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Use when the user asks to "write SEO content", "draft a blog post / landing page", "update outdated content", or "fix traffic/ranking decay"; two modes — new drafts pages with keywords, headers, snippets, and evidence boundaries; refresh scores decay,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 1-5

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

The content is a well-structured, actionable overview for a complex two-mode skill: explicit step sequences with validation checkpoints and feedback loops, concrete commands and thresholds, and clean one-level-deep references to a verified bundle. The only slack is mild verbosity and some procedural steps whose detail lives in reference files.

Suggestions

Tighten the Skill Contract / Data Sources prose where it restates mode behavior already covered in the Instructions section to lift conciseness toward 5.

Inline one complete worked mini-example (e.g., a short new-mode draft skeleton or a refresh decay-score calculation) so the common cases are fully copy-paste-ready rather than deferred to reference files.

Collapse the two nine-step lists into a shared prefix where steps overlap, reducing token weight without losing the validation checkpoints.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful — concrete steps, thresholds, and commands rather than basics Claude already knows — but the two-mode × nine-step structure plus contract/data-source sections leave minor instances that could be trimmed, so it sits above the 3 anchor's "could be tightened".	4 / 5
Actionability	Provides copy-paste-ready commands (indexpush.py with exact flags) and specific numeric thresholds (30% traffic drop, 40–60 word FAQs, republish-date percentages), but much of the guidance is procedural with details deferred to reference files, fitting "mostly executable guidance; minor gaps" rather than fully copy-paste-ready.	4 / 5
Workflow Clarity	Each mode has nine numbered steps with explicit quality bars, dependency_status checkpoints (verified/blocked/approved-fallback), decision gates, and an auditor feedback loop (SHIP → stop; FIX → return; BLOCK → stop), matching the explicit-validation-and-feedback-loops anchor.	5 / 5
Progressive Disclosure	The body is an overview with well-signaled one-level-deep references — all seven referenced files under references/ exist (instructions-detail.md, seo-writing-checklist.md, title-formulas.md, content-structure-templates.md, content-decay-signals.md, refresh-templates.md, refresh-example.md) — and bulk detail is appropriately split out, matching the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is strong across all dimensions: it states concrete actions for two modes, opens with natural trigger phrases, explicitly covers what and when, and draws clear boundaries against neighboring skills. It uses third person throughout with no over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both modes — "drafts pages with keywords, headers, snippets, and evidence boundaries" and "scores decay, prioritizes update work, and produces a republish plan with GEO guidance" — giving comprehensive coverage rather than the minor-gaps level of 4.	5 / 5
Completeness	Explicitly answers both what (two modes with their concrete outputs) and when ("Use when the user asks to…" with multiple concrete triggers), plus negative boundaries, fitting the explicit-both-what-and-when anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("write SEO content", "draft a blog post / landing page", "update outdated content", "fix traffic/ranking decay") with synonym variation, matching the comprehensive-coverage anchor better than the 4 anchor's "a few natural terms missing".	5 / 5
Distinctiveness Conflict Risk	Explicit "Not for… use geo-content-optimizer" and "not for publish-gate scoring — use content-quality-auditor" carve out a clear niche with minimal conflict risk, matching the clear-niche anchor.	5 / 5
	Total	20 / 20 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: 16 suspicious	Warning

	Total	13 / 16 Passed

Repository: aaron-he-zhu/aaron-marketing-skills
Path: seo-geo/implement/content-writer/SKILL.md
Commit: 888dd38

Reviewed: 6 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.