CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skills-manager

搜索、安装或创建 Agent Skill;用户说“find a skill”“搜索技能”“帮我做个 skill”或想扩展能力时使用。

Quality

90%

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

92%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.

An exceptionally lean, highly actionable skill body with concrete commands, explicit runtime fallbacks, safety checkpoints, and a validation feedback loop. The only notable gap is that the post-creation validation step says what to check but not how to check it.

Suggestions

In creation step 4, specify how to validate: e.g., the concrete check for frontmatter syntax, how to test the trigger description, and what running 'one real use case' looks like.

Add one example of expected search results (name/功能/来源 fields) so Claude knows what output shape to present to the user.

DimensionReasoningScore

Conciseness

The ~28-line body is lean and operational with zero concept-explanation padding; every line carries a decision, command, or rule. The single explanatory note ("Skills 是第三方代码有完整权限") directly justifies the mandatory security warning and earns its place, matching anchor 5.

5 / 5

Actionability

Concrete copy-paste-ready commands are given throughout: "npx skills find [query]", "npx skills add <owner/repo@skill> -y", "npx skills init <skill-name>", plus an explicit runtime fallback chain ("优先 npx skills,备选 $CHERRY_STUDIO_BUN_PATH x skills,都没有则提示安装 Node.js"). It stops short of 5 because step 4's validation ("验证 frontmatter、触发描述和一个真实用例") specifies what to validate but not how, and no example of expected search/add output is shown.

4 / 5

Workflow Clarity

Both workflows are explicitly sequenced with arrows and numbered steps, the install flow enforces a hard checkpoint before a risky third-party-code operation ("展示安全警告→提供源码链接→用户确认→npx skills add … -y"), and creation step 4 is an explicit validate→fix→re-run feedback loop ("验证失败就修正后重跑"). This matches anchor 5; the destructive-operation cap does not apply because confirmation and retry loops are present.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into two clearly labeled sections (搜索和安装 / 创建 Skills) with an inline external reference link. Per the rubric's simple-skill guideline, this qualifies for 5 with just well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

83%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 bilingual description that explicitly covers both what the skill does and when to use it, with concrete natural-language trigger phrases. Its only weaknesses are minor: a few missing trigger variations (notably install/add phrasing) and slightly incomplete action coverage.

Suggestions

Add an install-oriented trigger phrase (e.g., "install a skill" / "安装技能") alongside the existing find/search/create triggers.

Consider mentioning additional capabilities such as listing, updating, or removing installed skills if the skill supports them, to round out action coverage.

DimensionReasoningScore

Specificity

"搜索、安装或创建 Agent Skill" lists three concrete actions (search, install, create) in a named domain, matching 'lists several specific actions; minor gaps in coverage'. It falls short of 5 because coverage is not comprehensive (e.g., updating, removing, or listing skills is absent).

4 / 5

Completeness

It explicitly answers 'what' (search, install, or create Agent Skills) and 'when' ("用户说…或想扩展能力时使用") with concrete quoted trigger phrases, matching anchor 5. It is not 4 because the 'when' clause is fully explicit with specific triggers rather than merely adequate.

5 / 5

Trigger Term Quality

The quoted triggers "find a skill", "搜索技能", "帮我做个 skill" and "扩展能力" are natural phrases users would actually say, in both English and Chinese. A few natural terms are missing (e.g., an install- or add-skill trigger phrase), which fits anchor 4 rather than the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

Agent Skill management is a clear niche with distinct, specific triggers, so it is mostly distinguishable with only minor overlap risk against a dedicated skill-creation skill. It is not 3 since the triggers are far more specific than generic examples like "Works with document files".

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

CherryHQ/cherry-studio

Path

resources/builtin-agents/cherry-assistant/.claude/skills/skills-manager/SKILL.md

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.