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-optv-evolve-managementgit 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-optv-evolve-management)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-optv-evolve-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-optv-evolve-management/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-optv-evolve-management"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-optv-evolve-management.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 | $0.00173 | $0.09822 |
| Opus 5 | $0.00086 | $0.04911 |
| Sonnet 5 | $0.00035 | $0.01964 |
| Haiku 4.5 | $0.00017 | $0.00982 |
Grade B, and why
huawei-cloud-optv-evolve-management scanned grade B with 3 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 2d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| `requests.post('https://optverse...', json=...)` direct to OpenAPI | Bypasses KooCLI auth / error handling / retry / `--debug` logging; crosses the "direct OpenAPI" red line | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `requests.post('https://optverse...', json=...)` direct to OpenAPI | Bypasses KooCLI auth / error handling / retry / `--debug` logging; crosses the "direct OpenAPI" red line | Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| Direct Python fork (**not recommended**) | `python -c "import subprocess; subprocess.run(['hcloud',...])"` | Bypasses agent-framework isolation / cache semantics | How it starts
The opening of the file, as written. The whole thing — 676 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ Execution Method (Must Read): All scripts must be executed via
skill action=exec; do not run them directly in the shell.
- All OptVerse calls in this skill MUST go through KooCLI (command-line entry
hcloud). Direct calls to the OptVerse OpenAPI viarequestsor any other HTTP library are forbidden.- Files in
scripts/are skill-shipped helper tools (zip_helper.py/cache.py); all of them are pure-local tools that do not invoke KooCLI subprocesses.- The Agent itself MUST NOT create one-off temporary
.pyscript files; for Python JSON processing, preferpython -c "..."inline execution. Do NOT create temporary script files (.py/.zip/.json/.tomletc.); temporary artefacts (zip packages, JSON caches, scan results) go under.stats/orOPTV_CACHE_DIRin a fixed location, and must be cleaned up after use. ⚠️ Security Rule (Must Read): Never expose AK / SK in conversation, scripts, or output. Only verify credential presence viahcloud configure list.
Algorithm Auto-Design Skill (English)
Overview
End-to-end code evolution on the Huawei Cloud Scientific Computing Zone — Algorithm Design Module:
- Upload algorithm code, evaluator and baseline into an algorithm design project
- Create and start an evolve task, monitor progress, fetch results and logs
When result upload to OBS bucket is required (optional path, skip for default scenario):
- Create / maintain an IAM Agency as the cross-service trust anchor
- Grant bucket (OBS) permissions to the algorithm design module
Supported languages:
| Language | Algorithm | evaluator | baseline |
|---|---|---|---|
| Python | source file + function name | source file (e.g. evaluator.py) with def evaluate(): |
source file (e.g. baseline.py) with def baseline(): |
| C++ | source file + function name (evolved function) | compiled executable command (e.g. build/evaluate <args>) |
compiled executable command (may equal evaluator) |
C++ projects use CreateAlgorithm --build_command to compile the uploaded .cpp files into executables. The evaluator_file / evaluator_baseline fields are left blank for C++; only the command name is provided.
What ships with it
28 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/agency-policy.md 4.2 KB
- references/algorithm-workflow.md 7.3 KB
- references/api-mapping.md 8.5 KB
- references/cli-installation-guide.md 4.6 KB
- references/evolve-task-workflow.md 10.0 KB
- references/iam-agency.md 11 KB
- references/iam-policies.md 9.3 KB
- references/language-cpp.md 8.4 KB
- references/language-python.md 7.7 KB
- references/parameter-format.md 5.6 KB
- references/plan-maintenance.md 4.4 KB
- references/prerequisites.md 8.2 KB
- references/readme.md 2.8 KB
- references/result-logs-status.md 4.7 KB
- references/troubleshooting.md 9.2 KB
- references/verification-method.md 5.3 KB
- scripts/build_task_url.py 6.8 KB runs code
- scripts/cache.py 9.9 KB runs code
- scripts/precheck.ps1 6.8 KB runs code
- scripts/precheck.sh 6.7 KB runs code
- scripts/readme.md 4.9 KB
- scripts/zip_helper.py 2.9 KB runs code
- templates/cpp/baseline.cpp 706 B
- templates/cpp/evaluator.cpp 1.2 KB
- templates/python/algorithm.py 592 B runs code
- templates/python/baseline.py 349 B runs code
- templates/python/evaluator.py 1017 B runs code
- templates/README.md 5.2 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.
- 2d ago First seen · 676 lines · 173 tokens per session scan B c5e850bcfb92
huawei-cloud-optv-evolve-management is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (49 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 9,822 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 3 findings (sends data to an external url, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.
Other skills, from other repositories
pysr
Use when fitting equations to data with PySR or SymbolicRegression.jl, when a user wants an interpretable formula, symbolic model, scaling law, or empirical relation discovered from numeric data, or when debugging a PySR search that is slow, stuck, or giving poor equations.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cudaq-importing
Use when porting circuits from another framework (e.g. Qiskit) into CUDA-Q kernels while preserving the source algorithm and validation fidelity.
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
tilelang-cuda-examples-torch
A collection of runnable examples showing how to write CUDA kernels in TileLang, a Python-like language for GPU code, and use them with PyTorch, a machine-learning library.
gdal-api
Use when programming against GDAL/OGR in C, C++, Python, or .NET for raster/vector I/O, coordinate transformation, or custom geospatial algorithms. GDAL API: low-level programming interface for reading/writing 70+ geospatial formats.