CtrlK
BlogDocsLog inGet started
Tessl Logo

latchbio-integration

Build, register, debug, and operate bioinformatics workflows on Latch using the Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, and Latch MCP. Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and monitoring runs.

75

Quality

92%

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

SKILL.md
Quality
Evals
Security

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.

A well-architected skill body: a concise overview routing to verified reference files, executable code and commands, and a sequenced lifecycle with validation checkpoints and operational safeguards. Only minor conciseness trims would push it to the top anchor across every dimension.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (no "what is a workflow" padding), with lean code blocks, but a few explanatory sentences in the lifecycle and baseline sections could be trimmed, keeping it just below the lean anchor-5 example.

4 / 5

Actionability

It provides copy-paste-ready commands and code throughout (uv install, latch register/develop flags, a complete minimal workflow, the inspect script invocation) covering the common cases, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The seven-step Recommended Development Lifecycle is clearly sequenced with explicit validation checkpoints (staging validation, re-run after Dockerfile changes, launch only after cost review, monitor and verify), and Operational Safety adds safeguards for destructive/batch operations.

5 / 5

Progressive Disclosure

The routing table maps each need to one of nine reference files plus the inspect script, all of which exist on disk, with a one-level-deep, clearly signaled overview structure that matches the anchor example.

5 / 5

Total

19

/

20

Passed

Description

92%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.

A strong, third-person description that pairs a comprehensive list of concrete actions with an explicit "Use when..." trigger clause. Trigger-term coverage is good but could add a few more natural synonyms to reach the top anchor.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions ("Build, register, debug, and operate") across an enumerated set of technologies (Python SDK, CLI, Latch Data and Registry, Nextflow, Snakemake, programmatic execution, Latch MCP), matching the comprehensive-coverage anchor.

5 / 5

Completeness

It explicitly answers both "what" (build/register/debug/operate workflows with named tools) and "when" (a concrete "Use when..." clause with several trigger situations), matching the anchor that requires both with concrete trigger phrases.

5 / 5

Trigger Term Quality

The "Use when authoring or deploying Latch workflows, configuring resources or interfaces, moving data, integrating Registry, or launching and monitoring runs" clause provides good natural trigger phrases, but it stops short of comprehensive synonym/extension coverage typical of the anchor-5 example.

4 / 5

Distinctiveness Conflict Risk

The Latch-specific niche and named subsystems (Latch Data, Registry, Latch MCP) make it clearly distinguishable with minimal conflict risk against other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
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.