meta-results-sensitivity-analysis
Generates the "Results" section for meta-analysis sensitivity analysis based on statistical tables and titles. Use when the user wants to describe sensitivity analysis results or format sensitivity tables for a meta-analysis paper.
44
44%
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-sensitivity-analysis/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 well-crafted description for a highly specialized skill. It clearly identifies both what it does and when to use it, with domain-specific trigger terms that would naturally appear in user requests. The only minor weakness is that the 'what' could enumerate more specific actions (e.g., interpreting leave-one-out analyses, generating forest plot descriptions).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (meta-analysis sensitivity analysis) and a specific action (generates the 'Results' section), but doesn't list multiple concrete actions beyond generating text and formatting tables. | 2 / 3 |
Completeness | Clearly answers both what ('Generates the Results section for meta-analysis sensitivity analysis based on statistical tables and titles') and when ('Use when the user wants to describe sensitivity analysis results or format sensitivity tables for a meta-analysis paper'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'sensitivity analysis', 'meta-analysis', 'Results section', 'sensitivity tables', 'meta-analysis paper'. These are terms a researcher would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — meta-analysis sensitivity analysis results writing. Unlikely to conflict with other skills due to the highly specialized domain and specific output type (Results section). | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate that appears auto-generated, resulting in extreme verbosity and redundancy. The actual domain-specific content (sensitivity analysis formatting) is minimal and buried among generic sections about failure handling, deterministic output rules, and completion checklists. The code example is commented out, the referenced scripts are not in the bundle, and the workflow is contradictory and unclear.
Suggestions
Remove all generic boilerplate sections (Failure Handling, Deterministic Output Rules, Completion Checklist, Output Contract, Validation and Safety Rules) and focus only on the sensitivity analysis task-specific content.
Provide a complete, executable code example showing how to call `format_sensitivity_result()` with real input data and expected output, instead of commented-out pseudocode.
Consolidate the duplicated sections (two 'When to Use', three validation sections, two input specifications) into a single clear workflow with numbered steps and explicit validation checkpoints.
Include the actual `scripts/format_result.py` in the bundle or inline the key function signature and behavior so the skill is self-contained and actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Multiple sections restate the same information (e.g., 'When to Use' appears twice, 'Validation' appears three times, workflow is referenced circularly). Boilerplate sections like 'Key Features', 'Failure Handling', 'Deterministic Output Rules', and 'Completion Checklist' add generic filler that Claude already knows. The skill could be expressed in ~30 lines instead of 150+. | 1 / 3 |
Actionability | The code example is entirely commented out pseudocode. The primary script referenced (`scripts/validate_skill.py`) appears to be a generic validation script, not the actual `format_result.py` that does the work. There are no executable, copy-paste-ready examples. The 'Example run plan' is vague and generic rather than specific to this sensitivity analysis task. | 1 / 3 |
Workflow Clarity | The actual workflow (generate description via LLM, then format output) is buried and underspecified. There are contradictory validation sections — one says to run `validate_skill.py --help`, another says 'No local script validation step is required.' The two-step workflow lacks any validation checkpoints or error recovery for the LLM generation step. Steps are unclear and the sequence is muddled by boilerplate. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no external references despite referencing scripts that don't appear in the bundle. Internal cross-references are circular ('See ## Usage above', 'See ## Workflow above'). Multiple sections cover the same ground (three validation sections, two 'when to use' sections, two 'required inputs' sections) without clear navigation or hierarchy. | 1 / 3 |
Total | 4 / 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.