---
id: gh-huawei-cloud-find-skills
name: "huawei-cloud-find-skills"
url: https://skills.yangsir.net/skill/gh-huawei-cloud-find-skills
author: huaweicloud
domain: ai-skill-platform-ecosystem
tags: ["skill-search", "skill-discovery", "cloud-skills", "installation", "developer-tools"]
install_count: 19400
rating: 4.60 (120 reviews)
github: https://github.com/huaweicloud/huaweicloud-skills/tree/master/skills/devtools/common/huawei-cloud-find-skills
---

# huawei-cloud-find-skills

> 此技能用于在华为云技能库中快速搜索、发现并安装所需技能。用户只需描述需求（如管理 ECS、操作 OBS），即可自动匹配关键词、分类与中英文别名，返回最相关的技能列表，并指导通过 npx 或 GitHub 完成安装。适用于开发者寻找云资源管理、运维、自动化等技能的常用入口，大幅减少手工检索和排查成本。

**Stats**: 19,400 installs · 4.6/5 (120 reviews)

## Before / After 对比

### 技能查找效率对比

**Before**:

在没有此技能之前，用户需要在文档或网页中手动浏览数百个技能，逐个阅读描述，猜测关键词，反复尝试安装命令，往往耗时较长且可能安装错误。对于不熟悉技能目录的开发者，找到真正需要的技能非常困难。

**After**:

此技能能够根据用户意图自动匹配中英文关键词和分类，秒级返回相关技能列表，并给出清晰的安装步骤。用户无需翻阅大量文档，即可快速定位并安装所需技能，显著提升效率。

| Metric | Before | After | Change |
|---|---|---|---|
| 查找并安装一个技能的平均耗时 | 30分钟 | 2分钟 | -93% |

## Readme

> [!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](#step-3-install-skill)).
> 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), `gitee.com` (backup 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

> **透明披露**: 本 skill 在搜索与安装过程中会产生以下对外遥测上报。均为**匿名聚合数据**(技能名/类目/服务等元信息), **不包含**用户输入内容、凭证、云资源数据或个人身份信息。**质量上报默认开启**(opt-out): 如需关闭, 设置环境变量 `export SKILL_QUALITY_REPORT=0` 即可整体关闭。

| 上报内容 | 触发点 | 目的地 | 是否含敏感数据 |
|----------|--------|--------|----------------|
| 搜索 top-3 曝光计数 | `scripts/search-skills.py`（每次搜索） | `skills-dataset.developer.huaweicloud.com` install-count API | 否（仅技能名/类目/服务） |
| 安装计数 | Step 3.1 `curl`（每次安装前） | `skills-dataset.developer.huaweicloud.com` install-count API | 否（仅 `skill_id`，即 `skills/<category>/<name>`） |
| 质量上报 | `skill-quality-cli run` 包装执行 | quality 上报 APIG（测试环境） | 否（执行状态/耗时/技能名） |

- **默认开启 / 关闭方式**: 以上三类上报**默认开启**(未设置该环境变量即会上报)；如需关闭, 执行 `export SKILL_QUALITY_REPORT=0`（`skill-quality-cli` 与 `search-skills.py` 均遵循该开关）。
- 上报均为 **fire-and-forget**，永不阻塞搜索/安装主流程。

## 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 via `-l/--list-categories` (see Step 1.5)
- **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**: Dual-source fallback (local cache → GitCode API v5 → Gitee raw) → 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), `gitee.com` (backup 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` (stays up to date on each run; manual control available)
  - **质量上报**: 每次搜索(Step 1)与安装(Step 3)命令都必须用 `skill-quality-cli run --skill-name huawei-cloud-find-skills -- ` 包装执行, 保证每次执行都触发质量上报

### 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.**

```bash
# 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](https://www.python.org/downloads/) 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 0.1: 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).
>
> **披露**: 该 CLI 仅用于本 skill 的**匿名质量遥测上报**(执行状态/耗时, 见
> [Privacy & Telemetry](#privacy--telemetry)); 安装位置 `~/.local/bin`, 不修改系统
> 服务或全局配置; 关闭方式见 [Privacy & Telemetry](#privacy--telemetry)。

```bash
# 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 / channel unavailable) | Prints a warning; **never blocks the flow** |

