pysam

Genomic file toolkit. Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage, for NGS data processing pipelines.

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/pysam/SKILL.md

Quality

Content

70%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.

Highly actionable with excellent progressive disclosure and confirmed reference files, but it over-explains general concepts Claude already knows and lacks explicit validation checkpoints for batch/file-writing workflows.

Suggestions

Trim general-knowledge exposition in 'Key Concepts', 'Performance Considerations', and 'Common Pitfalls' to the pysam-specific gotchas only.

Add explicit validation checkpoints before/after batch or write operations (e.g. verify index presence before fetch, confirm written BAM with a quick count or index step).

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable snippets and bullet lists, but sections like 'Key Concepts', 'Common Pitfalls', and 'Performance Considerations' restate general library/coordinate knowledge Claude largely already knows, and could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready examples for reading BAM, VCF, and FASTA, plus concrete command-line samtools/bcftools invocations and error handling covering common cases.	5 / 5
Workflow Clarity	Operations are grouped into numbered capability sections with concrete steps, but this is a multi-step batch/file-processing skill with no explicit validation or verification checkpoints (e.g. confirming an index exists before fetch, verifying output after writing), which caps workflow clarity at 3 per the destructive/batch guidance.	3 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled, one-level-deep references to real files (alignment_files.md, variant_files.md, sequence_files.md, common_workflows.md), each summarized inline and reinforced by a 'Getting Help' routing section; all referenced files exist in references/.	5 / 5
	Total	16 / 20 Passed

Description

63%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 specific, format-rich description that clearly carves out a distinct genomic-file niche, but it omits an explicit 'Use when...' trigger clause, which caps its completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when working with BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, or NGS pipelines.'

Consider separating the format list from the action list so both 'what it does' and 'when to use it' are unmistakable.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage') but each is terse and some sub-formats are bundled, leaving minor coverage gaps compared to a fully comprehensive listing.	4 / 5
Completeness	The description clearly answers 'what' with concrete actions, but there is no explicit 'Use when...' / 'when should Claude use it' trigger clause; the trailing 'for NGS data processing pipelines' is a weak purpose hint rather than explicit when-guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Strong natural terms users say ('SAM/BAM/CRAM', 'VCF/BCF', 'FASTA/FASTQ', 'coverage', 'NGS data processing pipelines') with file extensions included, though a few common synonyms like 'alignment' phrasings and 'sequencing reads' are lightly covered.	4 / 5
Distinctiveness Conflict Risk	Clear genomic/NGS niche with distinct file-format triggers (SAM/BAM/CRAM, VCF/BCF, FASTA/FASTQ) that are unlikely to overlap with non-biology skills, giving minimal conflict risk.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: backend/cli/skills/biology/pysam/SKILL.md
Commit: a820c2f

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.