SuperAPI AI Directory
Partner中文AI newsFavorites
Skillshuawei-cloud-find-skills

huawei-cloud-find-skills

Agents & models

View repository

Updated 10-15 22:14

About this skill

[!IMPORTANT] When the user wants to search, discover, or install a Huawei Cloud (华为云) agent skill:

  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.

This skill handles skill discovery and installation only — it does not perform Huawei Cloud resource management/query tasks itself; those are handled by the skills it installs.

Overview

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

Dependency: Python 3.6+ and network access to gitcode.com (API v5 for the skill index) and github.com / raw.githubusercontent.com (for skill details). Quality telemetry is collected automatically via skill-quality-cli (installed by scripts/ensure_cli.sh if absent) — no other CLI or credential is required.

Privacy & Telemetry

Transparent Disclosure: During the search and installation process, this skill generates the following external telemetry reports. All areanonymous aggregate data(metadata such as skill name/category/service), does not includeuser input content, credentials, cloud resource data, or personally identifiable information.Quality reporting is enabled by default(opt-out): to disable it, set the environment variable export SKILL_QUALITY_REPORT=0 to disable it entirely.

Reported content Trigger point Destination Contains sensitive data
Search top-3 exposure count scripts/search-skills.py(each search) devdata2.huaweicloud.com install-count API No (only skill name/category/service)
Installation count Step 3.1 curl(before each installation) devdata2.huaweicloud.com install-count API No (only skill_id, i.e. skills/<category>/<service>/<name>）
Quality reporting skill-quality-cli run wrapped execution quality reporting APIG (test environment) No (execution status/duration/skill name)
  • Enabled by default / How to disable: The above three types of reporting areenabled by default(reporting occurs if this environment variable is not set); to disable it, execute export SKILL_QUALITY_REPORT=0（skill-quality-cli and search-skills.py both follow this switch).
  • All reporting is fire-and-forget, and never blocks the main search/installation 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 skills add https://clawhub.ai/huaweicloudskill/skills/<skill-name> (ClawHub), 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?"
  • "What VPC-related skills does Huawei Cloud have?"
  • "Browse all available Huawei Cloud skills"
  • "Install a skill for RDS management"
  • "Help me find a Huawei Cloud network-related 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)
  • skill-quality-cli — MANDATORY (Step 0.1): ensured by bash scripts/ensure_cli.sh (idempotent, skips if already present). MUST be triggered on EVERY execution of this skill before running any search/install command.
    • Upgrade: run skill-quality-cli upgrade manually (no auto-upgrade)
    • Quality reporting: Every search (Step 1) and installation (Step 3) command must be wrapped with skill-quality-cli run --skill-name huawei-cloud-find-skills -- for execution, ensuring that quality reporting is triggered on every execution

Step 0: Check Python Environment

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

⚠️ Mandatory: every hcloud command in this skill MUST be wrapped with skill-quality-cli run --skill-name huawei-cloud-find-skills -- — bare hcloud calls are strictly forbidden.

# 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: 
    # 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 0.1: Ensure skill-quality-cli (MANDATORY)

MANDATORY: Before running any search/install command, ensure skill-quality-cli is installed and available. This step MUST be triggered on EVERY execution of this skill, immediately after Step 0. It is at the same mandatory level as Step 0: Check Python Environment — do not skip it even if you believe the CLI is already present (ensure_cli.sh is idempotent and exits silently when everything is ready).

Disclosure: This CLI is only used for this skill'sanonymous quality telemetry reporting(execution status/duration, see Privacy & Telemetry); installation location ~/.local/bin, does not modify system services or global configuration; for how to disable, see Privacy & Telemetry。

# Ensure ~/.local/bin is on PATH (where skill-quality-cli is installed)
export PATH="$HOME/.local/bin:$PATH"

# Ensure skill-quality-cli is ready (idempotent: installs only if absent;
# also auto-links the CLI into a writable PATH dir so the bare command works)
bash scripts/ensure_cli.sh

# Verify availability
command -v skill-quality-cli && skill-quality-cli version
Outcome Behavior
CLI already installed & usable Silent pass — script exits immediately
CLI missing Installs the latest release into ~/.local/bin/ (prints skill-quality-cli vX.Y.Z 已就绪)
Install fails (no network, etc.) Prints a warning; never blocks the flow

ensure_cli.sh will automatically symlink skill-quality-cli into PATH the first writable directory (e.g. /usr/local/bin), so skill-quality-cli is usually directly callable. If it is still unavailable (no writable PATH directory exists), execute in the current shell:

export PATH="$HOME/.local/bin:$PATH"

Manual one-off install fallback: bash scripts/install_cli.sh.

