CtrlK
BlogDocsLog inGet started
Tessl Logo

skills-manager

搜索、安装和创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill,或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"的场景。

80

Quality

100%

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

100%

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

A compact, instruction-only skill body that is lean, actionable with real commands and paths, and clearly sequenced with safety and iteration checkpoints. It assumes Claude's competence and avoids filler.

DimensionReasoningScore

Conciseness

The body is keyword-dense with no padding and no explanation of concepts Claude already knows; every line is operational, matching the lean-and-efficient anchor.

3 / 3

Actionability

Provides executable commands (npx skills find, npx skills add ... -y), concrete paths (.claude/skills/, ~/.claude/skills/), and a concrete directory structure, yielding copy-paste-ready guidance despite being instruction-only.

3 / 3

Workflow Clarity

Multi-step flows are sequenced with explicit checkpoints — the install flow gates on 用户确认 before adding third-party code, and the creation flow includes an iterative test-and-revise loop.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the body is under 50 lines and cleanly organized into 搜索和安装 / 创建 Skills with clear sub-structure, satisfying the simple-skill allowance.

3 / 3

Total

12

/

12

Passed

Description

100%

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 tight, bilingual description that names concrete capabilities, supplies multiple natural trigger phrases, and explicitly covers both what and when. It uses third-person/action voice and avoids fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "搜索、安装和创建" (search, install, create) — on a clearly defined domain, matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Explicitly answers what (搜索、安装和创建 Agent Skills) and when ("当用户想要…时触发" plus scenario list), satisfying both halves with explicit trigger guidance.

3 / 3

Trigger Term Quality

Covers natural phrasings a user would actually say across both languages ("find a skill", "搜索技能", "帮我做个 skill", "create a skill", "有没有做 X 的工具"), giving good trigger coverage.

3 / 3

Distinctiveness Conflict Risk

The niche — managing Claude Code Agent Skills — is distinct and its triggers are specific to skill search/install/create, making conflict with unrelated skills unlikely.

3 / 3

Total

12

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
CherryHQ/cherry-studio
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.