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.
68
26%
Does it follow best practices?
Impact
98%
1.44xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/content-research-writer/SKILL.mdQuality
Discovery
25%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 lists several writing-related actions but remains too broad and generic to serve as an effective skill selector among many skills. It lacks a 'Use when...' clause, uses second person ('your writing process'), and the final sentence is marketing fluff that adds no discriminative value. The skill would benefit from narrowing its scope and adding explicit trigger conditions.
Suggestions
Add an explicit 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user asks for help drafting articles, blog posts, essays, or long-form content with citations.'
Narrow the scope to a specific content type or domain (e.g., 'academic writing', 'blog posts', 'marketing copy') to reduce conflict risk with other writing-related skills.
Remove the second-person fluff sentence ('Transforms your writing process...') and replace with concrete, third-person capability statements and natural trigger terms like 'draft', 'article', 'blog post', 'essay', 'proofread'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists several actions (conducting research, adding citations, improving hooks, iterating on outlines, providing feedback), but they are somewhat generic writing-related activities rather than highly concrete, tool-specific operations. The second sentence is pure marketing fluff. | 2 / 3 |
Completeness | Describes what it does (research, citations, hooks, outlines, feedback) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when...' caps completeness at 2, and the 'when' is not even implied clearly, warranting a 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'writing', 'citations', 'outlines', 'hooks', and 'research', but misses common user trigger terms like 'essay', 'article', 'blog post', 'draft', 'edit', or 'proofread'. Terms are moderately natural but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | 'Writing high-quality content' is extremely broad and would conflict with many other writing, editing, or content-related skills. There is no specific niche, file type, or domain that distinguishes this from general writing assistance. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is excessively verbose, spending hundreds of lines on templates, examples, and explanations that Claude doesn't need. While it provides some useful structure (feedback templates, workflow sequences), it fails to specify concrete tool usage for research and lacks validation checkpoints. The entire content should be condensed to roughly 25% of its current size, with templates moved to separate reference files.
Suggestions
Reduce content by 70-75%: remove 'When to Use', 'What This Skill Does', 'Pro Tips', 'Best Practices', and 'Related Use Cases' sections entirely—Claude already knows these concepts.
Specify concrete tool usage for research: which tools (web search, file reading) to use, how to verify sources, and what to do when sources can't be found.
Split large template blocks (feedback format, outline template, review checklist) into separate referenced files to improve progressive disclosure.
Add validation checkpoints to workflows: e.g., 'Verify all citations link to real sources before finalizing', 'Confirm tone matches user's sample writing before proceeding to next section'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains obvious concepts Claude already knows (what a hook is, what citations are, how to mkdir). Massive template blocks for feedback, outlines, and reviews that could be condensed to brief patterns. Sections like 'When to Use This Skill', 'What This Skill Does', 'Pro Tips', and 'Best Practices' are largely redundant filler that Claude doesn't need. | 1 / 3 |
Actionability | Provides structured templates and example outputs (feedback format, research format, hook alternatives), which give some concrete guidance. However, the skill is fundamentally about prompting patterns rather than executable code/commands, and the 'research' instructions are vague ('Search for relevant information', 'Find credible sources') without specifying which tools to use or how to actually perform web searches. | 2 / 3 |
Workflow Clarity | Multiple workflows are listed (blog post, newsletter, tutorial, thought leadership) with numbered steps, providing reasonable sequencing. However, there are no validation checkpoints or feedback loops for error recovery. The workflows are high-level checklists without explicit verification steps (e.g., confirming research accuracy, validating citations exist). | 2 / 3 |
Progressive Disclosure | Everything is crammed into a single monolithic file with no references to external files despite the content being long enough to warrant splitting. The file organization section suggests creating separate files (research.md, outline.md) for the user's project but doesn't split the skill's own content. Inline content includes full template blocks that could be referenced separately. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
d065ead
- Reviewed
Table of Contents
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.