bioimage-analysis

Microscopy image analysis for cell biology. Cell segmentation (Cellpose, watershed), object tracking (trackpy), morphology quantification, colony counting, colocalization analysis, and cytoskeleton characterization. For pathology WSI use pathml; for flow cytometry use flow-cytometry-analysis.

Quality

62%

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/bioimage-analysis/SKILL.md

Quality

Content

53%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 body is highly actionable with executable code for every capability and good internal section structure, but it inlines content that duplicates an unreferenced script bundle and lacks validation checkpoints in its batch workflow. Progressive disclosure is the weakest dimension because the existing scripts are never surfaced.

Suggestions

Replace the duplicated inline capability/workflow code with pointers to the bundled scripts, e.g. 'Ready-made implementation: see scripts/segment_cells.py', keeping only a concise Quick Start inline in SKILL.md.

Collapse the four 'Typical Workflows' or merge them into the matching Core Capabilities to remove the colony-counting and colocalization code that appears twice.

Add an explicit validation checkpoint to the batch workflow — e.g. segment and visually verify masks on one image before looping over all fields of view — so batch operations clear the workflow-clarity cap.

Dimension	Reasoning	Score
Conciseness	Prose is lean with no concept padding, but the four 'Typical Workflows' substantially duplicate the nine 'Core Capabilities' (colony counting, colocalization, and segmentation+quantification each appear twice), so the body could be meaningfully tightened rather than just 'minor' trimming.	3 / 5
Actionability	Overwhelmingly concrete, executable Python with real imports, parameters, and print statements across nine capabilities and four workflows, but a few blocks (tracking, mitochondrial, batch) reference pd/np/tifffile/skimage without importing them in-block, so they are not fully standalone copy-paste ready.	4 / 5
Workflow Clarity	Workflows are clearly sequenced (Load → Segment → Quantify → Print) but validation is only mentioned in Best Practices prose, not embedded as a checkpoint in the batch workflow (Core Capability 9 loops over images with no verify-before-batch step), so the batch cap at 3 applies.	3 / 5
Progressive Disclosure	Five ready-made, topically-matched scripts exist in ./scripts/ (segment_cells.py, track_cells.py, analyze_morphology.py, count_colonies.py, colocalization.py) yet the body never references or signals them, inlining ~400 lines of capability/workflow code that clearly belongs in those separate files.	2 / 5
	Total	12 / 20 Passed

Description

71%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.

The description is specific and well-differentiated, naming six concrete capabilities with tools and explicitly routing adjacent domains elsewhere. Its main weakness is the missing 'Use when...' trigger clause, which caps completeness at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases, e.g. 'Use when segmenting cells or nuclei, tracking objects in time-lapses, counting colonies, or quantifying colocalization from microscopy images.'

Include common synonyms and file extensions users would say — 'fluorescence or brightfield microscopy', 'time-lapse', '.tif/.tiff', '.czi' — to lift trigger-term coverage.

Convert the boundary routing ('For pathology WSI use pathml') into an affirmative trigger so the 'when' is stated positively, not only by exclusion.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools — 'Cell segmentation (Cellpose, watershed), object tracking (trackpy), morphology quantification, colony counting, colocalization analysis, and cytoskeleton characterization' — giving comprehensive coverage rather than just 'several' actions.	5 / 5
Completeness	The 'what' is clear and comprehensive, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the routing lines ('For pathology WSI use pathml') only say when NOT to use this skill, so the cap at 3 applies.	3 / 5
Trigger Term Quality	Strong domain-natural keywords ('cell segmentation', 'colony counting', 'colocalization', 'microscopy image analysis') that researchers actually say, but missing synonym/file-extension variations like 'time-lapse', 'fluorescence', '.tif', or '.czi' that the 5-anchor expects.	4 / 5
Distinctiveness Conflict Risk	A clear niche (microscopy for cell biology) with explicit routing away from adjacent domains minimizes conflict risk, but the absence of an affirmative 'use this when...' trigger leaves a small gap versus the 5-anchor which pairs the niche with an explicit trigger phrase.	4 / 5
	Total	16 / 20 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 (548 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/bioimage-analysis/SKILL.md
Commit: 3a6c3a9

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.