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)

Outcome Behavior
hcloud installed and version OK (≥ 3.0.0) Silent pass — no output
hcloud installed but too old Prints an upgrade reminder (hcloud update -y)
hcloud not installed Prints an install reminder (official KooCLI guide link)

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:

⚠️ MANDATORY (quality reporting): The search command must be wrapped with skill-quality-cli run --skill-name huawei-cloud-find-skills -- to ensure that quality reporting is triggered on every search. Calling python scripts/search-skills.py。

# PowerShell
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -k "<keyword>"
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -k "<keyword>" -c "<category>"
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -c "<category>"

# Bash
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -k "<keyword>"
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -k "<keyword>" -c "<category>"
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -c "<category>"

⚠️ Security (command injection protection): keyword/category comes from user input, and it is strictly forbidden to concatenate it unescaped directly into a shell command string. If the input contains $(), $(...), backticks , ;, |` and other shell metacharacters, it will trigger command injection in Bash/PowerShell double-quoted strings. It must be invoked as follows, avoiding concatenating external input into shell strings:

  1. Preferred (recommended): Use Python subprocess argument array invocation, without going through the shell:subprocess.run([sys.executable, "scripts/search-skills.py", "-k", keyword, "-c", category])；
  2. When it must be executed in a shell, usesingle quotesWrap the user input ('<keyword>'), and escape it first (replace ' in the input with '\'') or use a shell escaping tool (shlex.quote）；
  3. When encountering inputs containing $(), backticks, ;, | and other metacharacters, prefer switching to the parameter array approach, or sanitize the input before displaying it to the user.

→ 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 only the top-3 results' skill names to the install-count API (skills/<category>/<service>/<name>) as exposure impressions — fire-and-forget, never blocks or fails the search

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.

⚠️ MANDATORY (quality reporting): The install count request must likewise be wrapped with run to ensure the installation process triggers quality reporting.

skill-quality-cli run --skill-name huawei-cloud-find-skills -- curl -s -X POST "https://devdata2.huaweicloud.com/rest/developer/fwdo/rest/developer/servlet/hdskillservice/v1/obs/findcounts/increment" -H "Accept: application/json, text/plain, */*" -H "Content-Type: application/json" -H "Origin: https://skills.huaweicloud.com" -H "Referer: https://skills.huaweicloud.com/" -d "{\"skill_id\":\"skills/<category>/<service>/<skill-name>\"}"

This is a fire-and-forget request. Do NOT block the install flow on its success or failure.

Step 3.2: Execute Install Command

⚠️ MANDATORY (quality reporting): The install command must be wrapped with skill-quality-cli run --skill-name huawei-cloud-find-skills -- sh -c '...' to ensure every installation triggers quality reporting.sh -c within the printf "\n" is used to automatically confirm npx skills add 's scope interaction prompt.

# Option A: npx skills add from GitCode (default)
skill-quality-cli run --skill-name huawei-cloud-find-skills -- sh -c 'printf "\n" | npx skills add https://gitcode.com/huaweicloud/huaweicloud-skills.git#master --skill <skill-name> -y'

# Option B: npx skills add from ClawHub
skill-quality-cli run --skill-name huawei-cloud-find-skills -- sh -c 'printf "\n" | npx skills add https://clawhub.ai/huaweicloudskill/skills/<skill-name> -y'

# Option C (fallback): npx skills add from GitHub
skill-quality-cli run --skill-name huawei-cloud-find-skills -- sh -c 'printf "\n" | npx skills add huaweicloud/huaweicloud-skills --skill <skill-name> -y'

⚠️ Security: <skill-name> must come from the canonical skill name in the Step 1 search results (thename field). It is forbidden to concatenate unvalidated user input into sh -c '...' ; if the skill name contains ' and other shell metacharacters, it must first be escaped (' → '\'') or switch to the npx skills add ... -y bare call (in which case quality reporting is changed to a manual skill-quality-cli report --skill-name huawei-cloud-find-skills）。

If all installation attempts fail, report the error message to the user. Do NOT attempt any method outside the commands above.

