last30days-cn

Chinese-platform last-30-days research skill covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao. Includes Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output.

Quality

85%

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

Quality

Content

87%Weight 40%Scale 1-3

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

A well-structured, actionable instruction skill: lean body with executable commands and correct externalization of implementation into the scripts bundle. The main gap is soft validation guidance in the synthesis/research workflow, which lacks explicit error-recovery feedback loops.

Suggestions

Add an explicit validate->fix->retry checkpoint for failed or sparse sources, e.g. 'If a source returns no evidence, retry once with a broader query or a fallback source before declaring coverage sparse.'

Consolidate the env-var listing to one location (frontmatter optionalEnv or the Configuration INI block) to remove the duplicated list and tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean and instruction-dense with no concept padding (no 'what is Weibo' explanations); sections like Output Modes and 查询类型路由提示 are compact bullets, and every token largely earns its place, matching the lean-and-efficient anchor. The only minor redundancy is the env-var INI block duplicating frontmatter optionalEnv, which is slight and not conceptual padding.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands ("python {{SKILL_DIR}}/scripts/last30days.py ... --emit compact") plus nine concrete flag variants, --diagnose, setup, playwright install, and env exports — specific and complete rather than vague or pseudocode.	3 / 3
Workflow Clarity	A clear sequence exists (Run -> preserve badge/cite inline -> numbered Synthesis Guidance 1-6 -> Compliance), but validation checkpoints are soft/implicit ("if coverage is sparse, say so", "mention unavailable or failed sources") with no explicit validate->fix->retry feedback loop, matching the steps-listed-but-checkpoints-implicit anchor rather than the explicit-validation score-3 anchor.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview that delegates the heavy implementation to a one-level-deep script bundle (scripts/last30days.py with 27 lib modules) and assets/banner.png, all real files; the script is treated as a black-box entry point, which is appropriate progressive disclosure with clearly signaled {{SKILL_DIR}}/scripts paths.	3 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 specific, distinctive description naming eight Chinese platforms and concrete output formats, but it omits an explicit 'Use when...' trigger clause, which caps completeness at 2. Otherwise strong on specificity, trigger terms, and distinctiveness.

Suggestions

Add an explicit when-to-use clause, e.g. 'Use when the user asks for recent (last 30 days) Chinese internet discussion, trend research, or public-source evidence across Weibo/Xiaohongshu/Bilibili/Zhihu/Douyin/WeChat/Baidu/Toutiao.'

Include natural trigger phrasings users would say such as '舆情', '趋势', or 'recent Chinese platform trends' to round out trigger-term coverage beyond platform names.

Dimension	Reasoning	Score
Specificity	Names the domain concretely ("covering Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, and Toutiao") and lists multiple specific concrete outputs ("Markdown, JSON, compact context, and Guizang-inspired Swiss/IKB HTML report output"), matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	It clearly answers what (research across 8 platforms with several output formats) but has no "Use when..." clause or equivalent explicit when-to-use trigger, so per the judging guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	"last-30-days research" plus eight named platforms (Weibo, Xiaohongshu, Bilibili, Zhihu, Douyin, WeChat, Baidu, Toutiao) are natural terms users would say when requesting recent Chinese-platform coverage; good coverage with common platform variations.	3 / 3
Distinctiveness Conflict Risk	The combination of eight specific Chinese platforms with a 30-day research window is a clear niche with distinct triggers, unlikely to conflict with generic research or document skills; uses third-person voice so no specificity penalty applies.	3 / 3
	Total	11 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: Jesseovo/last30days-skill-cn
Path: SKILL.md
Commit: 1a8a04c

Reviewed: 12 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.