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-kunpeng-source-code-migrategit 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-kunpeng-source-code-migrate)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kunpeng-source-code-migrate"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kunpeng-source-code-migrate/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-kunpeng-source-code-migrate"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-kunpeng-source-code-migrate.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 | $0.00304 | $0.07078 |
| Opus 5.5 | $0.00122 | $0.02831 |
| Sonnet 5.5 | $0.00061 | $0.01416 |
| Haiku 4.5 | $0.00030 | $0.00708 |
Grade D, and why
huawei-cloud-kunpeng-source-code-migrate scanned grade D 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
tar -xzf huaweicloud-cli-linux-amd64.tar.gz && chmod +x hcloud && sudo mv hcloud /usr/local/bin/ Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| ❌ Execute destructive commands on remote server (rm -rf, format, etc.) | Prevent irreversible damage | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Root access required (default install path):** `install_devkit.sh` installs to `/usr/local` and creates a `/usr/local/bin/devkit` symlink, which requires root. Non-root users MUST use the `--no-sudo` flag (installs t How it starts
The opening of the file, as written. The whole thing — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kunpeng Source Code Migration Assessment
Analyze the migrability of C/C++/ASM/Fortran/Go/Java/Python/Scala source code to Kunpeng (ARM64) platform using Huawei DevKit CLI tool.
Overview
This skill assesses source code migrability to the Kunpeng (ARM64) platform using Huawei DevKit CLI. It connects to a source server via SSH (or installs locally), installs DevKit, scans source code, and generates a migration assessment report. If the user has no remote server, it can automatically provision a Kunpeng ECS instance on Huawei Cloud (Guiyang Region 1) via hcloud CLI.
⚠️ Analysis depth varies by language (DevKit limitation): C/C++/ASM = deep analysis; Fortran = shallow; Go/Java/Python/Scala = file-level stats only (architecture-dependent code like JNI/CGo/ctypes/unsafe will NOT be detected — manual review required). See Supported Languages for details.
Architecture: Local detection + remote execution + SFTP transfer. All SSH operations use the unified scripts/ssh_client.py (paramiko + password env var), cross-platform consistent.
Applicable scenarios: Assess source code portability to Kunpeng ARM; scan C/C++/ASM/Fortran/Go/Java/Python/Scala code; generate a migration report; check ARM64 compatibility; provision a Kunpeng server on Huawei Cloud.
Report save path: Windows → C:\devkit-report\, Linux/macOS → ~/devkit-report/ (resolved from current user's home, NOT hardcoded /home/).
Prerequisites
CLI version requirements:
| Tool | Version | Purpose |
|---|---|---|
| Python | 3.x | Run ssh_client.py, detect_os.py, paramiko dependency |
| paramiko | latest stable | SSH connection (pip install paramiko) |
| hcloud (KooCLI) | >= 3.2.0 | Only needed for provisioning path (Step 3d) |
| DevKit CLI | auto-installed by install_devkit.sh |
Source code migration scan |
Authentication:
- Root access required (default install path):
install_devkit.shinstalls to/usr/localand creates a/usr/local/bin/devkitsymlink, which requires root. Non-root users MUST use the--no-sudoflag (installs to$HOME/.local/devkit) and add DevKit to PATH manually:export PATH=$HOME/.local/devkit:$PATH. If system dependencies (python3, pip3, curl) are missing and--no-sudois set, the script will error out — install them first or run as root. - SSH user: The default SSH user is
root(seeKUNPENG_SERVER_USER). Non-root SSH users are supported, but the remote install path and report download path will be under that user's home directory (see--no-sudoabove). - SSH credentials (existing server, Step 3c): User must set env vars
KUNPENG_SERVER_HOST,KUNPENG_SERVER_PORT(default 22),KUNPENG_SERVER_USER(default root),MIGRATE_SSH_PASSin their own terminal. AI must NEVER ask for or echo these values. - Huawei Cloud AK/SK (provisioning path, Step 3d): User must run
hcloud configure set --cli-region=cn-southwest-2 --cli-access-key=<your-ak> --cli-secret-key=<your-sk>in their own terminal. AI must NEVER ask for AK/SK.
What ships with it
19 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 14 KB
- references/cli-installation-guide.md 12 KB
- references/devkit-cli-reference.md 7.1 KB
- references/devkit-installation-guide.md 3.8 KB
- references/iam-policies.md 10 KB
- references/migration-report-guide.md 8.6 KB
- references/prerequisites.md 16 KB
- references/scripts-guide.md 18 KB
- references/task-connect-server.md 8.9 KB
- references/task-install-devkit.md 7.7 KB
- references/task-local-devkit.md 6.6 KB
- references/task-prepare-server.md 25 KB
- references/task-scan-source-code.md 22 KB
- references/troubleshooting.md 31 KB
- references/verification-method.md 12 KB
- scripts/detect_os.py 4.9 KB runs code
- scripts/install_devkit.sh 15 KB runs code
- scripts/provision_kunpeng_server.sh 31 KB runs code
- scripts/ssh_client.py 40 KB runs code
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.
- 4d ago Changed · -70 lines 9463eecfcddc
- 1mo ago First seen · 494 lines · 304 tokens per session scan D 76e91a23c38d
huawei-cloud-kunpeng-source-code-migrate is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 304 tokens to every session and 7,078 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…