content-writer

Use when the user asks to "write SEO content", "draft a blog post / landing page", "update outdated content", or "fix traffic/ranking decay"; two modes — new drafts pages with keywords, headers, snippets, and evidence boundaries; refresh scores decay, prioritizes update work, and produces a republish plan with GEO guidance. Not for AI-citation/GEO readiness scoring — use geo-content-optimizer; not for publish-gate scoring — use content-quality-auditor. SEO文章写作/内容更新/排名恢复

Quality

92%

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

85%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 thorough, well-structured two-mode skill body: concrete commands and thresholds, clearly sequenced workflows with decision-gate checkpoints, and clean one-level-deep reference disclosure. The only weak spot is conciseness — the two-mode framing is restated several times across early sections.

Suggestions

Collapse the opening paragraph to a single sentence and let the Mode Selector table carry the per-mode trigger/output detail, since the intro largely duplicates that table.

Replace the Skill Contract's 'Expected output' line with a cross-reference to the Mode Selector table's Output column rather than restating what each mode produces.

In Quick Start, point back to the Mode Selector for trigger conditions instead of re-explaining the new-vs-refresh distinction inline.

Dimension	Reasoning	Score
Conciseness	Accurate and free of basic-concept padding, but the two-mode framing is restated across the intro paragraph, the Mode Selector table, Quick Start, and the Skill Contract's Expected-output line — mostly efficient but could be tightened rather than hitting the 'every token earns its place' bar.	2 / 3
Actionability	Highly actionable for an instruction skill: exact commands ('python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/indexpush.py" indexnow <url> --key $INDEXNOW_KEY --live'), specific numeric thresholds (30% traffic drop, 40-60 word FAQ answers, 50%+ new content republish rule), and concrete per-step guidance in both 9-step workflows.	3 / 3
Workflow Clarity	Both modes are laid out as explicit 9-step numbered sequences with validation checkpoints — the Decision Gates (stop-and-ask vs continue-silently), per-mode quality bars, 'Done when' criteria, and the step-9 self-check form a clear feedback loop for error recovery.	3 / 3
Progressive Disclosure	SKILL.md is a well-organized overview with a dedicated Reference Materials section giving a one-line description per file; all 7 bundle references in ./references/ exist and are referenced one level deep (e.g. references/instructions-detail.md §2, references/content-decay-signals.md), matching the clear-overview + well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

100%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 strong description: concrete actions, natural trigger phrasings, explicit what/when guidance, and explicit disambiguation from two sibling skills. No first/second-person voice issues — the 'Use when...' imperative matches the rubric's own good examples.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both modes — 'new drafts pages with keywords, headers, snippets, and evidence boundaries; refresh scores decay, prioritizes update work, and produces a republish plan with GEO guidance' — matching the score-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both: when (the 'Use when the user asks to...' clause with four triggers) and what (the two-mode output description), matching the score-3 anchor of clear what AND when with explicit triggers.	3 / 3
Trigger Term Quality	Quotes natural user phrasings — "write SEO content", "draft a blog post / landing page", "update outdated content", "fix traffic/ranking decay" — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Carves out a clear niche and actively disambiguates — 'Not for AI-citation/GEO readiness scoring — use geo-content-optimizer; not for publish-gate scoring — use content-quality-auditor' — making a wrong-skill trigger unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
relative_links	Relative link issues: 15 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/implement/content-writer/SKILL.md
Commit: 4a77c48

Reviewed: 9 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.