xhs-explore

小红书内容发现与分析技能。搜索笔记、浏览首页、查看详情、获取用户资料。当用户要求搜索小红书、查看笔记详情、浏览首页、查看用户主页时触发。

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/xhs-explore/SKILL.md

Quality

Content

92%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 highly actionable, concise skill body with excellent executable examples and a well-sequenced, risk-aware batch workflow. Its only gap is progressive disclosure: everything lives in one monolithic file with no bundled reference files to offload detail.

Suggestions

Move the detailed parameter tables and NetLog/risk-report material into a bundled reference file (e.g. references/cli-reference.md) and link to it from SKILL.md to achieve one-level-deep progressive disclosure.

Consider extracting the batch anti-风控 recipe into a reference so the main body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Lean and token-efficient: commands, parameter tables, and field descriptions with no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	Every workflow ships copy-paste-ready `python scripts/cli.py …` commands with concrete flags, values, and a real batching/rate-limit recipe.	3 / 3
Workflow Clarity	Multi-step batch detail retrieval is explicitly sequenced with a validation/risk checkpoint (3-feed groups + randomized sleep) and an input-judgment priority list; failure handling is enumerated.	3 / 3
Progressive Disclosure	Well-organized single-file structure, but there are no references, scripts, or assets bundled, so content that could be split out (full parameter tables, NetLog/risk-report detail) stays inline; no one-level-deep references exist to signal navigation.	2 / 3
	Total	11 / 12 Passed

Description

65%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, well-scoped description that names concrete actions and includes explicit trigger conditions for the Xiaohongshu use case. It is strong overall; the main improvement is aligning trigger phrasing closer to natural user language.

Suggestions

Add a clear 'Use when…' clause with natural variations users would say (e.g. '小红书、小红书笔记、小红书首页、看博主主页'), not just the four subcommand-style triggers.

Keep third-person voice but broaden trigger terms beyond literal subcommand names to reduce stiffness.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '搜索笔记、浏览首页、查看详情、获取用户资料' — each tied to a specific CLI capability.	3 / 3
Completeness	It clearly states what the skill does, and the '当用户要求…时触发' clause provides explicit when-guidance, but it reads as one combined sentence rather than a clean 'Use when…' clause, keeping it just short of the strongest anchor.	2 / 3
Trigger Term Quality	Triggers like '搜索小红书、查看笔记详情、浏览首页、查看用户主页' are natural, but phrasing mirrors technical subcommands rather than the full range of natural variations a user would say.	2 / 3
Distinctiveness Conflict Risk	Scoped tightly to Xiaohongshu content discovery with distinct trigger conditions, making overlap with unrelated skills unlikely.	3 / 3
	Total	10 / 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
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
referenced_paths_exist	Referenced path issues: 20 missing	Warning

	Total	12 / 16 Passed

Repository: autoclaw-cc/xiaohongshu-skills
Path: skills/xhs-explore/SKILL.md
Commit: b043748

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.