sn-search-code

用于查找代码示例、开源项目、GitHub Issue、技术问答、开发者讨论、HuggingFace 模型/数据集/Space。

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/sn-search-code/SKILL.md

Quality

Content

77%

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

The body is highly actionable with executable commands and clear fallback handling, and is reasonably concise. Its main weakness is progressive disclosure: the referenced requirements.txt file is missing, leaving one navigation path broken.

Suggestions

Add the missing requirements.txt at the repo root so the documented 'python3 -m pip install -r requirements.txt' command works as written.

Tighten the 凭证配置 and 依赖 prose sections to the essential credential-handling and install rules, reducing explanatory framing Claude already infers.

Optionally move the per-script parameter tables into a short reference block or keep them inline but ensure every referenced file path (including requirements.txt) resolves to an actual bundle file.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with compact tables and executable examples, but the credential-config and dependency prose sections add explanatory framing that could be tightened, matching the 'mostly efficient but could be tightened' anchor.	2 / 3
Actionability	Every script is documented with fully executable commands, complete parameter tables with defaults, and concrete copy-paste examples such as 'python3 scripts/github_search.py "import asyncio" --type code --token ghp_xxx --limit 5'.	3 / 3
Workflow Clarity	For a simple multi-script skill, the install-on-demand instructions include an explicit error-recovery path ('若安装失败…停止使用对应脚本并改用网页搜索，说明缺少依赖'), and no destructive or batch operations require additional validation loops.	3 / 3
Progressive Disclosure	Sections are well-organized and the four referenced scripts exist in scripts/, but requirements.txt is invoked ('pip install -r requirements.txt') yet is not present in the repo, breaking a referenced path.	2 / 3
	Total	10 / 12 Passed

Description

50%

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

The description clearly communicates the skill's search targets across developer platforms but is hampered by the absence of an explicit 'when to use' trigger clause and a single repeated action verb. Adding a 'Use when...' clause and more natural trigger variations would raise specificity and completeness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to find open-source projects, code examples, GitHub issues, technical Q&A, or HuggingFace models/datasets/Spaces.'

Vary the action verbs beyond the single '查找' to describe distinct capabilities (e.g. 'search, look up, discover') and include platform name variations like Stack Overflow and Hacker News.

Consider an English trigger-equivalent phrasing so the description matches how users phrase the request across languages.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete targets ("代码示例", "开源项目", "GitHub Issue", "技术问答", "HuggingFace 模型/数据集/Space") but uses a single action verb ("查找") rather than multiple distinct actions, matching the 'names domain and some actions but not comprehensive' anchor.	2 / 3
Completeness	It clearly states what the skill does but lacks an explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	Natural platform terms like "GitHub Issue" and "HuggingFace 模型/数据集/Space" are present, but common variations such as Stack Overflow, Hacker News, and English equivalents are missing.	2 / 3
Distinctiveness Conflict Risk	Named platforms (GitHub, HuggingFace) give it a distinct niche, but broad terms like "技术问答" and "开发者讨论" and the absence of explicit usage triggers leave overlap with general search skills.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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: OpenSenseNova/SenseNova-Skills
Path: skills/sn-search-code/SKILL.md
Commit: 179fea1

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.