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.
81
76%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/skills-codex-claude-review/research-review/SKILL.mdQuality
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 skill description that excels in completeness and trigger term coverage, with explicit 'Use when' guidance and natural user phrases. Its main weakness is that the capability description could be more specific about what kinds of critical review actions are performed (e.g., methodology critique, literature gap analysis, statistical review). Overall, it would perform well in skill selection scenarios.
Suggestions
Add more specific concrete actions beyond 'deep critical review', such as 'evaluates methodology, identifies gaps in reasoning, assesses experimental design, and provides structured feedback on research papers'.
| 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 research review via a specific MCP tool. The trigger terms are specific to research review contexts and unlikely to conflict with general writing or editing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%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 skill with a clear multi-step workflow and good convergence criteria, but it suffers from moderate verbosity and incomplete actionability. The MCP tool invocations are described rather than shown with precise, executable syntax, and the prompt templates partially duplicate the workflow guidance. The workflow clarity is the strongest dimension, with explicit polling checkpoints and iterative feedback loops.
Suggestions
Show the exact MCP tool invocation syntax (with all required parameters) for review_start, review_reply_start, and review_status as executable, copy-paste-ready examples rather than pseudo-YAML fragments.
Consolidate the prompt templates into the workflow steps where they're used, or move them to a separate TEMPLATES.md file to reduce duplication and improve conciseness.
Remove redundant guidance between 'Key Rules' and the workflow steps — for example, 'Send comprehensive context in Round 1' is already covered in Step 2.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary verbosity, such as the prompt templates section which largely repeats guidance already given in the workflow steps. The key rules section also partially duplicates workflow instructions. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete MCP tool names and a clear workflow, but the code/command examples are incomplete — the MCP call in Step 2 uses a pseudo-YAML format rather than showing exact invocation syntax, and the polling loop is described in prose rather than with executable code. The prompt templates are useful but are fragments rather than complete, copy-paste-ready examples. | 2 / 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 to poll for completion status before proceeding. The save-jobId-then-poll pattern is explicitly called out as a checkpoint. | 3 / 3 |
Progressive Disclosure | The content is reasonably well-structured with clear section headers, but it's somewhat monolithic — the prompt templates section and key rules could be split into a separate reference file. There are no references to external files for advanced usage or detailed API documentation, though the skill does reference prerequisite installation paths. | 2 / 3 |
Total | 9 / 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
700fbe2
- 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.