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

70%

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

72%Weight 40%Scale 1-3

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 and well-structured one-level-deep references, but it is somewhat padded with capability restatements and lacks explicit validation checkpoints in its write/index/subset workflows.

Suggestions

Trim the repeated capability bullet lists under each 'Core Capabilities' section, since the same operations are already shown in code and referenced docs.

Add explicit validation steps to destructive/batch workflows (e.g. verify the .bai/.csi index exists after pysam.index(), or check record counts before writing a subsetted VCF).

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable examples, but the 'Common operations' bullet lists and 'When to Use This Skill' section partially restate capabilities Claude already knows and could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready Python for reading BAM, VCF, and FASTA, plus concrete samtools/bcftools command examples and explicit file-mode and indexing recipes.	3 / 3
Workflow Clarity	Multi-step workflows are outlined and pitfalls listed, but there are no explicit validation checkpoints for risky batch operations like writing/indexing BAM or subsetting VCFs, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview with clearly signaled, one-level-deep references (alignment_files.md, variant_files.md, sequence_files.md, common_workflows.md), all of which exist in ./references/, with a 'Getting Help' navigation map.	3 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 niched to genomics file I/O, but it omits an explicit 'Use when...' trigger clause, capping its completeness, and its trigger terms are more technical-format than natural-user phrasing.

Suggestions

Add an explicit 'Use when...' clause naming the user situations that should trigger this skill (e.g. 'Use when working with BAM/VCF/FASTA files, calculating sequencing coverage, or building NGS analysis pipelines').

Broaden trigger terms to include natural user phrasings like 'alignment files', 'sequencing reads', 'genomic variants', and 'gene regions' alongside the format acronyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ sequences, extract regions, calculate coverage' — matching the multi-action anchor.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes recognizable domain terms (BAM, VCF, FASTA, coverage) but lacks conversational phrasings a user would naturally say (e.g. 'alignment files', 'sequencing reads', 'gene regions'); the trailing 'NGS data processing pipelines' is jargon-leaning.	2 / 3
Distinctiveness Conflict Risk	The genomic-file niche is narrow and well-scoped (htslib-backed alignment/variant/sequence formats), making it unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: dc00e07

Reviewed: 8 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.