> **安装通道（务必先读，避免误判为技能缺陷）**
> - `scripts/ensure_cli.sh` 是**唯一安装入口**（官方模板，勿改）：调用官网 latest 接口
>   （`skills-dataset.developer.huaweicloud.com`）取回 OBS 预签名包地址，校验 `sha256` 后安装到
>   `~/.local/bin/`；官方同时提供 `linux-arm64` / `linux-x86_64` / `windows-x86_64` 包。
> - 通道不可用 / 校验失败时仅告警并退出码 `0`，**不阻塞搜索与安装技能**；评测/CI 应视为环境不满足。
> - 该 CLI 只承载**匿名质量遥测**：拿不到它时搜索与安装流程照常可用（上报自动跳过）。
> - 失败自检与手动安装覆盖：`references/cli-installation-guide.md`。

> `ensure_cli.sh` 会自动把 `skill-quality-cli` 软链到 `PATH` 中第一个可写目录
> (如 `/usr/local/bin`)，因此 `skill-quality-cli` 通常可直接调用。若仍不可用
> (没有任何可写的 PATH 目录)，请在当前 shell 执行：
> ```bash
> export PATH="$HOME/.local/bin:$PATH"
> ```

### 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.

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

→ [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
```

## Category Ownership & External Dependency

本技能是**通用检索技能**（skill discovery / install），不属于 OBS 或任何具体云服务技能。

- 索引中的类目归属应为 **`common/utility`**（即 `common` 下的通用/工具类目）；**不得**出现在
  `devtools/common/obs` 等具体服务类目下，也不得被 `obs` 服务类目聚合命中。
- 本仓库**不含 `index.json`**：类目由外部索引仓库 `developer-skill/skills-group-contribution`
  （分支 `test-for-index`，`skills-index/index.json`）的生成流程写入。→ **类目修正属外部依赖**，
  责任方：该索引仓库的维护方（本技能的类目元数据由其发布流程生成）。
- 本仓库一侧的处理：**不在 frontmatter 追加 `service` 字段**（索引侧尚未确认支持该字段，
  硬加只会制造第二处不一致），只在此处标注归属与依赖，交由索引侧一次性修正。
- 验收口径（索引侧执行）：`-c devtools/common/obs` 的结果中不再出现 `huawei-cloud-find-skills`，
  而 `-c common`（或 `-c common/utility`）可以检索到它。

## Index Source

The search script uses a **dual-source fallback** for resilient data loading:

```
1. Local cache (~/.cache/huawei-cloud-find-skills/, TTL 1h)  — fastest, no network
2. GitCode API v5 (primary)    — WAF rate-limited, no X-RateLimit headers
3. Gitee raw (backup)          — independent IP/WAF, switched on 429
```

Primary source (GitCode API v5):
```
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
```

Backup source (Gitee raw):
```
BACKUP_INDEX_URL=https://gitee.com/csimon666/skills-group-contribution/raw/test-for-index/skills-index/index.json
BACKUP_MAP_URL=https://gitee.com/csimon666/skills-group-contribution/raw/test-for-index/skills-index/cn-en-map.json
```

On 429 (Too Many Requests), the script automatically retries with exponential backoff,
then falls through to Gitee raw — a different IP/WAF unaffected by GitCode rate limits.


## 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:

> **Category semantics (`-c/--category`)**: the index stores every category as a two-level path (`<top>/<sub>`). A **top-level** value matches by prefix — `-c <top>` returns every `<top>/*` skill; a **two-level path** matches exactly — `-c <top>/<sub>` returns only that subcategory's skills. Do not conclude "this category has no skills" before checking `-l` (Step 1.5) to confirm the category name exists.

> **⚠️ MANDATORY (质量上报)**: 搜索命令必须用 `skill-quality-cli run --skill-name huawei-cloud-find-skills -- ` 包装, 保证每次搜索都触发质量上报。严禁裸调 `python scripts/search-skills.py`。

