meta-results-risk-of-bias
Generates the "Risk of Bias" results section for a meta-analysis based on assessment tables and statistics. Use when the user wants to draft the risk of bias analysis text from provided data tables.
48
51%
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-results-risk-of-bias/SKILL.mdQuality
Discovery
75%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 is well-structured with a clear 'Use when' clause and occupies a distinct niche, making it unlikely to conflict with other skills. However, it could benefit from listing more specific concrete actions beyond just 'generates the results section' and including additional trigger terms that users in this domain commonly use (e.g., 'RoB', 'systematic review', 'ROBINS-I').
Suggestions
Add more specific concrete actions, e.g., 'Generates the Risk of Bias results section by summarizing bias domain ratings, interpreting overall bias judgments, and integrating statistical summaries into narrative text.'
Include additional natural trigger terms users might say, such as 'RoB', 'RoB 2', 'ROBINS-I', 'systematic review', 'quality assessment', 'bias domains', or 'methodological quality'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (meta-analysis risk of bias) and a primary action (generates the results section), but doesn't list multiple concrete actions like interpreting assessment tables, summarizing bias domains, or formatting statistics. | 2 / 3 |
Completeness | Clearly answers both what (generates the Risk of Bias results section for a meta-analysis based on assessment tables and statistics) and when (when the user wants to draft the risk of bias analysis text from provided data tables), with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'Risk of Bias', 'meta-analysis', 'assessment tables', and 'data tables', but misses common variations users might say such as 'RoB', 'bias assessment', 'systematic review', 'quality assessment', or specific tool names like 'RoB 2' or 'ROBINS-I'. | 2 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche — generating Risk of Bias results sections for meta-analyses — which is unlikely to conflict with other skills. The combination of 'risk of bias', 'meta-analysis', and 'results section' creates a distinct trigger profile. | 3 / 3 |
Total | 10 / 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 suffers from severe redundancy, appearing to be a generic template wrapper merged with the actual skill content, resulting in duplicate 'When to Use', validation, and workflow sections. The core idea — a two-step process of drafting risk-of-bias text then formatting it — is sound but buried under extensive boilerplate. The generic sections (Failure Handling, Deterministic Output Rules, Completion Checklist, Safety Rules) add no skill-specific value and waste significant token budget.
Suggestions
Remove all duplicate sections and generic boilerplate (Failure Handling, Deterministic Output Rules, Completion Checklist, Validation and Safety Rules) — these teach Claude nothing it doesn't already know and nearly double the file length.
Consolidate into a single clear structure: one 'When to Use' section, one 'Workflow' section with the prompt template and format command, and one 'Tools' section.
Add a concrete example showing actual input data (a small statistics table and assessment table) and the expected output text, so Claude can see the target format.
Add a validation step between drafting and formatting (e.g., verify word count, check that all D1-D5 domains are covered, confirm statistics match the input table).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The skill contains duplicate sections (two 'When to Use' sections, two 'Validation' sections, two 'Quick Validation' blocks). Generic boilerplate like 'Failure Handling', 'Deterministic Output Rules', 'Completion Checklist', and 'Validation and Safety Rules' sections are padded filler that Claude already knows. The 'Key Features' section restates the description verbatim. Much of the content could be cut by 60%+ without losing any actionable information. | 1 / 3 |
Actionability | The core workflow (draft text with specific requirements, then run format_result.py) is reasonably concrete, with a clear prompt template and a bash command. However, the script invocation uses a placeholder `--text "<generated_text>"` without clarifying how to pass multi-paragraph text, and no bundle files are provided to verify the script exists or works. The prompt template with {{variables}} is useful but not fully executable. | 2 / 3 |
Workflow Clarity | The actual workflow (draft then format) is a clear two-step sequence, but there are no validation checkpoints between steps. The skill doesn't specify how to verify the drafted text meets the >300 word requirement or is academically sound before formatting. The 'Example run plan' in the first half and the 'Workflow' in the second half are redundant and slightly inconsistent, creating confusion about which is authoritative. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files for detailed content. The skill appears to be two separate skill files merged together — a generic template wrapper and the actual skill content — creating a confusing, disorganized structure with duplicate sections. No bundle files are provided to verify referenced scripts exist. | 1 / 3 |
Total | 6 / 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.