meta-manuscript-generator
Generates a first draft of a clinical meta-analysis paper. Input the research report (including Methods and Results sections), language, and title to automatically generate a complete paper draft including Abstract, Introduction, Discussion, and other sections, with automatic PubMed retrieval of relevant references. Suitable for assisting in the writing of systematic reviews and meta-analyses.
56
65%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/meta-manuscript-generator/SKILL.mdQuality
Discovery
82%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 strong description that clearly communicates specific capabilities in a well-defined niche. The main weakness is the lack of an explicit 'Use when...' clause, which would help Claude better identify when to select this skill. The domain-specific terminology provides excellent trigger terms for the target audience.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for help writing or drafting a meta-analysis paper, systematic review manuscript, or needs to generate paper sections from research results.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generates a first draft, takes research report input, automatically generates Abstract/Introduction/Discussion sections, performs automatic PubMed retrieval of references. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | The 'what' is clearly answered with detailed capabilities. However, the 'when' is only implied through 'Suitable for assisting in the writing of systematic reviews and meta-analyses' rather than using an explicit 'Use when...' clause with trigger guidance. Per rubric guidelines, a missing explicit 'Use when...' clause caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'meta-analysis', 'clinical', 'paper', 'systematic reviews', 'PubMed', 'references', 'Abstract', 'Introduction', 'Discussion', 'draft'. These cover the domain well and match how researchers would describe their needs. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: clinical meta-analysis paper drafting with PubMed integration. This is unlikely to conflict with other skills due to its very specific domain (systematic reviews, meta-analyses) and specific tooling (PubMed retrieval). | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a well-structured five-stage workflow for meta-analysis manuscript generation with clear sequencing and a quality checklist, which is its strongest aspect. However, it suffers from significant verbosity—the description is repeated multiple times across sections, boilerplate 'When to Use' and 'Key Features' sections add little value, and concepts Claude already understands are over-explained. The actionability is moderate: while the workflow is detailed, the referenced scripts are not available in the bundle, limiting true executability.
Suggestions
Remove the redundant 'When to Use', 'Key Features', and 'Implementation Details' sections which largely repeat the description or contain generic boilerplate—start directly with Input Requirements and Workflow.
Eliminate explanations of concepts Claude already knows, such as what PubMed E-utilities are, what AMA citation format looks like, and how regex works—just provide the specific patterns and endpoints needed.
Provide the actual bundle files (scripts/search_references.py, scripts/insert_references.py, references/writing-guide.md) or include the essential logic inline so the skill is truly executable rather than referencing non-existent files.
Move detailed sub-workflows (e.g., the full reference insertion processing steps, search allocation tables) into separate reference files to reduce the monolithic nature of the SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is highly verbose with significant redundancy. The 'When to Use' section repeats the description nearly verbatim, 'Key Features' restates the description again, 'Implementation Details' says 'See Workflow above' then repeats generic boilerplate, and the 'Example Usage' section includes generic py_compile commands. Many sections contain information Claude already knows (what PubMed APIs are, what AMA citation format is, basic regex concepts). | 1 / 3 |
Actionability | The workflow stages provide reasonably concrete guidance with specific word counts, search allocation strategies, and code examples for the Python scripts. However, the code examples reference scripts (search_references.py, insert_references.py) whose actual implementations are not provided in the bundle, making them not truly executable. The PubMed API usage is described but not given as complete runnable code. | 2 / 3 |
Workflow Clarity | The five-stage workflow (Report Parsing → Reference Retrieval → Section Writing → Reference Insertion → Final Integration) is clearly sequenced with explicit substeps, a quality checklist at the end for validation, and clear input/output expectations at each stage. The reference insertion stage includes a detailed processing workflow with error-handling considerations like renumbering conflicts. | 3 / 3 |
Progressive Disclosure | The skill references `references/writing-guide.md` for detailed writing guidelines and mentions scripts in `scripts/`, which is good progressive disclosure structure. However, no bundle files are provided to verify these exist, and the SKILL.md itself is monolithic—much of the detailed workflow content (e.g., the full reference insertion processing workflow, search allocation details) could be split into separate reference files rather than inlined. | 2 / 3 |
Total | 8 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
d3c2c0f
- 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.