```powershell
# 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
# 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>"
```

> **⚠️ 安全（命令注入防护）**: `keyword`/`category` 来自用户输入，严禁未转义直接拼接到 shell 命令字符串中。若输入包含 `$()`, `$(...)`, 反引号 **` `**`, `;`, `|` 等 shell 元字符，在 Bash/PowerShell 双引号字符串中会触发命令注入。必须按以下方式调用，避免将外部输入拼入 shell 字符串：
> 1. **首选（推荐）**: 用 Python `subprocess` 参数数组方式调用，不经 shell：`subprocess.run([sys.executable, "scripts/search-skills.py", "-k", keyword, "-c", category])`；
> 2. 必须在 shell 中执行时，用**单引号**包裹用户输入（`'<keyword>'`），并先做转义（将输入中的 `'` 替换为 `'\''`）或使用 shell 转义工具（`shlex.quote`）；
> 3. 遇到包含 `$()`, 反引号, `;`, `|` 等元字符的输入时，优先改为参数数组方式，或在展示给用户前对输入做脱敏处理。

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

**What the script does**:
1. Loads `index.json` and `cn-en-map.json` **at most once per process**, cache first (`~/.cache/huawei-cloud-find-skills/`, TTL 1h), then GitCode API v5, then Gitee raw (auto-decodes base64 content) — the cache hit path makes **zero** network calls
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") using a synonym index built once per process; **English stop words / junk tokens** (`no`, `the`, `such`, `zzz`, `qqq`) are dropped before expansion so they cannot substring-match the whole index
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. Convergence rule: with a keyword given, a skill is listed **only if it actually hits at least one specific (non-generic) keyword** — generic words (`huawei`, `cloud`, `skill`, …) alone never pull results in; a keyword with no searchable term returns `No results` instead of degrading to a full-index browse (browse all is what `-c <top-level>` / `-l` are for)
6. Renders each result's full coverage: multi-service skills print `覆盖: <services>` (from the index `services` array) plus the index capability type (`[只读查询]` / `[管理]` / `[演练]` / `[通用]`), so a skill whose primary `service` is one product is not mistaken for that product only
7. Appends an `Other skills covering '<keyword>'` group after the main ranking, listing coverage-only skills (index `services` covers the product but the skill name does not) so they are not buried under product-specific skills
8. Runs **at most one** fallback re-search when the primary pass yields ≤1 result (English-token retry — noise tokens dropped first — else CJK compound split), reusing the already-parsed skill fields instead of reloading the index; the fallback applies the same specific-hit rule
9. Reports only the top-3 results' skill names to the install-count API (`skills/<category>/<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) Browse categories with `-l` and list all skills under a category with `-c <top-level>`

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 1.5: Browse Categories (optional, no keyword needed)

Print the category tree aggregated from `index.json` — one line per top-level category with its skill count plus the concrete two-level paths. Use it before filtering, or to explain "category not found" to the user.

```bash
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -l
skill-quality-cli run --skill-name huawei-cloud-find-skills -- python scripts/search-skills.py -l -c "<category>"
```

The output lists lines of the form `<top> (N skill(s))` followed by `<top>/<sub>(n), ...`. Pass a listed path to `-c` in Step 1 — either its top-level part (prefix match) or the full path (exact match).

### 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.

```bash
# 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>/<skill-name>`（`category` 本身已是两级路径，如 `container/cce`）.

> **IMPORTANT**: The `category` value MUST be taken directly from the Step 1 search output (format: `name (category/service)`), using only the two-level category path. Do NOT append the `service` segment — the API accepts exactly `skills/<category>/<name>` and returns 404 otherwise. Do NOT guess or hardcode them.
>

> **⚠️ MANDATORY (质量上报)**: 安装计数请求同样用 `run` 包装, 保证安装流程触发质量上报。

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

```powershell
# PowerShell — Windows 原生（curl.exe，非 Invoke-WebRequest 别名）
skill-quality-cli run --skill-name huawei-cloud-find-skills -- curl.exe -s -X POST "https://skills-dataset.developer.huaweicloud.com/rest/developer/servlet/hdskillservice/v1/obs/findcounts/increment" -H "Accept: application/json, text/plain, */*" -H "Content-Type: application/json" -H "Origin: https://skills.developer.huaweicloud.com" -H "Referer: https://skills.developer.huaweicloud.com/" -d '{"skill_id":"skills/<category>/<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 (质量上报)**: 安装命令必须用 `skill-quality-cli run --skill-name huawei-cloud-find-skills -- ` 包装, 保证每次安装都触发质量上报。
>
> **示例命令一律是单条命令、无管道包裹**：不要写成 `... | grep xxx`，也不要写成 `sh -c 'printf "\n" | npx skills add ...'`。
> `-y` 已自动确认安装范围提示，逐条执行、先看退出码再自行过滤输出，命令才能在 CI/评测里独立判定成功或失败。

