CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

tooluniverse-immune-repertoire-analysis

TCR/BCR repertoire analysis — V(D)J segment usage, CDR3 sequence diversity, clonality scoring, antigen specificity matching to IEDB, public-clone identification. Use for adaptive immune response characterization, post-treatment immune monitoring, antigen-specific clone tracking, and clonal-expansion analysis in immunotherapy or vaccination studies.

Quality

79%

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 ./plugin/skills/tooluniverse-immune-repertoire-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 well-structured with a clearly sequenced 8-phase workflow, real validation concepts, and domain-specific reasoning that goes beyond common knowledge. Its main weaknesses are a non-executable Quick Start relying on undefined helper functions, redundant explanation of standard diversity indices, and See Also references to files that are missing from the bundle.

Suggestions

Make the Quick Start executable: replace the undefined helper functions (load_airr_data, define_clonotypes, calculate_diversity, detect_expanded_clones, analyze_vdj_usage, query_epitope_database) with real, runnable ToolUniverse/pandas calls, mirroring the concrete VDJDB_get_antigen_specificity example already in Phase 7.

Trim glosses of standard statistics Claude already knows (Shannon entropy, Simpson index, Gini coefficient definitions) and merge the overlapping clonality interpretation between "Domain Reasoning" and "Interpretation Guidance"; keep only the domain-specific thresholds and reference ranges.

Fix the broken progressive disclosure: either add ANALYSIS_DETAILS.md and USE_CASES.md to the bundle (e.g., in references/) with the promised phase code snippets and use cases, or remove the "See Also" section and inline the essential details.

DimensionReasoningScore

Conciseness

The body is mostly efficient and dense with domain-specific value (tool names, thresholds, evidence grading), but it glosses concepts Claude already knows — e.g., "Shannon entropy: Overall diversity (higher = more diverse)" and "Gini coefficient ranges from 0 (perfectly even) to 1 (single dominant clone)" — and repeats clonality interpretation between the "Domain Reasoning" and "Interpretation Guidance" sections. This fits the score-3 anchor (mostly efficient with some unnecessary explanation); it is not score 4 because the redundant metric glosses and duplicated interpretation are more than minor trimmable instances.

3 / 5

Actionability

The Quick Start is not executable: it calls undefined helper functions (load_airr_data, define_clonotypes, calculate_diversity, detect_expanded_clones, analyze_vdj_usage, query_epitope_database) and imports ToolUniverse without using it — effectively pseudocode per the score-3 anchor. Concrete bright spots exist (real VDJDB call signature, named tools with parameters), keeping it above score 2, but the missing key implementation details are exactly what the anchor describes.

3 / 5

Workflow Clarity

The 8-phase workflow is clearly sequenced and includes genuine checkpoints: rarefaction curves to verify sequencing depth, comparison against healthy-donor reference distributions, and an evidence-grading framework that flags "Insufficient" evidence (depth < 10,000 clonotypes, no replication). It is not score 5 because intermediate-output validation (e.g., confirming standardized AIRR columns after import) is left implicit rather than stated as explicit validate-and-fix loops.

4 / 5

Progressive Disclosure

In-file structure is good (clear headers, phased sections) and the "See Also" section clearly signals references, but the referenced files ANALYSIS_DETAILS.md and USE_CASES.md do not exist anywhere in the bundle, so the one-level-deep navigation dead-ends — the detailed code for all 8 phases is effectively absent. This sits between anchor 2 (broken/minimal reference structure) and anchor 4 (references that actually resolve); the strong in-file organization keeps it at the midpoint rather than below.

3 / 5

Total

13

/

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.

A strong description: it enumerates concrete capabilities in third person and provides an explicit, well-scoped "Use for..." trigger clause covering immunotherapy and vaccination contexts. The only improvement is adding common synonyms such as "AIRR-seq" or "immune repertoire sequencing" to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

The description lists five concrete, specific actions ("V(D)J segment usage, CDR3 sequence diversity, clonality scoring, antigen specificity matching to IEDB, public-clone identification") with comprehensive coverage of the repertoire-analysis domain, matching the score-5 anchor. It is written in third person with no fluff or over-claims, so it is not the score-4 anchor (which implies minor coverage gaps).

5 / 5

Completeness

It explicitly answers both questions: the "what" is the enumerated action list, and the "when" is a concrete "Use for adaptive immune response characterization, post-treatment immune monitoring, antigen-specific clone tracking, and clonal-expansion analysis in immunotherapy or vaccination studies" clause. This mirrors the score-5 anchor example's structure; score 4 would require a less explicit trigger clause, which is not the case here.

5 / 5

Trigger Term Quality

Good keyword coverage of natural domain phrases a user would say ("TCR", "BCR", "repertoire", "CDR3", "clonality", "immunotherapy", "vaccination studies") but a few natural synonyms are missing — notably "AIRR-seq", "immune repertoire sequencing", and "immunosequencing". Not score 5 because coverage of common variations is incomplete, but clearly above the midpoint, ruling out score 3's "missing common variations" framing.

4 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (adaptive immune receptor repertoire analysis) with triggers specific to that domain, so it is unlikely to fire for unrelated skills. Score 4's "minor overlap risk with closely related skills" does not apply because the trigger terms (TCR/BCR, CDR3, clonality, epitope specificity) are unambiguous.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mims-harvard/ToolUniverse

Path

plugin/skills/tooluniverse-immune-repertoire-analysis/SKILL.md

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.