CtrlK
BlogDocsLog inGet started
Tessl Logo

alicloud-find-skills

搜索、发现和安装阿里云 Agent Skills。当用户提到阿里云、alicloud、aliyun、 ECS、RDS、OSS 等阿里云服务操作或需要查找阿里云相关 skill 时触发。 典型触发词:"找阿里云 skill"、"搜索 alicloud skills"、"有没有管理 ECS 的 skill"、 "阿里云 skills 有哪些类目"、"安装阿里云 skill"。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced CLI skill body with executable commands throughout and a real retry/feedback loop. It is held back from the top band by flag repetition across examples and inline reference material that would benefit from extraction into bundle files.

Suggestions

Reduce repetition by defining the shared --endpoint/--user-agent flags once and referencing them, or factor the full command templates into a references/ file linked from Step 2.

Move the RAM minimal-permission policy JSON into a references/ram-policy.json or references/RAM.md file and link to it, shrinking the inline body.

Make validation gates explicit in the workflow (e.g., 'Confirm search returned ≥1 result before declaring no Skill exists') rather than leaving checkpoints implicit.

DimensionReasoningScore

Conciseness

Mostly efficient — the body is dominated by executable commands and tables rather than explanations of concepts Claude already knows, but the --endpoint/--user-agent flags are repeated verbatim in every command and the 常用场景示例 table partially re-shows search examples already covered in Step 2.

4 / 5

Actionability

Every command is complete and copy-paste ready with all required flags (--endpoint, --user-agent, --search-mode, --max-results), and the common-cases table maps real user requests to concrete commands.

5 / 5

Workflow Clarity

A clear five-step sequence with verification checkpoints (plugin list grep, post-install verification) and an explicit feedback loop in Step 3 (iterate search with synonym/keyword adjustments); held at 4 because some checkpoints are implicit rather than called out as validation gates.

4 / 5

Progressive Disclosure

Well-organized into clear sections (前置条件, API 调用规范, 核心工作流, RAM 权限, 安全注意事项) with no nested references, but the ~120-line body inlines material (RAM policy JSON, full install snippets) that could live in separate reference files; no bundle files are present.

4 / 5

Total

17

/

20

Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that states concrete capabilities, rich natural trigger terms with synonyms, and explicit when-to-use guidance. The only minor weakness is slight redundancy between 'search' and 'discover' as distinct actions.

DimensionReasoningScore

Specificity

Names the domain and three concrete actions — "搜索、发现和安装阿里云 Agent Skills" (search, discover, install) — but 'discover' overlaps with 'search', leaving minor coverage gaps relative to the body's full capability set (e.g. browse-by-category is not named as an action).

4 / 5

Completeness

Explicitly answers both 'what' (搜索、发现和安装阿里云 Agent Skills) and 'when' ("当用户提到...时触发" plus a 典型触发词 list), matching the anchor for concrete trigger phrases on both halves.

5 / 5

Trigger Term Quality

Comprehensive coverage including synonyms (阿里云/alicloud/aliyun), service tokens (ECS/RDS/OSS), and five natural trigger phrases users would actually say ("找阿里云 skill", "安装阿里云 skill", etc.).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (finding/installing Alibaba Cloud Agent Skills) with triggers scoped to 阿里云/alicloud/aliyun, giving minimal conflict risk with non-Alibaba-cloud skills.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.