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 huaweicloud/huaweicloud-skills --skill huawei-cloud-codearts-pipeline-diagnosegit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote 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/huaweicloud/huaweicloud-skills/huawei-cloud-codearts-pipeline-diagnose)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-codearts-pipeline-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-codearts-pipeline-diagnose/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/huaweicloud/huaweicloud-skills/huawei-cloud-codearts-pipeline-diagnose"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-codearts-pipeline-diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00273 | $0.09352 |
| Opus 5.5 | $0.00109 | $0.03741 |
| Sonnet 5.5 | $0.00055 | $0.01870 |
| Haiku 4.5 | $0.00027 | $0.00935 |
Grade A, and why
huawei-cloud-codearts-pipeline-diagnose 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 11d 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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud CodeArts Pipeline & Build Diagnosis
Overview
This skill operates Huawei Cloud CodeArts (CodeArts Pipeline / CodeArts Build /
编译构建) through the hcloud CLI. CodeArts Pipeline orchestrates build, deploy
and release tasks as pipelines (流水线); CodeArts Build compiles source code
into artifacts as build tasks (构建任务). The skill covers:
| Category | Capabilities |
|---|---|
| Query | List pipelines (huawei_list_pipelines), list build tasks (huawei_list_build_tasks), get pipeline detail (huawei_get_pipeline), get build task detail (huawei_get_build_task), get build log (huawei_get_build_log) |
| Analyze | Build failure diagnosis (huawei_diagnose_build_failure — log fetch → error classification → root cause: network/parameter/load), pipeline failure diagnosis (huawei_diagnose_pipeline_failure — orchestration/execution error analysis), build log error extraction (huawei_extract_build_log_errors) |
| Manage | Create pipeline (huawei_create_pipeline), create build task (huawei_create_build_task), start pipeline (huawei_start_pipeline), start build task (huawei_start_build_task), delete pipeline (huawei_delete_pipeline), delete build task (huawei_delete_build_task) |
Always run
hcloud CodeArtsPipeline <Operation> --cli-region={region} --helporhcloud CodeArtsBuild <Operation> --cli-region={region} --helpbefore constructing a command to discover the exact parameter names and required flags for the current KooCLI version. Do not answer from general knowledge — follow the procedures in this document.
Critical Warnings
| Trap | Why |
|---|---|
Build service is CodeArtsBuild, not CloudBuild/CLOUDBUILD |
hcloud CloudBuild <op> and hcloud CLOUDBUILD <op> report [USE_ERROR]不支持的服务名称 (unsupported service). The real KooCLI service name is CodeArtsBuild (metadata directory codeartsbuild) — confirm with the service help output. |
| Pipeline APIs are project-scoped | Every CodeArtsPipeline operation requires --project_id of a CodeArts (DevCloud) project. A plain IAM project or wrong project returns pipeline.00060101 项目不存在 or an auth error. Omit --project_id only if your hcloud profile has a default project set. |
| Log download endpoints return raw/compressed content | DownloadBuildLog returns the full log for a record_id; for a running build use DownloadBuildRealTimeLog (job_id + build_no + --size). DownloadBuildFullLog adds --compress/--log_level. Match the operation to the run state. |
| record_id ≠ job_id ≠ build_no | Build APIs use three distinct identifiers: job_id (task id, 32 chars), build_no (per-build increment starting at 1), record_id (36-char build record uuid). Do not substitute one for another — the API rejects mismatched ids. |
| Create operations are complex | CreatePipelineNew needs a JSON --definition (best copied from an existing pipeline via ShowPipelineDetail); CreateBuildJob needs --steps.N.module_id/--steps.N.name for each build step. Prefer template-based creation (CreatePipelineByTemplate) for pipelines in production. |
| Concurrent runs may be rejected | Starting a pipeline that is already running returns a conflict error unless the run policy permits concurrency. Check the latest run state (ShowPipelineRunDetail) before RunPipeline/RunJob. |
| Security baseline | Never hardcode AK/SK or pipeline parameters with plaintext credentials in build steps/scripts. Use IAM roles where possible and encrypt sensitive parameters (KooCLI keeps secrets in the local profile; env-var credentials never appear in commands). |
What ships with it
12 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.
- references/acceptance-criteria.md 4.6 KB
- references/build-error-classification.md 5.4 KB
- references/cli-installation-guide.md 954 B
- references/dataflow-diagram.md 3.0 KB
- references/iam-policies.md 5.0 KB
- references/test-data-guide.md 3.9 KB
- references/test-report.md 4.5 KB
- references/verification-method.md 4.8 KB
- scripts/ensure_cli.sh 1.8 KB runs code
- scripts/install_cli.sh 1.4 KB runs code
- templates/test-defaults.json 4.4 KB
- templates/test-vars.json 5.4 KB
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.
- 11d ago Changed · -16 lines e1fce4b00397
- 20d ago First seen · 510 lines · 273 tokens per session scan A 022cca7c8e5e
huawei-cloud-codearts-pipeline-diagnose is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (53 stars, last pushed today), licensed MIT. It adds 273 tokens to every session and 9,352 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
Jenkins Access
Handles Cloudflare Access authentication for the ASU Jenkins instance. Manages the cloudflared login flow and provides context for using Jenkins MCP tools (builds, logs, test results, artifacts). Activate when Jenkins access is needed or auth errors occur.
cicd-pipeline-qe-orchestrator
Orchestrate quality engineering across CI/CD pipeline phases. Use when designing test strategies, planning quality gates, or implementing shift-left/shift-right testing.
gamedev-shipping
Use when exporting, packaging, signing, or publishing a game — export presets per engine, macOS notarization, cross-origin isolation for threaded web builds, Android AAB/keystore, iOS provisioning, store submission (Steam, Play, App Store, itch.io), headless build CI. NOT gameplay code inside the artifact (that is…
CI Pipeline Optimizer
Optimize CI test pipelines through intelligent test splitting, parallelization, caching strategies, and selective test execution based on code changes.
CI/CD Pipeline Advanced
Expert-level CI/CD pipeline skill for test automation. Covers GitHub Actions, Jenkins, GitLab CI, Azure DevOps, parallel execution, matrix strategies, caching, artifact management, and deployment gates.
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.