self-media-pre-publish-analyzer

Pre-publish diagnosis skill for self-media works. Use when the user asks for 发布前诊断, 发布前分析, content scoring, pre-publish review, or optimization diagnosis for Xiaohongshu/Rednote image-card posts or WeChat Official Account articles. Reads the mentioned post folder, searches comparable content online, scores the work, and outputs prioritized revision instructions.

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

81%Weight 40%Scale 1-5

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

A well-structured diagnostic skill body with excellent workflow sequencing, explicit checkpoints, and a fixed output template. Its weaknesses are moderate rule duplication across sections and a dangling reference to a nonexistent test-prompts.json file.

Suggestions

Add the missing test-prompts.json file (Xiaohongshu and WeChat covering IP增长, 产品转化, and 爆文流量 plus the edge cases described) or remove the Test Prompts section, since the body currently points to a file that does not exist.

Deduplicate rules stated in multiple sections — e.g., keep the third-party-source rule (Canva/KAWO/Yiban) and the base-weight rule in a single authoritative section (Scoring Rules or Do Not) instead of repeating them across Workflow, Quality Bar, and Do Not.

Move a few natural trigger phrasings ('能不能发', '帮我诊断这篇') from the body's Trigger section into the frontmatter description to strengthen trigger coverage without adding body length.

Dimension	Reasoning	Score
Conciseness	Efficient and instruction-only with no concept padding, but a few rules are duplicated across sections (the third-party-source rule appears in Workflow, Quality Bar, and Do Not; base-weight rules appear twice), which could be trimmed. Not score 5 due to this repetition; well above score 3's unnecessary explanation.	4 / 5
Actionability	Concrete file paths, exact commands ('python3 scripts/validate_skill_contract.py'), fixed score bands, and a copy-paste output template make the guidance mostly executable, but 'Use test-prompts.json in this skill directory' references a file that does not exist in the bundle.	4 / 5
Workflow Clarity	An 8-step sequenced workflow with explicit CHECKPOINT/STOP gates, a failure-mode and fallback table, an evidence-ledger step, and confidence-level rules — clear validation checkpoints throughout, matching the top anchor.	5 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references (rednote-rubrics.md, wechat-official-rubrics.md, comparison-protocol.md — all verified present) and an overview body, but the body points to test-prompts.json which is missing from the skill directory.	4 / 5
	Total	17 / 20 Passed

Description

88%Weight 40%Scale 1-5

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 strong description with explicit what/when structure, concrete actions, and bilingual trigger terms scoped to specific platforms. Its only weakness is missing a few natural trigger phrasings that users would plausibly say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads the mentioned post folder, searches comparable content online, scores the work, and outputs prioritized revision instructions' — covering the full diagnosis pipeline comprehensively, matching the score-5 anchor's breadth.	5 / 5
Completeness	Explicitly answers both what ('Reads... searches... scores... outputs prioritized revision instructions') and when ('Use when the user asks for 发布前诊断...'), matching the anchor for both concrete what and when with explicit trigger phrases.	5 / 5
Trigger Term Quality	Includes natural bilingual triggers ('发布前诊断, 发布前分析, content scoring, pre-publish review, or optimization diagnosis') plus platform names, but misses common natural variants like '能不能发' or '帮我打个分' that appear only in the body.	4 / 5
Distinctiveness Conflict Risk	Clear niche (pre-publish diagnosis for Xiaohongshu/Rednote image-card posts and WeChat articles) distinct from creation skills, but the generic term 'content scoring' creates minor overlap risk with other evaluation skills; not score 5, clearly above score 3's broader overlap.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: dtyq/magic
Path: backend/super-magic/agents/skills/self-media-pre-publish-analyzer/SKILL.md
Commit: f9973c5

Reviewed: 2 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.