sn-search-social-media

搜索社区、社媒、新闻热点、百科趋势、开发者生态和技术讨论时使用。

Quality

76%

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-social-media/SKILL.md

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.

The skill body is an operational, copy-paste-ready reference: a resource-selection table, concrete CLI examples, scenario strategies, and a standard JSON contract, all backed by real scripts. Its main gaps are recurring repetition of the crypto/fallback rules and the absence of any layered documentation files for progressive disclosure.

Suggestions

Consolidate the cryptocurrency prohibition into one authoritative section and cross-reference it instead of restating it across 硬性规则, 使用策略, and 输出约定.

Add a short numbered end-to-end workflow (select source → run script or browser-use → validate success=false/crypto → report with evidence URLs) to make the sequence and checkpoints explicit.

Verify the referenced requirements.txt exists at the skill root, since 依赖 instructs `pip install -r requirements.txt` but no such file is present in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with no padding about what social media or search APIs are, but the crypto prohibition and fallback guidance recur across 硬性规则, 使用策略, and 输出约定, leaving minor trimmable repetition.	4 / 5
Actionability	The 常用命令 section gives copy-paste-ready bash commands with concrete arguments covering each script's common cases, the 资源选择 table maps scenarios to specific real script paths and URLs, and the standard JSON output shape is specified.	5 / 5
Workflow Clarity	使用策略 sequences per-scenario workflows with explicit validation/error paths (crypto stop, dependency-fail fallback to browser-use, multi-source conflict reporting), but guidance is organized by scenario rather than as a numbered sequence with formal validate→fix→retry checkpoints.	4 / 5
Progressive Disclosure	The body is a well-organized overview with clearly signaled one-level-deep script references (all referenced scripts exist under scripts/), but content is not split into separate doc files — everything lives inline in SKILL.md, so there is no deeper layered material to navigate to.	4 / 5
	Total	17 / 20 Passed

Description

70%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.

The description is a concise third-person trigger clause that names six concrete domains and gives an explicit 'use when' condition, but it relies on a single generic action verb and never spells out concrete capabilities like fetching pageviews or listing trending topics.

Suggestions

Add 1-2 concrete actions to the description, e.g. '抓取百科页面浏览量、热搜榜单、开源项目与开发者讨论热度' alongside '搜索'.

Keep the explicit '搜索…时使用' trigger but pair it with concrete capability phrases so the 'what' is as explicit as the 'when'.

Consider adding one or two common synonyms (e.g. 舆情、热榜) to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The single action verb "搜索" is generic, but the description enumerates six concrete domains (社区、社媒、新闻热点、百科趋势、开发者生态、技术讨论), naming the domain space clearly with one action rather than being entirely vague.	3 / 5
Completeness	It has an explicit 'when' clause ("搜索…时使用") and an implied 'what' (search those domains), so both are present; the 'what' lacks concrete action phrases beyond '搜索', keeping it below a 5.	4 / 5
Trigger Term Quality	Six natural Chinese trigger terms covering distinct domains (社区、社媒、新闻热点、百科趋势、开发者生态、技术讨论) give good keyword coverage a user would actually say, though common synonyms and variations are not exhaustively listed.	4 / 5
Distinctiveness Conflict Risk	The niche (free, no-key social/community/news/encyclopedia trend search) is fairly specific and distinguishable, with only minor overlap risk against general web-search skills.	4 / 5
	Total	15 / 20 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-social-media/SKILL.md
Commit: 61b60bb

Reviewed: 8 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.