CtrlK
BlogDocsLog inGet started
Tessl Logo

inno-experiment-analysis

This skill should be used when the user asks to "analyze experimental results", "generate results section", "statistical analysis of experiments", "compare model performance", "create results visualization", or mentions connecting experimental data to paper writing. Provides comprehensive guidance for analyzing ML/AI experimental results and generating paper-ready content.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/inno-experiment-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A well-structured, clearly sequenced analysis workflow with a useful quality checklist and well-signaled reference files. It is held back by verbosity and section-to-section redundancy, vague 'select appropriate tools' directions lacking concrete tooling, and broken references to a nonexistent examples/ directory.

Suggestions

Collapse the 'Common Mistakes and Pitfalls' and 'Best Practices Summary' sections into a single reference (e.g. fold into references/common-pitfalls.md) to remove the duplicated ✅/❌ lists and tighten the body.

Replace vague directives like 'Select appropriate tools for data loading' and 'Use appropriate visualization tools' with named libraries/commands or concrete code snippets so the guidance is executable.

Either create the referenced examples/ directory with example-analysis-report.md and example-results-section.md, or remove those references from the body to avoid broken navigation.

DimensionReasoningScore

Conciseness

The body is mostly domain-specific and organized, but it explains concepts Claude already knows (basic statistics such as Mean/Standard Deviation/Confidence Interval, common chart types) and carries substantial redundancy — the 'Common Mistakes and Pitfalls' and 'Best Practices Summary' sections repeat the same cherry-picking, statistical-significance, colorblind-palette, and error-bar points, and the closing 'Workflow Overview' restates the opening pipeline.

2 / 3

Actionability

It provides concrete guidance such as a Results-section structure template, validation checks, and a quality checklist, but key directions are vague ('Select appropriate tools for data loading', 'Use appropriate visualization tools to generate publication-quality figures') with no specific libraries, commands, or executable code, so it is not fully copy-paste ready.

2 / 3

Workflow Clarity

The six-step pipeline (Data Loading → Validation → Statistical Analysis → Visualization → Writing → Quality Check) is clearly sequenced and ends in an explicit Quality Check checklist with concrete verification items, matching the clear-sequence-with-checklist anchor.

3 / 3

Progressive Disclosure

The four references/ guides are real files and clearly signaled at one level deep ('See references/statistical-methods.md'), but the body also references an examples/ directory (example-analysis-report.md, example-results-section.md) that does not exist, and the duplicated pitfalls/best-practices content is inline material that should have been externalized.

2 / 3

Total

9

/

12

Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description with explicit trigger guidance and good coverage of natural user phrases, clearly answering both what the skill does and when to use it. The main weakness is the vague 'comprehensive guidance' summary line, which keeps specificity below the top anchor.

DimensionReasoningScore

Specificity

The description names the ML/AI experimental-results domain and several concrete actions via trigger phrases ('analyze experimental results', 'generate results section', 'compare model performance', 'create results visualization'), but the capability summary 'Provides comprehensive guidance' is abstract padding rather than a crisp enumeration of capabilities, so it does not reach the multiple-specific-concrete-actions anchor.

2 / 3

Completeness

It explicitly answers both 'what' ('analyzing ML/AI experimental results and generating paper-ready content') and 'when' ('when the user asks to ... or mentions connecting experimental data to paper writing') with explicit triggers, satisfying the what-and-when anchor.

3 / 3

Trigger Term Quality

It covers natural phrases a user would actually say — 'analyze experimental results', 'generate results section', 'statistical analysis of experiments', 'compare model performance', 'create results visualization' — giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The niche — ML/AI experimental results analysis tied to paper writing — is fairly distinct, and the triggers are specific enough that it is unlikely to fire for unrelated skills despite a noted overlap with the ml-paper-writing skill.

3 / 3

Total

11

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
OpenLAIR/dr-claw
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.