一键导入
sequence-basic-analysis
Analyze DNA/RNA/protein sequences and optionally probe UniProt for homology. Use when user provides FASTA format or raw sequence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Analyze DNA/RNA/protein sequences and optionally probe UniProt for homology. Use when user provides FASTA format or raw sequence.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | sequence_basic_analysis |
| description | Analyze DNA/RNA/protein sequences and optionally probe UniProt for homology. Use when user provides FASTA format or raw sequence. |
| category | sequence |
| safety_level | safe |
| tools_used | ["sequence.analyze","uniprot.search"] |
Analyze biological sequence: $ARGUMENTS
Returns structured analysis:
annotation: Sequence metadata (kind, type, length)confidence: 0.7-0.85 depending on typesequence_stats: Detailed statistics per recorduniprot_hint: Optional homology probe results (protein ≥25aa)Call sequence.analyze tool (local BioPython):
from open_rosalind.skills_v2.sequence import tools
stats = tools.analyze(sequence)
# Returns: {records: [{type, length, gc_content, translation, ...}], n_records}
For each record:
If primary sequence is protein and length ≥25aa:
uniprot.search with probeuniprot_hintprobe = primary_sequence[:30]
result = uniprot_search(query=probe)
uniprot_hint = {
"hits": len(result["hits"]),
"top_match": result["hits"][0]["accession"],
"probe_length": 30
}
Construct response following Open-Rosalind principles:
annotation: Structured metadata (no free-form text)confidence: Rule-based score (0.85 for DNA/RNA, 0.7 for protein)notes: Fallback messages (e.g., "UniProt probe: 3 hits")sequence_stats: Full tool output (evidence)uniprot_hint: Probe results (evidence)Input:
{"sequence": "ATGGCCAAATTAA"}
Output:
{
"annotation": {"kind": "sequence", "primary_type": "dna", "length": 13},
"confidence": 0.85,
"sequence_stats": {
"records": [{
"type": "dna",
"length": 13,
"gc_content": 30.77,
"translation": "MAKL*",
"reverse_complement": "TTAATTTGGCCAT"
}]
}
}
Input:
{"sequence": "MVKVGVNGFGRIGRLVTRA"}
Output:
{
"annotation": {"kind": "sequence", "primary_type": "protein", "length": 19},
"confidence": 0.7,
"notes": ["UniProt probe: 3 hits"],
"sequence_stats": {
"records": [{
"type": "protein",
"length": 19,
"molecular_weight": 1.95
}]
},
"uniprot_hint": {
"hits": 3,
"top_match": "Q9H3P7",
"probe_length": 19
}
}
Following Open-Rosalind core principles:
sequence.analyze and uniprot.search toolssequence_stats and uniprot_hint are raw tool outputsnotes)> headers)Route non-tool questions to the language model with explicit no-tool labeling.
Analyze mutations by comparing wild-type and mutant sequences. Use this skill when: (1) User provides WT and MT sequences, (2) User asks about mutation impact (e.g., "p.R175H"), (3) User wants to compare two sequences, (4) User asks "what's the difference between these sequences".
Search PubMed for biomedical research papers by topic, disease, or gene. Use this skill when: (1) User asks to find papers about a topic, (2) User wants recent literature on a disease or gene, (3) User needs citations for research, (4) User asks "papers about X" or "literature on Y".
Query UniProt database for protein information including function, organism, sequence, and structure. Use this skill when: (1) User provides a UniProt accession (e.g., P38398, Q9H3P7), (2) User asks about a protein by name (e.g., "BRCA1", "hemoglobin"), (3) User wants protein function, organism, or sequence information, (4) User needs to find similar proteins by sequence search.