CtrlK
BlogDocsLog inGet started
Tessl Logo

bulk-omics-integrative-planner

Designs complete integrated research plans for bulk transcriptomics, proteomics, metabolomics, and related omics from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a bulk multi-omics or single-omics-plus-clinical study — including disease-focused, mechanism-focused, biomarker-focused, stratification-oriented, or translational projects. It should define the research question, choose the best-fit study pattern, recommend example datasets as reference candidates only, specify the core analysis modules and method choices, propose a validation ladder, and output four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, accession numbers, sample counts, metadata completeness, cohort availability, assay coverage, literature references, PMIDs, DOIs, or validation status. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.

72

Quality

88%

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

77%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, actionable instruction skill with clear workflow sequencing, an explicit validation checkpoint, and excellent progressive disclosure through mapped reference files. Its main weakness is systematic redundancy — core guardrails and the risk-review checklist are restated three to four times across sections.

Suggestions

Consolidate the repeated guardrails: state the no-fabrication, no-overclaim, and DESeq2/limma rules once in Hard Rules and reference them from Core Function and Formatting rather than restating verbatim.

Keep the self-critical risk-review checklist in a single place (Section L or Hard Rule 13) and have Step 7 point to it instead of duplicating the six-point list.

Add one short worked example (a skeleton plan for a representative input) so the A–L structure is anchored by a concrete reference output.

DimensionReasoningScore

Conciseness

The body is mostly efficient operational guidance, but the same guardrails are restated multiple times — the self-critical risk review appears in Step 7, Section L, and Hard Rule 13; the no-fabrication rule in Core Function, Hard Rule 1, and the description; the DESeq2/limma rule in Formatting and Hard Rule 7 — so it could be meaningfully tightened.

3 / 5

Actionability

Provides concrete, specific guidance — a fixed 7-step execution order, an explicit A–L output structure, section-to-reference-module mapping, and a hard DESeq2-for-count / limma-for-normalized rule — but lacks a worked example of a complete plan output to anchor the common cases.

4 / 5

Workflow Clarity

The 7-step sequence is clearly ordered and includes an explicit validation checkpoint (Step 5 'Dependency Consistency Check (mandatory before output)') plus a closing self-critical risk review, satisfying the feedback-loop requirement.

5 / 5

Progressive Disclosure

The body is an overview that points to nine one-level-deep reference modules, each clearly signaled and mapped to a specific output section in 'Reference Module Integration'; all referenced files exist in references/.

5 / 5

Total

17

/

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 specific, trigger-rich, and clearly distinguishes the skill's niche while answering both what it does and when to use it. Minor verbosity from embedded guardrails ('Never fabricate ...', 'Always include the mandatory Dataset Disclaimer') does not detract from completeness or specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'define the research question, choose the best-fit study pattern, recommend example datasets ... specify the core analysis modules and method choices, propose a validation ladder, and output four workload configurations (Lite / Standard / Advanced / Publication+)' — giving comprehensive coverage rather than a few actions.

5 / 5

Completeness

Explicitly answers both what ('Designs complete integrated research plans ...') and when ('Always use this skill whenever a user wants to design, scope, or structure ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural domain phrasing users would say — 'design, scope, or structure a bulk multi-omics or single-omics-plus-clinical study' plus disease-/mechanism-/biomarker-/stratification-/translational-focused variants — comprehensively with synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — bulk-omics integrative study planning — with distinct triggers and explicit scope boundaries ('not a generic omics tool list, not a literature review'), minimizing conflict with adjacent 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.