research-review
Get a deep critical review of research from Claude via claude-review MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both what the skill does and when to use it, with good trigger term coverage. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., identifying methodological issues, evaluating experimental design, checking logical consistency). Overall it performs well for skill selection purposes.
Suggestions
Add 2-3 more specific concrete actions beyond 'deep critical review', such as 'identifies methodological flaws, evaluates experimental design, checks logical consistency of arguments'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (research review) and mentions the tool (claude-review MCP), but the concrete actions are limited to 'deep critical review' without listing specific capabilities like identifying methodological flaws, checking statistical validity, evaluating novelty, etc. | 2 / 3 |
Completeness | Clearly answers both what ('Get a deep critical review of research from Claude via claude-review MCP') and when ('Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'review my research', 'help me review', 'get external review', 'critical feedback', 'research ideas', 'papers', 'experimental results' — these cover a good range of phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche — critical review of research via a specific MCP tool. The trigger terms are specific to research review workflows and unlikely to conflict with general writing or coding skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill that clearly guides Claude through a multi-round research review workflow using MCP tools. Its main strengths are the concrete tool call examples, clear async polling pattern, and well-defined convergence criteria. The main weakness is moderate verbosity — some content is repeated across sections (key rules vs. workflow steps, prompt templates vs. inline examples), and the skill could benefit from splitting supplementary content into referenced files.
Suggestions
Extract the prompt templates section into a separate PROMPTS.md file and reference it, reducing the main skill's length while preserving the actionable templates.
Remove redundancy between the 'Key Rules' section and the workflow steps — several rules (e.g., 'send comprehensive context in Round 1') are already stated in the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity — the prompt templates section repeats guidance already covered in the workflow, and some explanatory text (e.g., 'the external model cannot read your files') could be trimmed. The key rules section partially overlaps with workflow instructions. | 2 / 3 |
Actionability | The skill provides concrete MCP tool calls with specific parameters, exact polling patterns (jobId/threadId management), specific follow-up prompt patterns, and clear deliverables to request. The workflow is executable and copy-paste ready for the MCP interactions. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation/convergence criteria (Step 4), feedback loops (iterative dialogue in Step 3), and clear instructions for polling status until done=true. The async job pattern with bounded waitSeconds is well-specified. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's somewhat long for a single file with no references to supporting documents. The prompt templates could be split into a separate file, and the prerequisites/installation could reference external setup docs rather than being inline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
a425a71
- 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.