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

—

Does it follow best practices?

Impact

98%

1.44x

Average score across 6 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

27%

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

The skill is well-structured and sequenced but heavily over-long, dominated by placeholder templates and generic best-practice advice rather than concrete, executable guidance. It is a monolithic file with no progressive disclosure of the large template/example material into separate references.

Suggestions

Move the large feedback, hook, and final-review templates into separate reference files (e.g., references/feedback-template.md) and keep SKILL.md a concise overview with one-level-deep links.

Replace generic advice ('Verify sources before citing', 'Take breaks', 'Set deadlines') with concrete, Claude-specific guidance or remove it, since Claude already knows these basics.

Fill or remove the pervasive [bracket] placeholder scaffolding so the remaining instructions are executable rather than skeleton outlines.

Dimension	Reasoning	Score
Conciseness	The ~370-line body is padded with bracket-placeholder template scaffolding ('[Strength 1]', '[Specific issue] → [Suggested fix]', '[Opening line/story/statistic]') and generic advice Claude already knows ('Verify sources before citing', 'Take breaks', 'Set deadlines'), so most tokens do not earn their place.	1 / 3
Actionability	Concrete example prompts and a sequenced workflow are present, but the core instructions are largely placeholder templates with [brackets] rather than executable, copy-paste-ready guidance, leaving key details unspecified.	2 / 3
Workflow Clarity	The eight-step writing workflow is clearly sequenced (understand → outline → research → hooks → feedback → voice → citations → final review), but validation checkpoints are only implicit and feedback loops are described loosely rather than as explicit verify→fix→retry gates.	2 / 3
Progressive Disclosure	Everything lives in a single monolithic ~370-line SKILL.md with no bundle files and no external references; templates, examples, and workflow variants that should be split into separate reference files are inlined, making navigation heavy.	1 / 3
	Total	6 / 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 states concrete capabilities clearly but omits any 'Use when...' trigger clause, so it answers 'what' but not 'when'. Trigger terms are present but lack common variations. Distinctiveness is moderate due to the broad writing framing.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when writing blog posts, articles, newsletters, or tutorials that need research and citations').

Include common trigger variations users actually say ('blog posts', 'articles', 'newsletters', 'case studies') rather than only the abstract capability list.

Drop the marketing-style closing sentence ('Transforms your writing process from solo effort to collaborative partnership') since it adds no trigger or capability information.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section'), matching the multi-action anchor; the trailing 'Transforms your writing process...' is mild fluff but does not erase the concrete action list.	3 / 3
Completeness	It clearly answers 'what does this do' but has no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is missing; per the rubric a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some relevant natural terms ('writing', 'content', 'research', 'citations', 'hooks') but misses common user variations like 'blog posts', 'articles', or 'outlines', and 'real-time feedback on each section' is not phrased as a user utterance.	2 / 3
Distinctiveness Conflict Risk	The collaborative research+citation+feedback writing-partner niche is somewhat distinct, but broad 'writing high-quality content' phrasing could overlap with generic writing or editing skills.	2 / 3
	Total	9 / 12 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
Commit: 3c94e0c

Reviewed: about 11 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.