CtrlK
BlogDocsLog inGet started
Tessl Logo

synthetic-biology

Synthetic biology design and simulation tools. Codon optimization, gene circuit ODE modeling with growth feedback, SBML model creation, bifurcation analysis, barcode sequencing fitness analysis, and therapeutic genome engineering. For metabolic modeling use cobrapy; for sequence tools use biopython.

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/synthetic-biology/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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.

The body is highly actionable, executable Python across all six advertised capabilities with a useful troubleshooting section, but it functions as a monolithic document: it duplicates its own examples, inlines a full codon-usage data table, and — most seriously — never mentions the four ready-made CLI scripts sitting in scripts/, leaving the bundle's most powerful assets undiscoverable. Restructuring around the existing scripts with brief inline examples would resolve both the conciseness and progressive-disclosure weaknesses.

Suggestions

Reference the bundle scripts explicitly (e.g. 'Full CLI implementations: scripts/gene_circuit.py, scripts/codon_optimize.py, scripts/sbml_model.py, scripts/bifurcation.py — run with --help for options') and replace the long inline reimplementations with one short example plus the pointer.

Move the 24-line E. coli codon usage table into a reference file (e.g. references/codon_tables.md) and keep only the CAI/optimization functions inline, removing the duplicated toggle-switch and SBML examples between Quick Start, Core Capabilities, and Typical Workflows.

Turn 'Typical Workflows' into explicit ordered steps with validation checkpoints (e.g. SBML: build model → check doc.getNumErrors() → only write the file when clean), and fix the actionability gaps: import pandas in sensitivity_analysis, drop placeholder promoter/terminator sequences, and correct the 'Original CAI' label in Workflow 1.

DimensionReasoningScore

Conciseness

The body is mostly lean — it favors code over explanation and skips basic concept lectures — but it is noticeably redundant and could be tightened: the toggle-switch ODE model appears in both Quick Start and Workflow 2, SBML examples appear in both section 3 and Workflow 3, and the full 24-line E. coli codon table is inlined as data. It fits anchor 3 ('mostly efficient but... could be tightened') rather than 2 because the padding is duplication, not explanation of concepts Claude already knows.

3 / 5

Actionability

Nearly all guidance is complete, runnable Python with real parameter values, matching 'mostly executable guidance; concrete code or commands with minor gaps'. It is not a 5 due to concrete defects: sensitivity_analysis calls pd.DataFrame without importing pandas in that block, the genome-engineering cassette uses placeholder sequences (promoter 'A'*100), Workflow 1 mislabels optimized CAI as 'Original CAI', and Workflow 2 depends on toggle_switch being defined in an earlier section.

4 / 5

Workflow Clarity

Section structure implies a loose sequence (capabilities, then per-task workflows, then troubleshooting), and some validation exists (doc.getNumErrors() after SBML creation, stiff-solver fallback for ODE failures), but the 'Typical Workflows' are isolated snippets with no ordered steps or explicit checkpoints — no validate-then-proceed pattern anywhere. This matches anchor 3 ('steps listed but validation gaps... checkpoints missing or implicit') and does not reach 4's 'clear sequence with most checkpoints present'.

3 / 5

Progressive Disclosure

The bundle ships four substantial scripts (bifurcation.py, codon_optimize.py, gene_circuit.py, sbml_model.py — ~2,200 lines) that are never referenced anywhere in the body; the SKILL.md instead inlines ~450 lines of its own parallel implementations. This matches anchor 2 ('content that clearly belongs in separate files is inlined; or references are buried') — here the bundle content is not even buried, it is orphaned. The body's own header structure is reasonable, which keeps it from being worse, but zero navigation to the provided files is a deeper organization failure than anchor 3's 'references present but not clearly signaled'.

2 / 5

Total

12

/

20

Passed

Description

71%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, well-scoped description with good trigger vocabulary and thoughtful deconfliction against neighboring bioinformatics skills, but it lacks any explicit 'Use when...' trigger clause, which caps completeness and leaves activation guidance implicit. Adding an explicit usage clause and a few natural synonyms would lift it to the top band.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions codon optimization, gene circuits (toggle switches, repressilators), SBML models, bistability, or barcode fitness analysis.'

Include common natural synonyms such as 'toggle switch', 'repressilator', 'codon usage', and 'plasmid design' so the description matches how users actually phrase these requests.

Extend the boundary guidance to also disambiguate the molecular-cloning skill referenced in the body, so sequence-editing requests route correctly.

DimensionReasoningScore

Specificity

The description enumerates six concrete, distinct capabilities — 'Codon optimization', 'gene circuit ODE modeling with growth feedback', 'SBML model creation', 'bifurcation analysis', 'barcode sequencing fitness analysis', and 'therapeutic genome engineering' — matching the anchor for multiple specific concrete actions with comprehensive coverage, and mirroring exactly what the body delivers. It is not merely above anchor 4 ('several specific actions; minor gaps') because every major body capability is named; nothing is vague or padded.

5 / 5

Completeness

The 'what' is explicit and concrete, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the third sentence ('For metabolic modeling use cobrapy; for sequence tools use biopython') is boundary/delegation guidance, not when-to-use-this triggers. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3, which fits the anchor 'Has a clear what but when is missing or only weakly implied'.

3 / 5

Trigger Term Quality

Strong domain-natural terms users would say: 'codon optimization', 'gene circuit', 'ODE modeling', 'SBML', 'bifurcation analysis', 'barcode sequencing', 'genome engineering'. It falls short of anchor 5 because common variations are absent — e.g. 'toggle switch', 'repressilator', 'codon usage', 'plasmid', 'gene design' — and no file extensions or synonyms are offered.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (synthetic-biology design/simulation) and actively disambiguates from adjacent skills by name ('use cobrapy', 'use biopython'), which is strong boundary behavior. It is not a 5 because 'therapeutic genome engineering' and general sequence work still overlap with plausible cloning/genome-editing skills, and only two neighbor tools are disambiguated (e.g. molecular-cloning, referenced in the body, is not mentioned).

4 / 5

Total

16

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (571 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
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.