tooluniverse-antibody-engineering

Therapeutic antibody engineering and optimization, lead-to-clinical-candidate. Covers sequence humanization (germline alignment, framework retention), affinity maturation, developability (aggregation, stability, PTMs), structure modeling (AlphaFold/PDB CDR analysis), immunogenicity prediction, and manufacturing feasibility. Use for biologic-drug optimization, mAb design review, biosimilar engineering, and clinical-precedent comparison.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-antibody-engineering/SKILL.md

Quality

Content

57%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.

A well-organized, knowledgeable workflow whose on-paper structure is undermined by missing bundle files that the body repeatedly relies on for code examples. Code/executable guidance is largely deferred to references that are absent, and validation feedback loops for the analysis pipeline are thin.

Suggestions

Add the missing referenced files (WORKFLOW_DETAILS.md, REPORT_TEMPLATE.md, MANUFACTURING.md, EXAMPLES.md, CHECKLISTS.md, QUICK_START.md) to the bundle, or inline the essential code examples each phase promises so the skill is self-contained.

Add explicit validation/feedback checkpoints for the analysis steps (e.g., verify IMGT/AlphaFold results returned valid hits before proceeding, re-check CDR preservation after backmutations) to satisfy the batch/analysis feedback-loop expectation.

De-duplicate tool references (Phase 0 table, per-phase mentions, and the closing Tool Reference section overlap) to tighten the token footprint.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-oriented with little explanation of basics Claude already knows, but it carries repetition (tool names restated across Phase 0, per-phase 'See WORKFLOW_DETAILS.md', and the Tool Reference section) that could be trimmed.	4 / 5
Actionability	Phases give concrete specifics (positions, ddG < -0.5 cutoffs, `scripts/developability.py --seq`), but executable code examples are deferred to files (WORKFLOW_DETAILS.md) that are not present in the bundle, leaving mostly descriptive rather than copy-paste-ready guidance; the one real script does match its described use.	3 / 5
Workflow Clarity	The 8-phase sequence is clearly laid out with an ASCII flowchart and per-phase outputs, and it warns against fabricating data, but there are no explicit validate->fix->retry feedback loops for the analysis steps despite batch/analysis operations.	3 / 5
Progressive Disclosure	Structure is well-designed on paper — overview body with a Reference Files table pointing one level deep — but 6 of the 7 referenced bundle files (QUICK_START.md, WORKFLOW_DETAILS.md, REPORT_TEMPLATE.md, MANUFACTURING.md, EXAMPLES.md, CHECKLISTS.md) are missing; only scripts/developability.py exists, so the signaled navigation is broken in practice.	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, specific description that clearly states both capabilities and explicit use-triggers within a well-defined antibody-engineering niche. Slight room to broaden plain-language trigger synonyms, but it avoids vagueness and over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — 'sequence humanization (germline alignment, framework retention), affinity maturation, developability (aggregation, stability, PTMs), structure modeling (AlphaFold/PDB CDR analysis), immunogenicity prediction, and manufacturing feasibility' — giving comprehensive, specific coverage rather than generic language.	5 / 5
Completeness	It explicitly answers 'what' (the capability list and 'lead-to-clinical-candidate' scope) and 'when' via a concrete 'Use for ...' trigger clause, matching the top anchor's pattern.	5 / 5
Trigger Term Quality	The 'Use for' clause surfaces natural terms like 'biologic-drug optimization, mAb design review, biosimilar engineering, and clinical-precedent comparison', but a few plain user phrasings (e.g. 'humanize antibody', 'antibody affinity') are absent, so it stops just short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	The therapeutic-antibody niche with mAb/biospecific triggers is clearly distinct and unlikely to fire for unrelated skills, with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-antibody-engineering/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.