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-testergit 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-tester)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-tester"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-tester/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-tester"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-skill-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
- Socket warn
- Snyk pass
SkillSpector: 5 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 Rogue Agent · line 38 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 69 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 Excessive Agency · line 277 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 Excessive Agency · line 320 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 Excessive Agency · line 296 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 | $0.00189 | $0.05420 |
| Opus 5.5 | $0.00076 | $0.02168 |
| Sonnet 5.5 | $0.00038 | $0.01084 |
| Haiku 4.5 | $0.00019 | $0.00542 |
Grade A, and why
huawei-cloud-skill-tester 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 1mo 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 — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud Skill Tester — Three-Track Eight-Phase E2E Testing Pipeline
Independent, repeatable Huawei Cloud Skill testing framework. Does not depend on skill-creator; can test any existing Huawei Cloud Skill. Focuses on real-environment functional testing and multi-skill orchestration scenarios.
Overview
This Skill provides a three-track, eight-phase standardized testing pipeline (three-tier layout × 8 phases total: Phase 0-6 execution + Phase 7 final report):
| Tier | Phases | Goal |
|---|---|---|
| Tier 1: Single-Skill Unit Testing | Phase 0~4 | Verify each skill item by item: installation, feature extraction, technical research, test case generation, execution |
| Tier 2: Integration Testing | Phase 5~6 | Multi-skill orchestration scenario derivation + end-to-end real-environment flow verification |
| Tier 3: Final Report | Phase 7 | Consolidated report merging all phase outputs |
Core Design Principles
- Chain Verification — Before each Phase, check that the previous phase's JSON exists; if missing, refuse to execute
- Agent-proof — Write operations require user confirmation for each item; automatic gate bypassing is not allowed
- Three-Track Layering — Clear gates between Tiers; Tier 1 must be completed before entering Tier 2
- Batch Repeatable — Supports
--skills "skill-a,skill-b"or--all-installed - Fallback Strategy — When only 1 skill, Phase 5/6 automatically downgrade to single-skill lifecycle testing. Sibling auto-scan is ON by default (Phase 5/6 automatically looks for other
huawei-cloud-*skills in the same directory as the skill under test to run orchestration combos). Use--no-siblingsto opt-out. - Standardized JSON Output — All phases output in a unified schema; Phase 7 merges into a single report
- Real-Environment First — Tier 2 phases run against real Huawei Cloud where applicable (write operations gated by
ALLOW_WRITES); multi-skill Phase 6 currently derives a scenario plan without real execution, while single-skill Phase 6 runs a real create→query→update→delete loop. No mocks or simulations.
What ships with it
27 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 5.3 KB
- references/agent-protocol.md 4.2 KB
- references/architecture.md 3.4 KB
- references/cli-installation-guide.md 954 B
- references/iam-policies.md 774 B
- references/output-schema-spec.md 28 KB
- references/phase-details.md 26 KB
- references/phase-transition-rules.md 5.7 KB
- references/verification-method.md 11 KB
- scripts/ensure_cli.sh 4.7 KB runs code
- scripts/install_cli.sh 3.2 KB runs code
- scripts/lib/chain-verify.sh 4.1 KB runs code
- scripts/lib/config.sh 11 KB runs code
- scripts/lib/placeholder-utils.py 3.2 KB runs code
- scripts/lib/utils.sh 21 KB runs code
- scripts/run-test-pipeline.sh 8.6 KB runs code
- scripts/tier1/phase-0-install-check.sh 11 KB runs code
- scripts/tier1/phase-1-skill-analysis.sh 29 KB runs code
- scripts/tier1/phase-2-tech-research.sh 13 KB runs code
- scripts/tier1/phase-3-gen-testcases.sh 18 KB runs code
- scripts/tier1/phase-4-execute-tests.sh 30 KB runs code
- scripts/tier2/phase-5-orchestration.sh 18 KB runs code
- scripts/tier2/phase-6-full-flow.sh 21 KB runs code
- scripts/tier3/phase-7-final-report.sh 33 KB runs code
- templates/phase-report-schema.json 1.2 KB
- templates/scenario-example.json 3.0 KB
- templates/test-case-schema.json 1.5 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.
- 1mo ago Changed · -79 lines scan E → A ab9cacb56e0d
- 1mo ago Changed · +28 lines scan A → E 6093a5cda8e7
- 1mo ago Changed · +11 lines 98eff6debc64
- 1mo ago Changed · +54 lines 497a5448d684
- 1mo ago First seen · 321 lines · 189 tokens per session scan A f2013145b708
huawei-cloud-skill-tester is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 5,420 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
maestro-work
The contract every playbook shares - the brief a writer receives, the rules it writes by, the handback it returns, and the store record the holder keeps. Reuse existing checks and add tests only for concrete uncovered behavior or risk.
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
proof-strategy
Produce a test strategy for a project or feature — risk map, test type decisions, coverage targets, CI config. Use when asked to "create test strategy", "what should we test", "testing plan", or "improve test coverage".
testing-expert
Expert-level software testing with unit tests, integration tests, E2E tests, TDD/BDD, and testing best practices. Use when the user mentions TDD, BDD, unit tests, integration tests, or end-to-end tests, or when the task involves Testing Fundamentals, Unit Testing, Integration Testing, or End-to-End Testing.
automacao-de-testes
Automação de testes: unitários (Jest, Pytest), integração (supertest, httpx) e E2E com Playwright. Inclui estratégia de pirâmide de testes, cobertura mínima, CI/CD integration e testes para contexto brasileiro (CPF, CNPJ, CEP, PIX).