geniml

Use Geniml for audited local genomic-interval workflows: validate BED and universe contracts, plan Region2Vec or scEmbed runs, inspect model/tokenizer compatibility, and assess consensus universes.

Quality

83%

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

92%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 a strong, expert-calibrated skill: executable commands, a checkpointed safety and validation workflow, and a clean one-level reference structure. The only soft spot is mild verbosity in the version/migration notes, which keeps conciseness just short of the top band.

Dimension	Reasoning	Score
Conciseness	Dense, expert-oriented prose with pinned versions and minimal concept-explanation padding, but the 'Important 0.8.4 migration notes' and verified-release-snapshot sections carry time-sensitive detail that could be trimmed, so it sits just below the leanest anchor.	4 / 5
Actionability	Copy-paste-ready `uv pip install` and `python skills/geniml/scripts/...` commands plus executable Python imports with concrete module paths and arguments cover the common Region2Vec, scEmbed, validation, and inspection cases.	5 / 5
Workflow Clarity	A numbered 7-step safety gate, an explicit validation-before-analysis loop ('Run a bounded validation and normalization plan before analysis'), rejection lists, and checkpointed artifact inspection provide clear sequencing with validation feedback loops for the batch/destructive operations involved.	5 / 5
Progressive Disclosure	The overview body points one level deep to five real reference files (region2vec, scembed, bedspace, consensus_peaks, utilities), all clearly signaled in a References section, with bulk detail offloaded and planner/inspector scripts bundled separately — easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

75%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, distinctive, and names the right domain actions, but it omits an explicit 'Use when...' trigger clause, leaving the 'when' implicit and capping completeness. Adding a concrete trigger sentence would lift it to the top band.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user works with BED intervals, Region2Vec/scEmbed embeddings, consensus universe construction, or model/tokenizer compatibility checks.'

Add a few natural synonyms or file extensions (e.g. '.bed', 'genomic intervals', 'embedding models') to broaden trigger term coverage.

Lead with the 'what' as a capability list and follow with the 'when' condition so both are explicit and unambiguous.

Dimension	Reasoning	Score
Specificity	Lists four concrete actions in the domain — 'validate BED and universe contracts', 'plan Region2Vec or scEmbed runs', 'inspect model/tokenizer compatibility', and 'assess consensus universes' — giving comprehensive coverage of the skill's surface area.	5 / 5
Completeness	The description gives a clear 'what' but no explicit 'Use when...' trigger clause; the leading 'Use Geniml for...' states purpose rather than a use condition, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms ('BED', 'universe', 'Region2Vec', 'scEmbed', 'consensus universes'), but lacks common synonyms and file extensions that would push it to the top anchor.	4 / 5
Distinctiveness Conflict Risk	A highly specific niche — audited local genomic-interval ML workflows with named methods Region2Vec/scEmbed and BED/universe contracts — gives minimal overlap with other skills.	5 / 5
	Total	17 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/geniml/SKILL.md
Commit: b2a92ba

Reviewed: 3 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.