xhs-content-ops

小红书复合内容运营技能。组合搜索、详情、发布、互动等能力完成运营工作流。当用户要求竞品分析、热点追踪、内容创作、互动管理等复合任务时触发。

Quality

77%

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-content-ops/SKILL.md

Quality

Content

65%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.

The body is highly actionable with concrete executable CLI commands and well-sequenced workflows gated by user confirmation. It loses points for repetitive boundary framing, delegated (non-inline) error recovery, and keeping all per-workflow detail inline with no reference files.

Suggestions

Condense the 技能边界 section: merge the four restated 'only use this script / ignore other projects' bullets into a single concise rule to improve conciseness.

Inline a concrete validate→fix→retry loop for publish/comment batch operations instead of deferring to '参考 xhs-publish/xhs-interact 的失败处理', which would lift workflow_clarity.

Move the four per-workflow detailed step lists into reference files (e.g., references/competitor-analysis.md) and keep SKILL.md as an overview with one-level-deep links to improve progressive_disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with terse code blocks and tables and no concept-explaining padding, but the 技能边界 section restates the 'only use this project's script / ignore other projects' constraint across four repetitive bullets that could be condensed.	2 / 3
Actionability	Every workflow ships copy-paste-ready CLI commands with real flags (e.g., `--keyword`, `--sort-by 最多点赞`, `--feed-id`, `--xsec-token`) plus a subcommand-to-purpose reference table.	3 / 3
Workflow Clarity	Workflows are clearly numbered and sequenced with user-confirmation gates and a failure-handling section, but error recovery is delegated ("参考 xhs-publish/xhs-interact 的失败处理") rather than inline, and batch/destructive operations lack explicit validate→fix→retry loops.	2 / 3
Progressive Disclosure	Content is well-sectioned into headed parts, but with no bundle files everything is inline in a ~180-line file; the per-workflow detail a multi-workflow skill would offload to reference files is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

90%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.

The description is concise and clearly states both what the skill does and when to trigger it, with natural user-facing trigger terms. Specificity could be sharper by naming more granular actions instead of broad capability categories.

Suggestions

Replace broad category words ("搜索、详情、发布、互动") with more concrete actions (e.g., "搜索笔记、抓取笔记详情与评论、图文发布、批量评论/点赞/收藏") to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and several capability areas ("搜索、详情、发布、互动"), but they remain at category level rather than granular concrete actions like 'extract text/fill forms/merge documents'.	2 / 3
Completeness	Explicitly answers both what ("组合搜索、详情、发布、互动等能力完成运营工作流") and when ("当用户要求...复合任务时触发") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Provides natural task phrases users would actually say ("竞品分析、热点追踪、内容创作、互动管理"), giving good coverage of trigger terms for this niche.	3 / 3
Distinctiveness Conflict Risk	Clearly scoped to 小红书 composite operations with distinct triggers; the "复合任务" framing distinguishes it from sibling xhs-publish/xhs-interact skills despite minor overlap risk.	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
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: 13 missing	Warning

	Total	12 / 16 Passed

Repository: autoclaw-cc/xiaohongshu-skills
Path: skills/xhs-content-ops/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.