CtrlK
BlogDocsLog inGet started
Tessl Logo

xhs-content-ops

小红书图文内容调研与对标分析。搜索小红书图文笔记,下载图片和正文进行深度分析。当用户要求小红书竞品分析、对标分析、图文内容调研时触发。视频内容请使用 viral-chaser 技能。

71

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

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 and well-sequenced with strong failure-handling feedback loops, but it loses token efficiency through repeated mechanism explanations across the three scenarios, and its bundle references are not explicitly signaled as navigable links.

Suggestions

Factor the "无 cookie SSR HTML 路线 / cookie 仅回退 / exit 2 → login-manager" rationale into a single '下载路线' section and reference it from scenarios A/B/C instead of repeating it verbatim three times.

Add a one-level-deep signaled reference to the script (e.g. a 'See scripts/fetch_note_content.ts' link and/or move the full parameter/exit-code table to a reference file) to improve progressive disclosure.

Consider moving the detailed --url/--note-id/--xsec-token parameter table and JSON output schema out of the main body into a scripts/README or reference doc, keeping the main SKILL.md a concise overview.

DimensionReasoningScore

Conciseness

The body is largely lean and operational (tables, commands, exit codes), but the "无 cookie SSR HTML 路线…cookie 仅回退…exit 2 交 login-manager" rationale and the login-manager fallback instructions repeat verbatim ~3× across scenarios A/B/C, which could be factored once. It is efficient, not padded with concepts Claude already knows, so it stays above 1.

2 / 3

Actionability

It provides copy-paste-ready commands (e.g. `camoufox-cli --session xhs-browse --persistent --json open "..."`, `xhs-content-ops --url <url> --output-dir ...`), concrete exit codes (0/1/2), an exact JSON output schema, and a parameter table — fully executable guidance.

3 / 3

Workflow Clarity

Three scenarios are clearly numbered and sequenced, with explicit validation/feedback loops for risky batch operations (exit 2 → login-manager re-login → retry once; NO_XSEC_TOKEN/NEED_VERIFY handling) and a structured failure-handling table, satisfying the batch-operation feedback-loop requirement.

3 / 3

Progressive Disclosure

Bundle files exist (scripts/fetch_note_content.sh, .ts) and are invoked via the real PATH wrapper `xhs-content-ops`, and sections are well organized, but references are not signaled as navigable links and substantial parameter/API detail sits inline in the body rather than split into a one-level-deep signaled reference. Not 3 because there is no clear 'See X' one-level-deep pointer; not 1 because structure is present and references are real.

2 / 3

Total

10

/

12

Passed

Description

100%

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 yet complete: it states concrete capabilities, gives explicit natural-language triggers, and draws a clear boundary against sibling skills. Voice is third-person throughout, incurring no penalty.

DimensionReasoningScore

Specificity

Names multiple concrete actions — "搜索小红书图文笔记", "下载图片和正文", "进行深度分析", "对标分析" — matching the anchor for listing several specific actions rather than a vague domain claim.

3 / 3

Completeness

It explicitly answers both "what" (search/download/analyze/benchmark image-text notes) and "when" (explicit trigger clause), so it is not capped at 2 for a missing trigger.

3 / 3

Trigger Term Quality

The clause "当用户要求小红书竞品分析、对标分析、图文内容调研时触发" supplies natural user phrasings users would actually say, giving good coverage of trigger terms.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (Xiaohongshu image-text notes) and adds explicit conflict avoidance ("视频内容请使用 viral-chaser 技能"), making mis-triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
Reviewed

Table of Contents

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.