Parameter Confirmation

Parameter Required/Optional Description Default
Keyword Optional Search keyword (matched against name, description, triggers, service) None
Category Optional Category code for filtering (e.g., "computing", "storage", "network") None
skill-name Required (Step 3) Exact skill name for installing None

References

Document Description
GitCode API v5 index.json Skill index fetched via HTTP GET (base64 decoded)
GitCode API v5 cn-en-map.json Chinese-English keyword mapping fetched via HTTP GET (base64 decoded)
scripts/search-skills.py Search script (Python) — fetches from GitCode API v5, expands keywords, scores, sorts, reports top-3 search-result exposures
scripts/check-koocli.py Step 0.5 non-blocking KooCLI (hcloud) availability/version check
scripts/ensure_cli.sh MANDATORY (Step 0.1) idempotent installer for skill-quality-cli (installs only if absent, no auto-upgrade)
scripts/install_cli.sh Manual one-off installer for skill-quality-cli (user-triggered only)
references/iam-policies.md IAM permission description — This Skill only accesses public interfaces and requires no IAM credentials/policies
references/verification-method.md Verification method — Verification steps and expected results for each scenario
references/acceptance-criteria.md Acceptance criteria — Functional/data/security/file specification acceptance items
references/cli-installation-guide.md CLI installation/upgrade/telemetry disabling instructions

Search Heuristics

Optional reference for keyword-to-category hints. The agent can infer categories from index.json without these.

  • Cloud infrastructure keywords (ecs, bms, vpc, obs, rds, ...) → likely computing, network, storage, etc.
  • Tool keywords (cli, terraform, koo) → likely devtools
  • Management keywords (monitoring, alarm, log) → likely monitoring

Troubleshooting

Issue: python is not recognized as a command

Cause: Python 3 is not installed or not in PATH Solution: Install Python 3.6+ and ensure it is added to PATH. On Windows, re-run the installer and check "Add Python to PATH". Alternatively, use python3 if available.

Issue: skill-quality-cli: command not found (exit 127)

Cause: skill-quality-cli is installed into ~/.local/bin/, which is usually NOT on the default PATH. Solution: Re-run bash scripts/ensure_cli.sh — it now auto-links the CLI into the first writable directory on PATH (e.g. /usr/local/bin), so the bare command works. As a manual fallback, run export PATH="$HOME/.local/bin:$PATH" in the current shell. If the CLI is missing entirely, ensure_cli.sh installs it idempotently (skips if already present) and never blocks the business flow.

Issue: Script fails with SyntaxError: invalid syntax

Cause: System python points to Python 2.x (the script requires Python 3.6+) Solution: Run with python3 explicitly: python3 scripts/search-skills.py -k "<keyword>"

Issue: Script fails with "Failed to fetch index.json"

Cause: GitCode API v5 URL unreachable Solution: Verify network connectivity to gitcode.com

Issue: GitCode API v5 returns 404

Cause: File path incorrect or the branch is not test-for-index Solution: Verify the skill's category, service, and name from search results

Issue: Search returns no results

Cause: Keywords don't match any skill Solution:

  1. Try broader keywords
  2. Switch between Chinese and English keywords (e.g., "对象存储" → "obs")
  3. List all skills: python scripts/search-skills.py -c "computing"

Notes

  • This skill is read-only and does not create any cloud resources
  • No cache management needed — index is fetched fresh from GitCode API v5 each run
  • Network required — index data is hosted on GitCode, fetched via HTTP GET (base64 decoded)
  • MUST use script to search — do not read index.json directly
  • Index repo: https://gitcode.com/developer-skill/skills-group-contribution (branch: test-for-index)
  • Skills repo: https://github.com/huaweicloud/huaweicloud-skills (branch: master)
  • KooCLI: the search/install flow itself is pure Python + HTTP (no service-level hcloud commands, no --cli-region). Step 0.5 performs only a non-blocking KooCLI availability/version check (hcloud version via scripts/check-koocli.py) to warn about a missing/outdated CLI before installing skills that depend on it.