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-terraform-generatorgit 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-terraform-generator)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-terraform-generator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-terraform-generator/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-terraform-generator"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-terraform-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Prompt Injection · line 55 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 121 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00193 | $0.03609 |
| Opus 5 | $0.00097 | $0.01804 |
| Sonnet 5 | $0.00039 | $0.00722 |
| Haiku 4.5 | $0.00019 | $0.00361 |
Grade A, and why
huawei-cloud-terraform-generator 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 9d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Terraform Generator
1. Overview
This skill turns user infrastructure goals into Terraform configurations for Huawei Cloud. The primary workflow is to:
- understand the user's actual deployment intent
- determine which resources should be created
- determine whether existing resources should be reused
- confirm key specifications and dependencies
- verify every resource specification against the target region's available resources — query first, write later
- ensure Terraform is installed
- generate Terraform configuration files
- run validation steps and fix generation issues until
terraform plansucceeds - ask user for confirmation and execute
terraform applyif approved
This skill provides an interactive workflow where the agent guides the user through credential configuration, validates the plan, and executes apply upon explicit user confirmation.
2. Prerequisites
Before using this skill, ensure the following are available:
- Terraform — installed in PATH or auto-installable (see validation-workflow.md)
- Provider download source — the Huawei Cloud mirror should be reachable (see validation-workflow.md)
- Target region — the deployment region (e.g. cn-north-4, cn-south-1) must be identified
3. Parameter Confirmation
Before generating Terraform, propose a concrete resource plan for the user to confirm. The plan should include:
- recommended resource specifications
- available candidate options when applicable
- whether to create new resources or reuse existing ones
- pricing information only when obtained from a reliable source
See reference/guardrails.md for rules about not fabricating specifications and prices.
Do not ask the user to provide every parameter manually. Instead:
- infer the likely architecture from the user's goal
- propose a concrete plan with recommended defaults
- confirm only the small number of decisions that materially affect correctness, cost, or architecture
Users should mainly confirm a proposed solution, not build the full parameter set themselves.
What ships with it
60 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.
- assets/antiddos/basic/main.tf 894 B
- assets/antiddos/basic/providers.tf 305 B
- assets/antiddos/basic/README.md 2.7 KB
- assets/antiddos/basic/terraform.tfvars 543 B
- assets/antiddos/basic/variables.tf 1.8 KB
- assets/antiddos/default-protection-policy/main.tf 125 B
- assets/antiddos/default-protection-policy/providers.tf 305 B
- assets/antiddos/default-protection-policy/README.md 1.4 KB
- assets/antiddos/default-protection-policy/terraform.tfvars 34 B
- assets/antiddos/default-protection-policy/variables.tf 585 B
- assets/antiddos/lts-config/main.tf 671 B
- assets/antiddos/lts-config/providers.tf 305 B
- assets/antiddos/lts-config/README.md 1.7 KB
- assets/antiddos/lts-config/terraform.tfvars 181 B
- assets/antiddos/lts-config/variables.tf 1.0 KB
- assets/aom/action-callback/main.tf 1.5 KB
- assets/aom/action-callback/providers.tf 305 B
- assets/aom/action-callback/README.md 4.7 KB
- assets/aom/action-callback/terraform.tfvars 474 B
- assets/aom/action-callback/variables.tf 3.5 KB
- assets/aom/alarm-rule/distribute-alarm/main.tf 4.7 KB
- assets/aom/alarm-rule/distribute-alarm/providers.tf 305 B
- assets/aom/alarm-rule/distribute-alarm/README.md 6.9 KB
- assets/aom/alarm-rule/distribute-alarm/terraform.tfvars 1.7 KB
- assets/aom/alarm-rule/distribute-alarm/variables.tf 2.9 KB
- assets/aom/alarm-rule/prevent-elb-alarm-storm/main.tf 4.0 KB
- assets/aom/alarm-rule/prevent-elb-alarm-storm/providers.tf 305 B
- assets/aom/alarm-rule/prevent-elb-alarm-storm/README.md 6.9 KB
- assets/aom/alarm-rule/prevent-elb-alarm-storm/terraform.tfvars 1.3 KB
- assets/aom/alarm-rule/prevent-elb-alarm-storm/variables.tf 3.8 KB
- assets/apig/api-custom-authorizer-with-functiongraph/main.tf 4.2 KB
- assets/apig/api-custom-authorizer-with-functiongraph/providers.tf 305 B
- assets/apig/api-custom-authorizer-with-functiongraph/README.md 6.0 KB
- assets/apig/api-custom-authorizer-with-functiongraph/terraform.tfvars 1.5 KB
- assets/apig/api-custom-authorizer-with-functiongraph/variables.tf 6.1 KB
- assets/apig/kafka-forward-plugin/main.tf 4.7 KB
- assets/apig/kafka-forward-plugin/providers.tf 305 B
- assets/apig/kafka-forward-plugin/README.md 6.9 KB
- assets/apig/kafka-forward-plugin/terraform.tfvars 1.7 KB
- assets/apig/kafka-forward-plugin/variables.tf 7.2 KB
- assets/apig/proxy-cache-plugin/main.tf 2.6 KB
- assets/apig/proxy-cache-plugin/providers.tf 305 B
- assets/apig/proxy-cache-plugin/README.md 4.1 KB
- assets/apig/proxy-cache-plugin/terraform.tfvars 301 B
- assets/apig/proxy-cache-plugin/variables.tf 2.7 KB
- assets/as/alarm-policy/main.tf 4.5 KB
- assets/as/alarm-policy/providers.tf 305 B
- assets/as/alarm-policy/README.md 6.3 KB
- assets/as/alarm-policy/terraform.tfvars 785 B
- assets/as/alarm-policy/variables.tf 5.6 KB
- assets/as/scaling-configuration/main.tf 2.4 KB
- assets/as/scaling-configuration/providers.tf 305 B
- assets/as/scaling-configuration/README.md 3.9 KB
- assets/as/scaling-configuration/terraform.tfvars 628 B
- assets/as/scaling-configuration/variables.tf 3.0 KB
- assets/as/scaling-group/main.tf 3.9 KB
- assets/as/scaling-group/providers.tf 305 B
- assets/as/scaling-group/README.md 5.3 KB
- assets/as/scaling-group/terraform.tfvars 785 B
- assets/as/scaling-group/variables.tf 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.
- 9d ago First seen · 310 lines · 193 tokens per session scan A 4d754192c375
huawei-cloud-terraform-generator is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 193 tokens to every session and 3,609 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
cloud-architect
Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…