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-skill-creatorgit 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-skill-creator)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-creator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-creator/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-skill-creator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-creator.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 | $0.00253 | $0.08606 |
| Opus 5 | $0.00127 | $0.04303 |
| Sonnet 5 | $0.00051 | $0.01721 |
| Haiku 4.5 | $0.00025 | $0.00861 |
Grade A, and why
huawei-cloud-skill-creator scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **API** | curl command + user-provided endpoint (mark as user-provided) | How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Skill Creator v2
Six-Phase Strict Pipeline — Each phase depends on the previous phase's output and cannot be skipped. If any phase is missing, restart from the missing phase.
Overview
The Huawei Cloud Skill Creator v2 is based on a six-phase strict pipeline: starting with Socratic Q&A requirements analysis, followed by technical research (CLI→SDK→API three-level fallback), document generation, test preparation, detailed testing, resource cleanup and compliance check, ultimately generating a complete skill package that conforms to the Huawei Cloud Skill Specification. It only creates/packages skills — it does not directly operate cloud resources (no creating/deleting/modifying ECS, VPC, OBS, etc.); use it to generate a management Skill or use another dedicated management Skill for cloud-resource operations.
Pre-check: Huawei Cloud Credentials Required
Mandatory gate. This pre-check MUST pass before invoking any hcloud / huaweicloudsdk command — including Phase 2 research, Phase 4/5 testing, and Phase 6 validation. If no valid credential profile is detected, STOP and obtain credentials out-of-band.
Security Rules
- NEVER read, echo, or print AK/SK values (e.g., printing the value of an
HUAWEI_ACCESS_KEY-style env var is FORBIDDEN). - NEVER read or cat the on-disk credential files for hcloud, obsutil, the SDK, or any other secret-storing location. Treat all such files as confidential; the names of those files (used by their owners) are documented in
references/cli-installation-guide.md. - NEVER ask the user to input AK/SK directly in the conversation or command line.
- NEVER invoke
hcloud configure setwith literal credential strings passed via the CLI'scli-<ak-flag>/cli-<sk-flag>parameters or any equivalent in-band secret-entry form. - ONLY use
hcloud configure listto check credential status — non-interactive, read-only, no secrets echoed.
Verification Steps
hcloud configure list
What ships with it
14 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 2.3 KB
- references/cli-installation-guide.md 2.8 KB
- references/dataflow-diagram.md 2.5 KB
- references/iam-policies.md 1.3 KB
- references/quality-reporting.md 4.1 KB
- references/related-commands.md 1.3 KB
- references/verification-method.md 2.0 KB
- scripts/quality-report.sh 3.8 KB runs code
- scripts/report-skill-created.sh 3.6 KB runs code
- scripts/skill_quality_sdk.py 52 KB runs code
- scripts/test-cli-commands.sh 19 KB runs code
- scripts/validate-skill.sh 18 KB runs code
- scripts/yaml-check-frontmatter.py 1.9 KB runs code
- templates/test-vars.json 1.9 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.
- yesterday Changed scan C → A e57cff531868
- 4d ago Changed · -40 lines 9bd64af50716
- 9d ago First seen · 527 lines · 253 tokens per session scan C e6fcb17b60e8
huawei-cloud-skill-creator is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 253 tokens to every session and 8,606 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.