alicloud-skill-creator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Category: tool

分类：工具

Alibaba Cloud Skill Creator

阿里云技能创建器

Repository-specific skill engineering workflow for

alicloud-skills

专为

alicloud-skills

仓库打造的技能研发工作流。

Use this skill when

适用场景

Creating a new skill under
```
skills/**
```
.
Importing an external skill and adapting it to this repository.
Updating skill trigger quality (
```
name
```
and
```
description
```
in frontmatter).
Adding or fixing smoke tests under
```
tests/**
```
.
Running structured benchmark loops before merge.

在
```
skills/**
```
目录下创建新技能。
导入外部技能并适配到本仓库。
优化技能触发器质量（即frontmatter中的
```
name
```
和
```
description
```
字段）。
在
```
tests/**
```
目录下添加或修复冒烟测试。
在代码合并前运行结构化基准测试循环。

Do not use this skill when

不适用场景

The user only needs to execute an existing product skill.
The task is purely application code under
```
apps/
```
with no skill changes.

用户仅需要执行已有的产品技能。
任务仅涉及
```
apps/
```
目录下的纯应用代码，无技能相关变更。

Repository constraints (must enforce)

仓库约束（必须遵守）

Skills live under

skills/<domain>/<subdomain>/<skill-name>/

Skill folder names use kebab-case and should start with
```
alicloud-
```
.
Every skill must include
```
SKILL.md
```
frontmatter with
```
name
```
and
```
description
```
.
```
skills/**/SKILL.md
```
content must stay English-only.

Smoke tests must be in

tests/<domain>/<subdomain>/<skill-name>-test/SKILL.md

Generated evidence goes to
```
output/<skill-or-test-skill>/
```
only.
If skill inventory changes, refresh README index with
```
scripts/update_skill_index.sh
```
.

技能存放路径为

skills/<domain>/<subdomain>/<skill-name>/

。

技能文件夹名称采用kebab-case命名，且必须以
```
alicloud-
```
开头。
每个技能必须包含带有
```
name
```
和
```
description
```
字段的
```
SKILL.md
```
frontmatter。
```
skills/**/SKILL.md
```
文件内容必须保持全英文。

冒烟测试必须存放于

tests/<domain>/<subdomain>/<skill-name>-test/SKILL.md

。

生成的证明文件仅可存放于
```
output/<skill-or-test-skill>/
```
目录下。
如果技能清单发生变更，需使用
```
scripts/update_skill_index.sh
```
脚本更新README索引。

Standard deliverable layout

标准交付物结构

text

skills/<domain>/<subdomain>/<skill-name>/
├── SKILL.md
├── agents/openai.yaml
├── references/
│   └── sources.md
└── scripts/ (optional)

tests/<domain>/<subdomain>/<skill-name>-test/
└── SKILL.md

text

skills/<domain>/<subdomain>/<skill-name>/
├── SKILL.md
├── agents/openai.yaml
├── references/
│   └── sources.md
└── scripts/ (optional)

tests/<domain>/<subdomain>/<skill-name>-test/
└── SKILL.md

Workflow

工作流

Capture intent

Confirm domain/subdomain and target skill name.
Confirm whether this is new creation, migration, or refactor.
Confirm expected outputs and success criteria.

Implement skill changes

For new skills: scaffold structure and draft
```
SKILL.md
```
+
```
agents/openai.yaml
```
.
For migration from external repo: copy full source tree first, then adapt.
Keep adaptation minimal but explicit:
- Replace environment-specific instructions that do not match this repo.
- Add repository validation and output discipline sections.
- Keep reusable bundled resources (
```
scripts/
```
  ,
```
references/
```
  ,
```
assets/
```
  ).

Add smoke test

Create or update
```
tests/**/<skill-name>-test/SKILL.md
```
.
Keep it minimal, reproducible, and low-risk.
Include exact pass criteria and evidence location.

Validate locally

Run script compile validation for the skill:

bash

python3 tests/common/compile_skill_scripts.py \
  --skill-path skills/<domain>/<subdomain>/<skill-name> \
  --output output/<skill-name>-test/compile-check.json

Refresh skill index when inventory changed:

bash

scripts/update_skill_index.sh

Confirm index presence:

bash

rg -n "<skill-name>" README.md README.zh-CN.md README.zh-TW.md

Optional broader checks:

bash

make test
make build-cli

Benchmark loop (optional, for major skills)

If the user asks for quantitative skill evaluation, reuse bundled tooling:

```
scripts/run_eval.py
```
```
scripts/aggregate_benchmark.py
```
```
eval-viewer/generate_review.py
```

Prefer placing benchmark artifacts in a sibling workspace directory and keep per-iteration outputs.

捕获需求

确认领域/子领域和目标技能名称。
确认是新技能创建、迁移还是重构。
确认预期输出和成功标准。

实现技能变更

新技能：搭建基础结构，编写
```
SKILL.md
```
+
```
agents/openai.yaml
```
初稿。
从外部仓库迁移：先复制完整源码树，再进行适配。
适配工作尽量精简但清晰：
- 替换不符合本仓库规范的环境特定说明。
- 添加仓库验证和输出规范章节。
- 保留可复用的捆绑资源（
```
scripts/
```
  、
```
references/
```
  、
```
assets/
```
  ）。

添加冒烟测试

创建或更新
```
tests/**/<skill-name>-test/SKILL.md
```
。
保持测试精简、可复现、低风险。
包含明确的通过标准和证明文件存放位置。

本地验证

运行脚本对技能进行编译验证：

bash

python3 tests/common/compile_skill_scripts.py \
  --skill-path skills/<domain>/<subdomain>/<skill-name> \
  --output output/<skill-name>-test/compile-check.json

技能清单变更后刷新技能索引：

bash

scripts/update_skill_index.sh

确认索引已更新：

bash

rg -n "<skill-name>" README.md README.zh-CN.md README.zh-TW.md

可选的更全面检查：

bash

make test
make build-cli

基准测试循环（可选，适用于核心技能）

如果用户需要对技能进行量化评估，可复用捆绑工具：

```
scripts/run_eval.py
```
```
scripts/aggregate_benchmark.py
```
```
eval-viewer/generate_review.py
```

建议将基准测试产物存放在同级工作区目录下，并保留每次迭代的输出。

Definition of done

完成标准

Skill path and naming follow repository conventions.
Frontmatter is complete and trigger description is explicit.
Test skill exists and has objective pass criteria.
Validation artifacts are saved under
```
output/
```
.
README skill index is refreshed if inventory changed.

技能路径和命名符合仓库规范。
Frontmatter字段完整，触发器描述清晰明确。
测试技能已存在，且有客观的通过标准。
验证产物已保存至
```
output/
```
目录下。
若技能清单发生变更，README技能索引已更新。

References

参考资料

```
references/schemas.md
```
```
references/sources.md
```

```
references/schemas.md
```
```
references/sources.md
```