CtrlK
BlogDocsLog inGet started
Tessl Logo

peer-review-response-drafter

Assist in drafting professional peer review response letters. Trigger.

33

Quality

28%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/peer-review-response-drafter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

22%

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 description is underdeveloped and appears incomplete, with the trailing 'Trigger.' suggesting an unfinished thought. It lacks concrete actions, explicit trigger guidance, and natural keyword variations. The domain is somewhat distinctive but the description fails to provide enough detail for Claude to confidently select this skill over others.

Suggestions

Add a 'Use when...' clause with trigger terms like 'reviewer comments', 'rebuttal letter', 'manuscript revision', 'journal review response', 'revision letter'.

List specific concrete actions such as 'Structures point-by-point responses to reviewer comments, drafts rebuttal arguments, formats revision cover letters for journal submissions'.

Remove the meaningless trailing 'Trigger.' fragment and replace it with substantive trigger guidance.

DimensionReasoningScore

Specificity

The description says 'drafting professional peer review response letters' which names a domain but describes only one vague action ('assist in drafting'). No concrete sub-actions like structuring rebuttals, addressing reviewer comments point-by-point, or formatting are mentioned.

1 / 3

Completeness

The 'what' is weakly stated ('assist in drafting') and there is no 'when' clause or explicit trigger guidance. The word 'Trigger' appears to be a placeholder or fragment rather than actual trigger guidance. Missing a 'Use when...' clause caps this at 2, and the weak 'what' brings it to 1.

1 / 3

Trigger Term Quality

It includes 'peer review response letters' which is a relevant keyword a user might say, but misses common variations like 'reviewer comments', 'rebuttal letter', 'revision response', 'manuscript revision', or 'journal review'. The word 'Trigger' at the end is meaningless noise.

2 / 3

Distinctiveness Conflict Risk

The domain of 'peer review response letters' is fairly specific and unlikely to conflict with many other skills, but the vague phrasing 'assist in drafting professional' could overlap with general writing or letter-drafting skills.

2 / 3

Total

6

/

12

Passed

Implementation

35%

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

This skill suffers from extreme verbosity and heavy boilerplate that obscures the actual peer review response drafting guidance. The domain-specific content (Overview, Input/Output Format, Usage Example, Quality Checklist) is reasonable but buried under generic scaffolding sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Input Validation) that add no actionable value. There are signs of template-based auto-generation, including a mismatched audit command referencing 'symptoms, history, assessment' from what appears to be a medical/clinical skill.

Suggestions

Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Output Requirements, Response Template, Input Validation) that don't contain peer-review-specific guidance — these waste tokens on content Claude already knows.

Add a concrete, complete example showing input reviewer comments and the expected formatted response letter output, demonstrating the exact tone and structure expected.

Fix the audit command that references 'symptoms, history, assessment, and next-step plan' — this appears copied from a different medical skill and is not relevant to peer review responses.

Consolidate the workflow into a single, clear peer-review-specific sequence: parse reviewer comments → match with author changes → draft point-by-point responses → apply tone adjustment → format final letter, with explicit validation at each step.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. Contains massive amounts of boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no value for Claude. Multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Overview above'). The skill explains obvious concepts and includes generic template sections that aren't specific to peer review response drafting. Much of the content is scaffolding that wastes tokens.

1 / 3

Actionability

The Usage Example with reviewer comments and the Quality Checklist provide some concrete guidance. The Parameters table is specific. However, the actual peer-review-specific instructions are thin — there's no executable code showing how responses are structured, no concrete examples of good vs bad response phrasing, and the 'scripts/main.py' commands are generic placeholders with no evidence the script exists (no bundle files provided). The audit command '--input "Audit validation sample with explicit symptoms, history, assessment, and next-step plan"' appears to be from a different medical skill entirely.

2 / 3

Workflow Clarity

The Workflow section lists 5 steps but they are generic process steps (confirm objective, validate scope, use script, return result, fallback) rather than peer-review-specific steps. The Quality Checklist provides good validation checkpoints. However, there's no clear feedback loop for iterating on response quality, and the workflow doesn't clearly sequence the actual peer review response drafting process (parse comments → draft responses → adjust tone → format letter).

2 / 3

Progressive Disclosure

References to supporting files (references/response_templates.md, references/tone_guide.md, references/examples/) are present and clearly signaled. However, the main SKILL.md is a monolithic wall of text with many sections that should be separated or removed entirely. The document is poorly organized with sections like 'Prerequisites' appearing after 'Security Checklist', and cross-references pointing to sections that don't logically precede them.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
aipoch/medical-research-skills
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.