tooluniverse-immune-repertoire-analysis

Comprehensive immune repertoire analysis for T-cell and B-cell receptor sequencing data. Analyze TCR/BCR repertoires to assess clonality, diversity, V(D)J gene usage, CDR3 characteristics, convergence, and predict epitope specificity. Integrate with single-cell data for clonotype-phenotype associations. Use for adaptive immune response profiling, cancer immunotherapy research, vaccine response assessment, autoimmune disease studies, or repertoire diversity analysis in immunology research.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%

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

The skill is highly actionable with executable code across a well-sequenced 8-phase workflow, but it is verbose, lacks validation checkpoints for batch operations, and is a monolith with no progressive file structure. Tightening explanations and adding verification steps would raise the weaker dimensions.

Suggestions

Add explicit validation checkpoints (e.g., assert expected columns exist after load_airr_data, verify clonotype aggregation counts) and a validate→fix→retry loop for batch operations like longitudinal tracking and public clonotype detection to raise workflow clarity.

Tighten or remove docstrings that re-explain well-known concepts (Shannon entropy, Simpson index, convergent recombination) and trim the Overview's restated phase list to improve conciseness.

Split the Advanced Use Cases, ToolUniverse Tool Integration, and Troubleshooting sections into referenced bundle files (e.g., ADVANCED.md, TROUBLESHOOTING.md) to introduce genuine progressive disclosure and reduce the monolithic SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly executable code but re-explains metrics Claude already knows (e.g., 'Shannon entropy: Overall diversity', 'Convergent recombination = ...') and the Overview restates phases already covered by the phase sections, so it could be tightened.	2 / 3
Actionability	Provides complete, executable function implementations (load_airr_data, define_clonotypes, calculate_diversity, detect_expanded_clones) with concrete ToolUniverse and scanpy calls; the few placeholder sections (VDJdb) are honestly flagged rather than presented as final pseudocode.	3 / 3
Workflow Clarity	The 8 phases are clearly sequenced, but validation/verification checkpoints are missing for batch operations (longitudinal tracking, public clonotype detection), capping workflow clarity at 2 per the destructive/batch-operations guideline.	2 / 3
Progressive Disclosure	A single monolithic ~950-line SKILL.md with good header organization but no references/scripts/assets bundle files and no one-level-deep referenced material; advanced use cases and tool integration are inline rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 strong: it specifies concrete capabilities, includes natural trigger terms, provides an explicit 'Use for' clause, and carves out a clearly distinct niche. No significant weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — assess clonality, diversity, V(D)J gene usage, CDR3 characteristics, convergence, predict epitope specificity, and single-cell integration — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers what it does and includes an explicit 'Use for ...' trigger clause enumerating concrete use cases, satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Uses natural domain terms a researcher would say (TCR/BCR, immune repertoire, cancer immunotherapy, vaccine response, autoimmune disease) with good coverage, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear, specialized niche (AIRR-seq / TCR-BCR repertoire analysis) with distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (950 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-immune-repertoire-analysis/SKILL.md
Commit: df37802

Reviewed: 2 days 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.