molecular-cloning

Molecular cloning simulation and design. PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation. For protein-level sequence analysis use biopython or esm; for database lookups use gene-database or ensembl-database.

Quality

73%

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/molecular-cloning/SKILL.md

Quality

Content

65%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.

Highly actionable executable code with good section organization and useful troubleshooting, but it is token-heavy and fails to leverage the provided bundle scripts, inlining implementations that should be referenced. Workflow checkpoints are implicit rather than explicit.

Suggestions

Replace the inline implementations with concise summaries that point to the existing bundle scripts (e.g. 'See scripts/simulate_pcr.py — run: python scripts/simulate_pcr.py --template …'), cutting hundreds of lines.

Add explicit validation checkpoints to the workflows (e.g. after Golden Gate design: 'verify overhangs unique and non-palindromic before ordering primers; re-run if violations') to form validate→fix→retry loops.

Tighten redundant sections — the Quick Start and Typical Workflows overlap with the Core Capabilities examples — to recover context budget.

Dimension	Reasoning	Score
Conciseness	The body is ~660 lines with seven full inline Python implementations, much of which duplicates the bundled scripts in ./scripts/, so it could be tightened substantially; it avoids score 1 because it does not explain basic concepts Claude already knows — the verbosity is domain code, not fluff.	2 / 3
Actionability	Code is fully executable and copy-paste ready using real Biopython (Bio.Restriction, SeqUtils.MeltingTemp) and primer3-py APIs with concrete examples, matching the score-3 anchor for specific executable guidance rather than pseudocode.	3 / 3
Workflow Clarity	Three 'Typical Workflows' are sequenced with concrete code and a Troubleshooting section offers error-recovery pairs, but there are no explicit validate→fix→retry checkpoints or checklists for the design operations, so it sits at score 2 rather than 3.	2 / 3
Progressive Disclosure	Sections are well organized, but ~500 lines of full implementations are inlined while five real bundle scripts exist in ./scripts/ (simulate_pcr.py, design_crispr.py, design_primers.py, golden_gate.py, restriction_digest.py) and are never referenced from the body — the classic score-2 pattern of content that should be separate being inline with bundle references not signaled.	2 / 3
	Total	9 / 12 Passed

Description

82%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.

A specific, well-scoped description with strong natural trigger terms and good distinctiveness via negative guidance. Its main gap is the absence of an explicit 'Use when…' trigger clause, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when simulating or designing molecular cloning workflows — PCR, digests, Golden Gate/Gibson assembly, primer or sgRNA design, or plasmid annotation.'

Consider adding common user phrasings ('restriction digest', 'assembly planning', 'plasmid map') to broaden trigger coverage beyond the current capability nouns.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'PCR amplicon prediction, restriction enzyme digestion, Golden Gate and Gibson assembly simulation, primer design, CRISPR sgRNA design, and plasmid annotation' — matching the score-3 anchor for several specific concrete actions rather than the partial score-2 set.	3 / 3
Completeness	It clearly answers 'what' via the capability list but has no 'Use when…' trigger clause — only negative guidance ('For protein-level… use biopython or esm; for database lookups use gene-database or ensembl-database') — so per the rubric a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Uses natural domain terms a user would actually say ('primer design', 'CRISPR sgRNA', 'Golden Gate', 'Gibson assembly', 'plasmid annotation'), giving good coverage; it is above score 2 because these are the common variations users voice, not generic jargon.	3 / 3
Distinctiveness Conflict Risk	The explicit redirection to biopython/esm and gene-database/ensembl-database carves out a clear molecular-cloning niche and actively reduces conflict with adjacent skills, matching the score-3 anchor for a distinct niche unlikely to trigger the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (666 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/molecular-cloning/SKILL.md
Commit: dc00e07

Reviewed: 11 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.