CtrlK
BlogDocsLog inGet started
Tessl Logo

methods-reverse-engineer

Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow. Use this skill when a user wants to understand how a study was actually executed, extract data sources, inclusion/exclusion logic, preprocessing, analytical sequence, software/tools, validation path, and critical parameters, or build a replication checklist from a paper, abstract, DOI, PMID, title, screenshot, or partial methods text. Do not treat this as generic summarization. Focus on reconstructing the operational method pipeline, surfacing missing reproducibility details, and distinguishing explicitly reported steps from inferred or unresolved ones. Never fabricate references, methods details, identifiers, software versions, parameters, datasets, or validation steps.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The content is a well-structured, instruction-dense skill with strong progressive disclosure and a clear sequenced workflow, weakened mainly by redundant prohibition sections and the absence of a worked example.

Suggestions

Consolidate the overlapping negative guidance in 'Out-of-scope', 'This skill should not', 'What This Skill Should Not Do', and 'Hard Rules' into a single deduplicated section to reduce token redundancy.

Add one short worked example showing a reconstructed output (e.g., a sketch of Sections A-K for a sample omics paper) to make the deliverable concrete.

Inline the most decision-critical extraction rules (e.g., the explicit/inferred/missing labeling rule for Section F) rather than only pointing to reference files, so the core workflow is self-contained.

DimensionReasoningScore

Conciseness

The body is operationally dense rather than padded with beginner concepts, but negative guidance is repeated across 'Out-of-scope', 'This skill should not', 'What This Skill Should Not Do', and 'Hard Rules', so it could be tightened by consolidating overlapping prohibitions.

3 / 5

Actionability

Provides concrete per-section deliverables (Section A-K bullet lists) and a defined 10-step execution sequence, but delegates most specific extraction rules to reference files and includes no worked example of a reconstructed output.

4 / 5

Workflow Clarity

A clearly ordered Step 1-10 sequence with a coverage-level gating checkpoint and a final 'Reproduction Readiness Judgment' checkpoint is present, but it lacks an explicit validate-and-retry feedback loop (not strictly required for a non-destructive analysis skill).

4 / 5

Progressive Disclosure

The body is an overview that maps each of 11 reference files to a specific use point (e.g. Section B, D-F) in a dedicated integration section; all referenced files exist and are one level deep with clear navigation.

5 / 5

Total

16

/

20

Passed

Description

100%Weight 40%Scale 1-5

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 exemplary: third-person, specific, comprehensive in actions and trigger terms, and unambiguously defines both purpose and invocation conditions while actively distinguishing itself from generic summarization.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Reverse-engineers the methods section', 'extract data sources, inclusion/exclusion logic, preprocessing, analytical sequence, software/tools, validation path', 'build a replication checklist'), giving comprehensive coverage of capabilities.

5 / 5

Completeness

Explicitly answers both what ('Reverse-engineers the methods section of a biomedical paper into a structured, reproducible workflow') and when ('Use this skill when a user wants to understand how a study was actually executed... or build a replication checklist...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user phrasings and synonyms comprehensively ('how a study was actually executed', 'build a replication checklist from a paper, abstract, DOI, PMID, title, screenshot, or partial methods text'), matching the breadth a user would naturally say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (biomedical methods reconstruction) with distinct triggers and an explicit disambiguator ('Do not treat this as generic summarization'), minimizing overlap with other skills.

5 / 5

Total

20

/

20

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
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.