content-research-writer

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

1.44x

Quality

55%

Does it follow best practices?

Impact

98%

1.44x

Average score across 6 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/content-research-writer/SKILL.md

Quality

Content

56%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 body delivers genuinely actionable writing-partner guidance with clear workflows and worked examples, but at roughly three times the token budget the content justifies. The heavy placeholder templates and redundant restatement sections make it verbose, and nothing is split into reference files despite ample material that warrants it.

Suggestions

Move the outline template, section-feedback template, and full-draft review template into a references/ file (e.g. TEMPLATES.md) and keep only a one-line pointer plus a single worked example in SKILL.md — this alone would cut the body by more than half.

Delete or merge the redundant restatement sections (Writing Workflows, Pro Tips, Best Practices, Related Use Cases largely repeat the Instructions and Examples); keep the file-organization layout and one workflow.

Replace placeholder skeletons ('[Strength 1]', '[Suggested fix]') with one fully worked example per template — Claude fills templates competently and the empty brackets add tokens without adding guidance.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: large placeholder templates ('[Strength 1]', '[Key point A]', '[Suggested fix]') spell out feedback and outline structures Claude already knows how to produce, and the Examples, Writing Workflows, Pro Tips, Best Practices, and Related Use Cases sections substantially restate the same guidance, matching the 'several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	Gives concrete setup commands ('mkdir ~/writing/my-article-title', 'touch article-draft.md'), specific user prompts for each workflow phase, three citation formats, and fully worked examples (the hook rewrites in Example 3 and the section feedback in Example 4). It falls short of 5 because the core instruction templates are skeletons with unfilled placeholders rather than concrete, ready-to-use output.	4 / 5
Workflow Clarity	The 8-step instruction sequence and the four format-specific workflows (blog, newsletter, tutorial, thought leadership) are clearly ordered, and a feedback loop (write section → get feedback → revise) plus a pre-publish checklist are present. Not 5 because source verification ('Verify sources before citing') is a one-line mention rather than an explicit validation checkpoint in the research workflow.	4 / 5
Progressive Disclosure	The file is well-sectioned with headers, but it is a monolithic ~535-line SKILL.md with no bundle files at all — the outline template, research output format, feedback templates, and example gallery clearly belong in separate reference files, matching the 'content that should be separate is inline' anchor.	3 / 5
	Total	13 / 20 Passed

Description

55%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 names concrete, distinctive capabilities but reads as half description and half marketing copy. Its main deficiency is the complete absence of trigger guidance — no 'Use when...' clause telling Claude when to activate it — plus a thin set of natural trigger terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when writing blog posts, articles, newsletters, or tutorials, or when the user asks for research, citations, hook improvement, or feedback on drafts.'

Cut the marketing sentence 'Transforms your writing process from solo effort to collaborative partnership' — it adds no capability information and consumes the token budget.

Broaden natural trigger terms to include synonyms users actually say: 'blog posts', 'articles', 'drafts', 'editing', 'proofreading', not just the abstract 'high-quality content'.

Dimension	Reasoning	Score
Specificity	Lists five concrete actions ('conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section'), but the closing line 'Transforms your writing process from solo effort to collaborative partnership' is vague marketing fluff and 'high-quality content' is generic, keeping it below the comprehensive-and-clean 5 anchor.	4 / 5
Completeness	The 'what' is clearly stated through concrete capability verbs, but there is no 'Use when...' clause or equivalent explicit trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes some natural keywords users would say ('writing', 'research', 'citations', 'hooks', 'outlines', 'feedback') but misses common variations and synonyms like 'blog', 'article', 'newsletter', 'draft', 'edit', or 'proofread', matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche (hook improvement, outline iteration, section-by-section feedback with citations) is somewhat specific, but the framing 'Assists in writing high-quality content' is broad enough to overlap with general writing, editing, and proofreading skills.	3 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (540 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/content-research-writer/SKILL.md
Commit: c9856ea

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.