内存、磁盘空间、超时等
步骤 4: 关联 PR 信息（如果适用）
# 查看关联的 PR
gh pr view --json number,title,headRefName
# 查看 PR 的检查状态
gh pr checks
常见失败类型分析
1. 测试失败
识别特征:
- AssertionError, unittest failures
- pytest exit codes
- 测试覆盖率报告
分析要点:
- 哪个测试失败
- 失败的具体断言
- 期望值 vs 实际值
- 是否为 flaky test
2. 依赖安装失败
识别特征:
- pip/conda install errors
- 版本冲突
- 网络超时
分析要点:
- 哪个包安装失败
- 版本要求冲突
- 索引源问题
- 缓存问题
3. 构建失败
识别特征:
- 编译错误
- 语法错误
- linting failures
分析要点:
- 具体的编译错误
- 代码规范问题
- 类型检查失败
4. 环境问题
识别特征:
- 权限错误
- 资源不足
- 配置问题
分析要点:
- 权限设置
- 内存/磁盘使用
- 环境变量配置
结构化报告格式
CI 失败分析报告模板
# CI 失败分析报告
## 基本信息
- **Run ID**: <run-id>
- **Workflow**: <workflow-name>
- **分支**: <branch-name>
- **提交**: <commit-sha>
- **时间**: <timestamp>
- **PR**: <pr-number> (如果适用)
## 失败概览
- **失败 Job**: <job-name>
- **失败 Step**: <step-name>
- **错误类型**: <error-category>
- **失败时间**: <failure-timestamp>
## 错误详情
[粘贴关键错误日志]
## 根本原因分析
[详细分析失败的根本原因]
## 影响范围
- **受影响功能**: <affected-features>
- **影响程度**: <high/medium/low>
- **是否阻塞性**: <yes/no>
## 修复建议
1. **立即修复**: <immediate-fix-steps>
2. **长期改进**: <long-term-improvements>
3. **预防措施**: <prevention-measures>
## 相关资源
- **失败日志链接**: <log-url>
- **PR 链接**: <pr-url>
- **提交链接**: <commit-url>
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 278 lines · 27 tokens per session scan A b0d916765a7f
gh-ci-analyzer is a skill published in the GitHub repository tao12345666333/ankaloop (48 stars, last pushed 14d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,674 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
memory-leak-debug
Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.
bugfix
Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.