CtrlK
BlogDocsLog inGet started
Tessl Logo

latchbio-integration

Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir, Nextflow/Snakemake integration.

54

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/biology/latchbio-integration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured with strong progressive disclosure and real reference files, but code examples are not fully executable and the deployment workflow lacks validation checkpoints. Tightening redundant reference summaries and making code examples runnable would improve actionability and workflow clarity.

Suggestions

Make code examples executable by defining the returned variables (e.g., actually assign qc_output, bam_output, output_file) or mark them clearly as illustrative placeholders.

Add an explicit validation/feedback step to the Quick Start deployment sequence (e.g., verify registration succeeded with a check command, and what to do on failure) rather than relegating troubleshooting to a separate section.

Collapse the duplicated 'Read this for' and 'Key topics' lists for each reference into a single concise pointer to reduce token overhead.

DimensionReasoningScore

Conciseness

Bullet lists are efficient, but the 'Read this for' plus 'Key topics' double lists per reference are redundant, and overview prose re-explains what Latch is — could be tightened.

2 / 3

Actionability

CLI commands (latch init/register/login) are concrete and copy-paste ready, but the code examples return undefined variables like 'return output_file', 'return qc_output', and 'return bam_output', so they are not executable as written.

2 / 3

Workflow Clarity

Quick Start gives an install→login→init→register sequence, but there are no validation checkpoints or feedback loops for the registration/deploy batch operation; troubleshooting is siloed at the end rather than inline, capping this at 2.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview pointing to four well-signaled, one-level-deep reference files (all present on disk, no further nesting), with content appropriately split for easy navigation.

3 / 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 clearly distinguishable, but it omits an explicit 'Use when...' trigger clause and leans on some technical jargon over natural user phrasing. Adding explicit trigger guidance and broader natural-language keywords would raise completeness and trigger-term quality.

Suggestions

Append an explicit 'Use when...' clause naming natural triggers (e.g., 'Use when deploying bioinformatics pipelines to Latch, converting Nextflow/Snakemake workflows, or running RNA-seq/AlphaFold on Latch').

Replace some technical jargon ('@workflow/@task decorators', 'LatchFile/LatchDir') with user-facing phrasings or pair them with natural terms users would actually say.

Add common task variations like 'RNA-seq', 'differential expression', and 'protein structure prediction' to broaden trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build pipelines with Latch SDK', 'deploy serverless workflows', 'Nextflow/Snakemake integration' — rather than vague language, matching the top anchor.

3 / 3

Completeness

It states what the skill does but lacks any explicit 'Use when...' trigger clause, so completeness is capped at 2 per the rubric guideline.

2 / 3

Trigger Term Quality

'bioinformatics workflows', 'pipelines', and 'Nextflow/Snakemake' are natural, but '@workflow/@task decorators' and 'LatchFile/LatchDir' are technical jargon and common variations like 'RNA-seq' or 'deploy to Latch' are missing.

2 / 3

Distinctiveness Conflict Risk

'Latch platform for bioinformatics workflows' carves out a clear niche with distinct triggers unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
synthetic-sciences/openscience
Reviewed

Table of Contents

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.