intelligent-content-system

智能内容创作与发布全流程系统。根据用户需求自动识别场景，编排调用网页采集、智能配图、小红书图文生成、热点内容创作、多平台发布等技能，实现从内容获取到发布的一站式自动化。支持场景： - 网页内容采集与再创作（采集→配图→发布） - 热点内容创作（热点采集→AI生成→多平台发布） - 原创内容优化（配图→小红书图文→发布） - 单一功能调用（采集/配图/图文/发布）支持平台：微信公众号、小红书、X/Twitter、B站

Quality

51%

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/intelligent-content-system/SKILL.md

Quality

Content

42%

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

The skill has clear structure and concrete scenario coverage, but the body is verbose with redundant examples and relies on references that are mostly broken. Workflow sequencing lacks validation checkpoints for batch and publishing operations.

Suggestions

Fix or remove the dead reference links (workflow-templates.md, skill-integration.md, platform-config.md, troubleshooting.md) and the missing examples/ directory, or fold that essential content inline.

Add explicit validation/confirmation checkpoints before destructive or batch actions — e.g., confirm platform accounts and content compliance before publishing, and verify each item before batch processing.

Collapse the four 使用示例 and the per-scenario 执行流程/输出 duplication into one canonical worked example plus a compact scenario table to cut the body substantially.

Dimension	Reasoning	Score
Conciseness	The core sections are mostly efficient, but the ~580-line body is padded: the four 使用示例 repeat the step-by-step progress output already shown in §3 and §操作步骤, and the 14 scenario entries repeat near-identical 执行流程/输出 blocks.	2 / 3
Actionability	It names concrete sub-skills, scenario codes, and parameter lists, but execution flows are prose ('使用 baoyu-url-to-markdown 采集') rather than executable commands, and some named skills (baoyu-format-markdown, wechat-publisher) differ from the frontmatter dependencies.	2 / 3
Workflow Clarity	Steps are sequenced with branch and failure handling, but batch processing and multi-platform publishing (destructive/outward-facing) have no validation or confirmation checkpoints before publish, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body references 9 paths but only 2 exist (scenario-detection.md, quick-reference.md); workflow-templates.md, skill-integration.md, platform-config.md, troubleshooting.md and the entire examples/ directory are broken links, leaving a monolithic body with dead references.	1 / 3
	Total	7 / 12 Passed

Description

60%

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 specific about capabilities and platforms but lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' only implied. As a broad orchestrator combining five sub-skills, its triggers risk overlapping with those sub-skills.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasing (e.g., 'Use when the user wants to collect web content, add illustrations, generate Xiaohongshu posts, create hotspot articles, or publish to multiple platforms').

Sharpen trigger terms to distinguish orchestration requests from single-skill calls (e.g., '采集并发布', '采集并转小红书') so it does not fire for a plain '采集' or '配图' request that a single sub-skill should handle.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('网页采集、智能配图、小红书图文生成、热点内容创作、多平台发布'), matching the highest anchor for listing several specific concrete actions.	3 / 3
Completeness	The 'what' is clearly stated, but 'when' is only implied via the scenario list rather than an explicit trigger clause, which caps completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Relevant domain terms appear ('采集', '配图', '小红书', '热点', '发布') but there is no 'Use when...' trigger clause and common natural variations are missing, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	It has a clear orchestrator niche, but its trigger terms (采集, 配图, 发布) overlap with each constituent sub-skill, so it could still trigger for the wrong skill.	2 / 3
	Total	9 / 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
skill_md_line_count	SKILL.md is long (580 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 8 missing, 5 suspicious	Warning
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	12 / 16 Passed

Repository: anbeime/skill
Path: skills/intelligent-content-system/SKILL.md
Commit: f595e96

Reviewed: about 12 hours 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.