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.

Quality

52%

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

Fix and improve this skill with Tessl

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

Quality

Content

46%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 skill is well-structured and covers a complete collaborative-writing workflow, but it is significantly verbose for an instruction-only skill, leaning heavily on inlined placeholder templates Claude can produce on demand. Tightening the body and moving large templates to reference files would materially improve conciseness and progressive disclosure.

Suggestions

Move the large reusable templates (outline, section feedback, full-draft review, research) into separate reference files and link to them from a lean SKILL.md overview.

Add explicit validation checkpoints for citation-bearing work, e.g. 'Verify each source resolves and supports the cited claim before adding it'.

Replace placeholder scaffolding like '[Specific issue] -> [Suggested fix]' with a short, concrete worked example so the guidance is actionable rather than fill-in-the-blank.

Dimension	Reasoning	Score
Conciseness	The ~530-line body extensively inlines template scaffolding Claude could generate itself (outline, feedback, research, and full-draft-review templates) and restates obvious guidance, making it noticeably verbose for what is an instruction-only workflow.	2 / 5
Actionability	It provides concrete template structures and example prompts, but much guidance is placeholder pseudocode like '[Specific issue] -> [Suggested fix]' rather than executable, specific instruction; missing concrete verification of citations/sources.	3 / 5
Workflow Clarity	A clear eight-step Instructions sequence and several workflow variants exist, but there are no validation checkpoints (e.g. verify sources before citing) and feedback loops are only implicit, which caps this skill at 3 given batch/research operations.	3 / 5
Progressive Disclosure	Content is well organized into clearly headed sections (When to Use, Instructions, Examples, Workflows, Pro Tips) with no bundle files present; the main gap is that large template blocks that could live in separate reference files are inlined.	4 / 5
	Total	12 / 20 Passed

Description

58%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 a clear, multi-capability niche around research-backed writing and feedback, but it omits an explicit 'Use when...' trigger clause and relies on third-person verbs without strong natural trigger phrases. Adding concrete when-to-use triggers would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when writing blog posts, articles, or newsletters that need citations, hooks, or section feedback'.

Include natural user phrasings and synonyms ('edit my draft', 'cite sources', 'improve my introduction') to improve trigger-term coverage.

Tighten abstract verbs like 'providing real-time feedback' into concrete actions such as 'reviews each section for clarity, flow, and evidence'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (research, citations, hooks, outlines, section feedback) rather than a single generic verb, though 'improving hooks' and 'real-time feedback' are somewhat abstract compared to the most concrete anchor.	4 / 5
Completeness	It clearly states what the skill does, but the 'when' is only weakly implied via the capability list; there is no explicit 'Use when...' clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('citations', 'hooks', 'outlines', 'feedback') but lacks common synonyms a user might say like 'edit my draft', 'cite sources', 'fix my intro', or explicit file/format triggers.	3 / 5
Distinctiveness Conflict Risk	The citation/research/section-feedback niche is fairly distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against generic writing assistants.	4 / 5
	Total	14 / 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: MoizIbnYousaf/ai-agent-skills
Path: skills/content-research-writer/SKILL.md
Commit: 1159592

Reviewed: 18 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.