immunology-assays

Computational analysis of immunology experimental data. ATAC-seq differential accessibility, immune cell tracking from microscopy, ELISA data processing with 4-parameter logistic fitting, immunohistochemistry quantification, antibody titer analysis, and cell cycle phase duration estimation. For flow cytometry use flow-cytometry-analysis; for scRNA-seq use scanpy.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/immunology-assays/SKILL.md

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 body is highly actionable with executable, well-exemplified code, but it is verbose and monolithic: full implementations are inlined despite a scripts/ bundle that goes unreferenced, and workflows lack explicit validation checkpoints for batch operations.

Suggestions

Move the full per-capability implementations into the existing scripts/ files and replace inline code in SKILL.md with concise signatures plus clearly signaled links (e.g., 'See scripts/process_elisa.py for the full 4PL pipeline').

Add explicit validation checkpoints to the batch workflows (e.g., verify 4PL R-squared and in-range samples before reporting; check ATAC-seq mitochondrial read fraction and peak counts before downstream analysis), with a fix-and-retry loop.

De-duplicate the 4PL definition (Quick Start vs. section 2) and trim print-debugging from the worked examples to reduce token load.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the body is ~580 lines of inline implementations with full docstrings and print debugging, and duplicates the 4PL definition (Quick Start and section 2) that could live in the existing scripts/ bundle; some tightening possible.	2 / 3
Actionability	Provides fully executable Python functions with typed args, realistic worked example data (ELISA standards/unknowns, dilution series), and copy-paste-ready snippets, matching the 'fully executable code/commands' anchor.	3 / 3
Workflow Clarity	'Typical Workflows' exist and Troubleshooting gives error-recovery hints, but for batch/processing-heavy tasks (ATAC-seq, multiplex cytokine processing) there are no explicit validation checkpoints or validate->fix->retry feedback loops, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Monolithic body inlines all seven capabilities as full code blocks, while a scripts/ bundle (process_elisa.py, atac_peaks.py, quantify_ihc.py, track_immune_cells.py, antibody_titer.py) exists but is never referenced; content that should be split and signaled is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 and well-differentiated with strong capability enumeration and good routing to adjacent skills, but it omits a positive 'Use when...' trigger clause and leans on a broad 'immunology experimental data' framing rather than crisp natural triggers.

Suggestions

Add an explicit 'Use when...' clause listing natural user triggers (e.g., 'Use when processing ELISA plate data, quantifying IHC staining, analyzing ATAC-seq accessibility, or tracking immune cells from microscopy').

Surface more natural trigger variations a user would actually say (e.g., 'H-score', '4PL standard curve', 'Luminex/MSD cytokine data', 'pulse-chase cell cycle labeling') in the description.

Lead with the actionable trigger framing rather than the generic 'Computational analysis of immunology experimental data' opener.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('ATAC-seq differential accessibility', 'ELISA data processing with 4-parameter logistic fitting', 'immunohistochemistry quantification', 'antibody titer analysis', 'cell cycle phase duration estimation'), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers 'what' thoroughly with an explicit capability list, but lacks a positive 'Use when...' clause; the only trigger-like phrases are negative routing ('For flow cytometry use...'), which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Contains strong domain keywords (ATAC-seq, ELISA, immunohistochemistry, antibody titer) but the primary trigger 'immunology experimental data' is broad, and common natural variations for the sub-tasks are not exhaustively covered.	2 / 3
Distinctiveness Conflict Risk	Clear niche (immunology assays) with explicit routing to flow-cytometry-analysis and scanpy to prevent overlap, third-person voice, and unlikely-to-conflict triggers.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (592 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/immunology-assays/SKILL.md
Commit: dc00e07

Reviewed: 6 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.