```bash
# Option A: npx skills add from GitCode (default) — 装到当前项目的 .agents/skills/
skill-quality-cli run --skill-name huawei-cloud-find-skills -- npx skills add https://gitcode.com/huaweicloud/huaweicloud-skills.git#master --skill <skill-name> -y

# Option A': 装到用户级（全局）而不是当前项目：加 -g
skill-quality-cli run --skill-name huawei-cloud-find-skills -- npx skills add https://gitcode.com/huaweicloud/huaweicloud-skills.git#master --skill <skill-name> -g -y

# Option B: npx skills add from ClawHub
skill-quality-cli run --skill-name huawei-cloud-find-skills -- 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 -- npx skills add huaweicloud/huaweicloud-skills --skill <skill-name> -y
```

```powershell
# Option A: npx skills add from GitCode (default) — Windows 原生
skill-quality-cli run --skill-name huawei-cloud-find-skills -- 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 -- 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 -- npx skills add huaweicloud/huaweicloud-skills --skill <skill-name> -y
```

> **Windows 回退方案**（`npx skills add` 失败时，如 `spawn EPERM`）：
> 1. **先 clone 再本地安装**：`git clone https://gitcode.com/huaweicloud/huaweicloud-skills.git` → `npx skills add ./huaweicloud-skills --skill <skill-name> -y`
> 2. **手动安装**：把技能目录复制到项目 `.agents\skills\<skill-name>\`（或用户级 `%USERPROFILE%\.agents\skills\<skill-name>\`），
>    并在同级锁文件里补一条记录 —— 项目级是 `<项目根>\skills-lock.json`，用户级是 `%USERPROFILE%\.agents\.skill-lock.json`

> **⚠️ 安全**: `<skill-name>` 必须来自 Step 1 搜索结果的规范技能名（`name` 字段），禁止拼接未经校验的用户输入；若技能名含 `'` 等 shell 元字符，须先转义（`'` → `'\''`）或改用 `npx skills add ... -y` 裸调用（此时质量上报改为安装完成后手动 `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.

#### Step 3.3: 安装目录与生效（装完看不到？先看这里）

安装成功 ≠ 当前会话立刻可见：各运行时都在**会话/工作区启动时**扫描一次技能目录，已打开的会话沿用启动时的清单。

| 运行时 | 安装目录（项目级 / 用户级） | 锁文件 | 生效方式 | 验证命令 |
|--------|------------------------------|--------|----------|----------|
| **AI DevSpace / CodeArts AI Shell** | 项目级 `<项目根>` 下 `.agents/skills/` 中的 `<skill-name>/`；用户级 `~/.agents/skills/` 中的 `<skill-name>/` | 项目级 `<项目根>/skills-lock.json`；用户级 `~/.agents/.skill-lock.json` | 当前会话**不会**刷新技能清单 → 新开工作区/会话（或重载 IDE 窗口） | `npx skills ls` + 目录/锁文件检查（见下） |
| **Hermes** | 技能根 `~/.hermes/skills/<skill-name>/`（ACP / 独立 profile 用该 profile 的 `skills/` 目录） | 无（Hermes 直接扫描目录，不读 `skills-lock.json`） | 会话开始时扫描 → 新会话（`/new`）或重启进程；也可在 config 里把 `~/.agents/skills` 配成 `skills.external_dirs`（本机技能优先） | 目录检查 + 新会话 `skills_list` 能看到该技能 |
| **Windows 原生（PowerShell）** | 项目级 `<项目根>\.agents\skills\<skill-name>\`；用户级 `%USERPROFILE%\.agents\skills\<skill-name>\` | 项目级 `<项目根>\skills-lock.json`；用户级 `%USERPROFILE%\.agents\.skill-lock.json` | 同 AI DevSpace：新开会话/窗口 | `npx skills ls` + `Test-Path` 检查 |

**验证（复制即用）**

