Huawei Cloud Find Skills

[!IMPORTANT] For any Huawei Cloud query or management task: 1. Search — use this skill (huawei-cloud-find-skills) to find the relevant Skill. 2. Install — install the matched Skill (see Step 3). 3. Execute — follow the installed Skill's instructions to fulfill the request.

Overview

This skill enables users to efficiently search, discover, and install Huawei Cloud skills.

<!-- cli-install-version: 3.8.0 -->

Step 0: Install skill-quality-cli (idempotent, skip if already installed)

bash scripts/ensure_cli.sh
export PATH="$HOME/.local/bin:$PATH"

The script detects whether skill-quality-cli is available; if not, it downloads the tar.gz package (wrapper + ELF + Python fallback, low-GLIBC compatible) and installs it to ~/.local/bin/. The `export PATH` line is required — ensure_cli.sh installs into ~/.local/bin/, which is usually NOT on the default PATH; without the export, bare skill-quality-cli fails with command not found (exit 127). Silently skipped when offline — never blocks the business flow.

Scenario Description

This skill enables users to:

• Search Skills: Find skills by keyword, category, or both (matched against name, description, and triggers)
• Browse Categories: Explore available skill categories
• View Skill Details: Fetch full SKILL.md content from GitHub for specific skills
• Install Skills: Guide users through skill installation via npx skills add (GitCode default), npx clawhub install, or fallback GitHub method

Architecture: GitCode API v5 (index.json + cn-en-map.json) → HTTP GET (base64 decode) → In-memory search → GitHub raw fetch for details → Install

Use Cases

• "Find a skill for managing ECS instances"
• "What Huawei Cloud skills are available for OBS?"
• "华为云有哪些 VPC 相关的 skill?"
• "Browse all available Huawei Cloud skills"
• "Install a skill for RDS management"
• "帮我找一个华为云网络相关的skill"

Prerequisites

• Python 3.6+ must be installed and available as python (or python3) in PATH
• Network access to gitcode.com (API v5 for index) and github.com / raw.githubusercontent.com (for skill details)

Step 0: Check Python Environment

MANDATORY: Before running any script command, verify Python is available.

# Check Python availability
python --version   # or: python3 --version

If the command fails or returns Python 2.x:

1. Install Python 3: Download from python.org or use a package manager: ``bash # macOS brew install python3 # Ubuntu/Debian sudo apt-get install python3 # Windows — download installer from python.org, check "Add Python to PATH" ``
2. Verify after install: Run python --version again to confirm Python 3.6+ is available
3. If `python` points to Python 2: Use python3 instead of python in all commands below

Step 0.5: Check KooCLI Version (NON-BLOCKING)

OPTIONAL: A KooCLI (hcloud) availability/version check that never blocks the flow. Skills installed later may depend on KooCLI; this step warns early, then always continues to Step 1 regardless of the outcome.

# Check KooCLI availability & version (non-blocking)
python scripts/check-koocli.py

→ scripts/check-koocli.py (Python — cross-platform)

The script always exits 0 — it is informational only and never interrupts search or installation.

Repository Info

INDEX_REPO=developer-skill/skills-group-contribution
INDEX_BRANCH=test-for-index
SKILLS_REPO=huaweicloud/huaweicloud-skills
SKILLS_BRANCH=master
RAW_BASE=https://raw.githubusercontent.com/$SKILLS_REPO/$SKILLS_BRANCH

Index Source

The search script fetches the skill index from GitCode API v5 via HTTP GET (base64 auto-decoded):

SKILLS_INDEX_URL=https://gitcode.com/api/v5/repos/developer-skill/skills-group-contribution/contents/skills-index/index.json?ref=test-for-index
SKILLS_CN_EN_MAP_URL=https://gitcode.com/api/v5/repos/developer-skill/skills-group-contribution/contents/skills-index/cn-en-map.json?ref=test-for-index

Core Workflow and Core Commands

Step 1: Search Skills

MANDATORY: The agent MUST execute the search script to search the skill index. Do NOT read the JSON file directly — always use the script.

Given keyword (from AI-understood user intent) and optional category, run the search script:

# PowerShell
python scripts/search-skills.py -k "<keyword>"
python scripts/search-skills.py -k "<keyword>" -c "<category>"
python scripts/search-skills.py -c "<category>"

# Bash
python scripts/search-skills.py -k "<keyword>"
python scripts/search-skills.py -k "<keyword>" -c "<category>"
python scripts/search-skills.py -c "<category>"

→ scripts/search-skills.py (Python — cross-platform)

What the script does:

1. Fetches index.json and cn-en-map.json via HTTP GET from GitCode API v5 (auto-decodes base64 content)
2. Expands keywords via cn-en-map.json (bidirectional CN↔EN, e.g., "ECS" → "ECS, 弹性云服务器, 云服务器")
3. Scores each skill: name match +10, trigger match +8, description match +5, service match +3
4. Sorts by score descending, outputs formatted results with matched keywords
5. Reports every result's skill name to the install-count API (skills/<category>/<service>/<name>) as an exposure impression — fire-and-forget, never blocks or fails the search
6. Auto-reports execution quality via `skill-quality-cli` (resolved as: PATH binary → ~/.local/bin/skill-quality-cli → bundled scripts/cli/cli_entry.py) — report --skill-name huawei-cloud-find-skills --status success|sys_fail|biz_fail is fired on every run (success and failure paths), fire-and-forget. No action needed from the caller; when the whole command is already wrapped with skill-quality-cli run (SKILL_TRACE_ID set), the script skips its own report to avoid double counting

Fallback iteration (if no results): 1) Switch CN↔EN keywords 2) Expand keywords 3) Remove category filter 4) Try synonyms 5) List all skills

The process should persist until the skill is found or its absence is confirmed. In the event of total failure, notify the user of the specific steps that were attempted.

Step 2: View Skill Details (optional)

Fetch the full SKILL.md content from GitHub for intent validation. Skip this step if the search results from Step 1 are sufficiently informative.

# URL pattern — use the skill's category, service, and name from index
DETAIL_URL="https://raw.githubusercontent.com/huaweicloud/huaweicloud-skills/master/skills/${category}/${service}/${name}/SKILL.md"

The agent can fetch this URL using curl or its web-fetch tool, then present the skill's full documentation to the user.

Step 3: Install Skill

MANDATORY: Before installing, the agent MUST call the install-count API to record the installation. Then use one of the install commands below. Option A is the default; Option C is a fallback when Option A is unavailable.

Step 3.1: Record Install Count

Before executing the install command, call the install-count API. The skill_id is constructed from the search results in Step 1: skills/<category>/<service>/<skill-name>.

IMPORTANT: The category and service values MUST be taken directly from the Step 1 search output (format: name (category/service)). Do NOT guess or hardcode them.