cibersort-immune-infiltration-analysis

Use when estimating relative immune cell infiltration from a bulk expression matrix with a CIBERSORT-style nu-SVR deconvolution workflow based on an LM22 signature matrix, comparing one case group against one control group, and generating structured tables plus immune-fraction plots. NOT for single-cell RNA-seq, spatial data, clinical diagnosis, or workflows that require the original hosted CIBERSORT web service.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

68%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 body is highly actionable and well-organized with concrete commands, argument and output tables, and clear external-file navigation. The main weaknesses are duplicated scope guidance and a passive rather than gated validation workflow for a batch operation.

Suggestions

Consolidate the scope/exclusion guidance (currently repeated in 'When Not to Use', 'Input Validation', and the out-of-scope response block) into a single section to reduce duplicated tokens.

Add an explicit validate-then-fix-then-rerun checkpoint to the Workflow sequence (e.g., after running, check run_record.txt for error codes, fix the input, and rerun before reviewing results) rather than only inspecting after each run.

Resolve the missing tests/ references: either add the tests/data/ inputs and tests/run_tests.R, tests/test_skill.R files to the bundle or update the body to point to the actually-shipped test path.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables and concrete examples, but scope material is duplicated across 'When to Use'/'When Not to Use' and the later 'Input Validation'/'Do not use'/'If the user's request is outside this scope' block, adding restated tokens.	3 / 5
Actionability	Copy-paste-ready bash usage, a complete arguments table with types and defaults, concrete CSV input-format examples, a full output-file table, and a validated test command with exact flags.	5 / 5
Workflow Clarity	A four-step sequence is present, but validation is passive ('Inspect run_record.txt and output_manifest.txt after each run') rather than an explicit validate-fix-retry checkpoint; for a batch analysis operation the missing feedback-loop gate caps this at 3.	3 / 5
Progressive Disclosure	Good structure with a clear 'When to Read External Files' navigation table pointing one level deep to real references (algorithm.md, troubleshooting.md, cli-guide.md), though the body references a tests/ directory and tests/run_tests.R that are not present in the bundle.	4 / 5
	Total	15 / 20 Passed

Description

92%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, complete, and well-differentiated, clearly stating both what the skill does and when to use it with concrete exclusion guidance. It is a strong, low-conflict trigger description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'estimating relative immune cell infiltration', 'nu-SVR deconvolution', 'comparing one case group against one control group', and 'generating structured tables plus immune-fraction plots' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (estimate infiltration via nu-SVR deconvolution, compare groups, generate tables/plots) and when ('Use when...'), reinforced by a concrete 'NOT for' exclusion clause.	5 / 5
Trigger Term Quality	Strong natural-term coverage including 'immune cell infiltration', 'bulk expression matrix', 'CIBERSORT', 'LM22', 'case group/control group', plus exclusion terms, but a few common synonyms or file extensions (e.g. .txt) are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (CIBERSORT-style, LM22, one case vs one control, local R implementation) with explicit exclusions (single-cell, spatial, clinical, hosted service) gives minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/cibersort-immune-infiltration-analysis/SKILL.md
Commit: 63c61d3

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

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.