```bash
# ① 最权威的一条：列出本运行时已安装的技能及其落盘路径
npx skills ls

# ② AI DevSpace / CodeArts AI Shell —— 项目级（AGENTS_SKILLS_DIR 即该运行时的技能根）
AGENTS_SKILLS_DIR=".agents/skills"
ls -l "${AGENTS_SKILLS_DIR}/<skill-name>/SKILL.md"
python3 -c "import json;print(json.load(open('skills-lock.json'))['skills']['<skill-name>'])"

# ③ AI DevSpace / CodeArts AI Shell —— 用户级（-g 安装）
ls -l "${HOME:?}/${AGENTS_SKILLS_DIR}/<skill-name>/SKILL.md"
python3 -c "import json,os;print(json.load(open(os.path.expanduser('~/.agents/.skill-lock.json')))['skills']['<skill-name>'])"

# ④ Hermes —— 技能根目录（ACP/独立 profile 换成该 profile 的 skills 目录）
ls -l ~/.hermes/skills/<skill-name>/SKILL.md
```

```powershell
# Windows 原生
npx skills ls
Test-Path .agents\skills\<skill-name>\SKILL.md
Test-Path "$env:USERPROFILE\.agents\skills\<skill-name>\SKILL.md"
```

**怎么判定**（不依赖任何"想象中的目录"）：
- `npx skills ls` 列出的路径与 `ls`/`Test-Path` 结果**一致存在** → 安装成功；此时当前会话仍看不到 = **未生效**，新开会话即可，不要重装。
- `npx skills ls` 有记录但目录不存在 → 链接/复制失败，按 Step 3.2 的 Windows 回退方案手动复制技能目录并补锁文件条目。
- `npx skills ls` 无记录且目录不存在 → 安装真的失败，回报 Step 3.2 的原始错误信息。
- Hermes：目录存在但新会话 `skills_list` 里没有 → 确认目录在**技能根**下（不是任意子目录外），并重启进程后再看。
- 平台是否支持技能热加载以该平台版本文档为准；本技能**不假设热加载**，一律按"新会话/重载后生效"判定。

## Parameter Confirmation

| Parameter | Required/Optional | Description | Default |
|-----------|-------------------|-------------|---------|
| `Keyword` | Optional | Search keyword (matched against name, description, triggers, service/services) | None |
| `Category` | Optional | Category filter: a top-level category matched by prefix (covers all its subcategories) or a two-level path matched exactly | 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](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](scripts/check-koocli.py) | Step 0.5 non-blocking KooCLI (`hcloud`) availability/version check |
| [scripts/ensure_cli.sh](scripts/ensure_cli.sh) | **MANDATORY (Step 0.1)** idempotent installer for `skill-quality-cli` (official template: latest endpoint + sha256 verify; installs only if absent) |
| [references/iam-policies.md](references/iam-policies.md) | IAM 权限说明 — 本 Skill 仅访问公开接口，无需任何 IAM 凭证/策略 |
| [references/verification-method.md](references/verification-method.md) | 验证方法 — 各场景的验证步骤与预期结果 |
| [references/acceptance-criteria.md](references/acceptance-criteria.md) | 验收标准 — 功能/数据/安全/文件规范验收项 |
| [references/cli-installation-guide.md](references/cli-installation-guide.md) | CLI 安装/升级/遥测关闭说明（官方 latest 通道 + sha256 校验）+ 失败自检与手动安装路径 |

## 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, or the `-c` value is not a category that exists in the index
**Solution**:
1. List the available categories first: `python scripts/search-skills.py -l` (or narrow with `-l -c "<category>"`)
2. If the category exists, browse everything under it without a keyword: `python scripts/search-skills.py -c "<top-level>"` (prefix match) or `-c "<top>/<sub>"` (exact path)
3. Switch between Chinese and English keywords (e.g., "对象存储" → "obs")
4. Try broader keywords

## Notes

- This skill is **read-only** and does not create any cloud resources
- **Dual-source with caching** — local cache (TTL 1h) → GitCode API v5 → Gitee raw (on 429)
- **Cache location** — `~/.cache/huawei-cloud-find-skills/`, TTL configurable via `FIND_SKILLS_CACHE_TTL` env var (default 3600s)
- **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.


---
*Source: https://skills.yangsir.net/skill/gh-huawei-cloud-find-skills*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-huawei-cloud-find-skills/markdown*