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

90%

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

80%

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-organized and scientifically concrete with explicit thresholds and a real helper script, but it is somewhat verbose, defers most executable code to references, lacks per-phase validation feedback loops, and crucially references six detail files that do not exist in the bundle.

Suggestions

Ship the six referenced files (QUICK_START.md, WORKFLOW_DETAILS.md, REPORT_TEMPLATE.md, MANUFACTURING.md, EXAMPLES.md, CHECKLISTS.md) or remove the dangling references and inline the essential content, since broken links undermine navigation.

Add explicit validate->fix->retry checkpoints for batch/output operations (e.g., after report generation and sequence optimization, verify outputs before proceeding to the next phase).

Tighten the body by deduplicating the tool tables (the Phase 0 required-tools table overlaps the Tool Reference section) and trimming the repeated 'See WORKFLOW_DETAILS.md Phase X' boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes domain competence with no concept padding, but ~320 lines with repeated Goal/Key steps/Output/See-reference boilerplate and overlapping tool tables (Phase 0 required-tools table vs. the full Tool Reference section) could be tightened.	2 / 3
Actionability	Inline specifics are concrete (CDR positions 27-38, 4.5 A cutoff, ddG < -0.5 kcal/mol, PTM motifs, real `scripts/developability.py --seq` CLI), but most runnable code per phase is deferred to WORKFLOW_DETAILS.md rather than provided copy-paste-ready in the body, leaving guidance partly incomplete.	2 / 3
Workflow Clarity	The 8-phase pipeline is clearly sequenced with an ASCII diagram and per-phase Goal/Output, plus tool verification and report-first mandates, but there is no explicit validate->fix->retry feedback loop per phase for this batch/output-generating workflow, capping it at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	The body is structured as an overview with well-signaled, one-level-deep references (QUICK_START, WORKFLOW_DETAILS, REPORT_TEMPLATE, MANUFACTURING, EXAMPLES, CHECKLISTS), but a filesystem check shows only scripts/developability.py exists and none of the six referenced .md files are present, so the actual bundle navigation is broken.	2 / 3
	Total	8 / 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 across all dimensions: it lists concrete capabilities, includes explicit 'Use for' triggers, and occupies a clearly distinct niche. Third-person voice is preserved throughout, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities (sequence humanization with germline alignment/framework retention, affinity maturation, developability covering aggregation/stability/PTMs, AlphaFold/PDB CDR analysis, immunogenicity prediction, manufacturing feasibility), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly states both what the skill does (the capability list) and when to use it via an explicit 'Use for ...' trigger clause, satisfying the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	The 'Use for biologic-drug optimization, mAb design review, biosimilar engineering, and clinical-precedent comparison' clause plus 'lead-to-clinical-candidate' gives good coverage of natural terms practitioners would actually say.	3 / 3
Distinctiveness Conflict Risk	The therapeutic antibody engineering niche with domain-specific triggers (mAb, biosimilar, humanization, affinity maturation) is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 089eb8e

Reviewed: about 8 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.