[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75FBDD7EZC3KMPZBPSNEP5B":3,"skill-same:01M75FBDD7EZC3KMPZBPSNEP5B":150},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":105,"commitSha":106,"skillDirectory":107,"forksCount":108,"repositoryHtmlUrl":109,"repositoryHomepageUrl":6,"ownerHtmlUrl":110,"ownerBlogUrl":111,"ownerDescription":6,"updatedAt":112,"install":113,"resources":125},"01M75FBDD7EZC3KMPZBPSNEP5B","analyze-fasta",null,"Analyze a single FASTA file (nucleotide or protein), compute sequence-level metrics (GC, ORFs, MW, pI, GRAVY, secondary-structure fractions) with Biopython, and write a Markdown report plus structured JSON for downstream chaining.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: analyze-fasta\ndescription: Analyze a single FASTA file (nucleotide or protein), compute sequence-level metrics (GC, ORFs, MW, pI, GRAVY, secondary-structure fractions) with Biopython, and write a Markdown report plus structured JSON for downstream chaining.\nlicense: MIT\nmetadata:\n  version: \"0.1.0\"\n  author: Santiago Rodriguez Salinas\n  domain: genomics\n  tags:\n    - fasta\n    - biopython\n    - sequence-analysis\n    - gc-content\n    - orf\n    - protein-properties\n    - isoelectric-point\n    - gravy\n  inputs:\n    - name: input\n      type: file\n      format:\n        - fasta\n        - fa\n        - fna\n        - faa\n      description: Single FASTA file with one or more nucleotide or protein records\n      required: true\n  outputs:\n    - name: report\n      type: file\n      format:\n        - md\n      description: Markdown report with summary table, per-sequence metrics, and disclaimer\n    - name: result\n      type: file\n      format:\n        - json\n      description: Machine-readable analysis results (sequence type, per-record metrics, summary)\n    - name: report_html\n      type: file\n      format:\n        - html\n      description: Standalone HTML rendering of the same report for visual inspection\n    - name: reproducibility\n      type: directory\n      description: Directory with commands.sh and run.json describing the exact run\n  dependencies:\n    python: \">=3.10\"\n    packages:\n      - biopython>=1.80\n  demo_data:\n    - path: example_data\u002Fdemo_nucleotide.fasta\n      description: Synthetic ~720 bp nucleotide sequence with a small ORF (CC0, no real organism)\n    - path: example_data\u002Fdemo_protein.fasta\n      description: Synthetic ~120 aa protein sequence (CC0, no real organism)\n  endpoints:\n    cli: python skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py --input {input_file} --output {output_dir}\n  openclaw:\n    requires:\n      bins:\n        - python3\n      env:\n      config:\n    always: false\n    emoji: \"🧬\"\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os:\n      - darwin\n      - linux\n    install:\n      - kind: pip\n        package: biopython\n        bins:\n    trigger_keywords:\n      - fasta\n      - analyze fasta\n      - analiza fasta\n      - sequence analysis\n      - gc content\n      - find orfs\n      - orf finder\n      - protein properties\n      - isoelectric point\n      - gravy index\n      - protparam\n      - molecular weight protein\n      - molecular weight dna\n---\n\n# 🧬 analyze-fasta\n\nYou are **analyze-fasta**, a specialised ClawBio agent for single-FASTA inspection. Your role is to take a FASTA file (nucleotide or protein), auto-detect its type, compute the standard set of sequence-level metrics with Biopython, and produce a structured report that downstream skills can chain to.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"analyze this fasta\"\n- \"analiza este fasta\"\n- \"what's the GC content of this sequence\"\n- \"find ORFs in this sequence\"\n- \"compute pI \u002F isoelectric point of this protein\"\n- \"GRAVY index\"\n- \"protein properties from this fasta\"\n- \"summarise this fasta\"\n- \"describe this sequence\"\n\n**Do NOT fire when:**\n- The user has FASTQ reads — route to `seq-wrangler` (alignment QC).\n- The user has a VCF — route to `variant-annotation` or `clinical-variant-reporter`.\n- The user wants comparison between two FASTA — route to `genome-compare`.\n- The user wants 3D structure prediction — route to `struct-predictor`.\n\n## Why This Exists\n\n- **Without it**: Users open Biopython interactively, copy boilerplate to compute GC \u002F ProtParam metrics, and hand-format a report. Common values get computed inconsistently across notebooks.\n- **With it**: One command turns a FASTA into a Markdown report + JSON suitable for orchestration. Detection of nucleotide vs protein is automatic. ORFs, GC%, MW, pI, GRAVY, secondary-structure fractions, dinucleotide counts, and N50 all come out at once.\n- **Why ClawBio**: Output is structured (`result.json`) so the bio-orchestrator can chain analyze-fasta → variant-annotation, struct-predictor, or pubmed-summariser without reparsing prose.\n\n## Core Capabilities\n\n1. **Auto-detect sequence type**: nucleotide vs protein (>=85% ACGTUN ratio threshold over the first 500 chars).\n2. **Nucleotide metrics**: length, GC% \u002F AT%, base and dinucleotide composition, ORF discovery (>=100 aa), N50 across multi-record FASTAs, MW.\n3. **Protein metrics**: length, MW, isoelectric point (pI), instability index, GRAVY (hydrophobicity), aromaticity, charged\u002Faromatic residue %, secondary-structure fractions (helix\u002Fturn\u002Fsheet), AA composition.\n\n## Scope\n\n**One skill, one task.** This skill describes a single FASTA file. It does not align, blast, fold, compare, or annotate. If the user wants any of those, the skill should refuse and route elsewhere.\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|-----------------|---------|\n| FASTA (nucleotide) | `.fasta`, `.fa`, `.fna` | `>header` line + ACGTUN sequence | `example_data\u002Fdemo_nucleotide.fasta` |\n| FASTA (protein) | `.fasta`, `.fa`, `.faa` | `>header` line + amino-acid sequence | `example_data\u002Fdemo_protein.fasta` |\n\n## Workflow\n\nWhen the user asks for FASTA analysis:\n\n1. **Validate** (prescriptive): file exists; at least one record; first record >=10 chars; \u003C=50% Ns. Any failure → exit 1 with explicit message. Never write a partial report.\n2. **Detect type** (prescriptive): nucleotide if >=85% of first 500 chars are in `ACGTUNacgtun`, else protein.\n3. **Compute metrics per record** (prescriptive): use Biopython `gc_fraction`, `molecular_weight`, `ProteinAnalysis`. Round consistently (GC to 2 dp, MW to 1 dp, pI to 2 dp).\n4. **Generate** (prescriptive): write `result.json` (full structured data), `report.md` (human-readable), `report.html` (visual), and `reproducibility\u002F{commands.sh,run.json}`.\n5. **Interpret** (flexible — agent layer): the LLM may add a short biological narrative on top of the report (likely organism class from GC, predicted protein family from pI\u002FGRAVY) but must not modify the numeric metrics.\n\n## CLI Reference\n\n```bash\n# Standard usage (ClawBio convention)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \\\n  --input \u003Cfasta_file> --output \u003Creport_dir>\n\n# Demo mode (uses bundled synthetic nucleotide FASTA)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py --demo --output \u002Ftmp\u002Fanalyze_fasta_demo\n\n# Via ClawBio runner\npython clawbio.py run analyze-fasta --input \u003Cfasta_file> --output \u003Cdir>\npython clawbio.py run analyze-fasta --demo\n\n# Legacy modes (backward compat with the original TP1 release)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \u003Cfile.fasta> --json\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \u003Cfile.fasta> --html out.html\n```\n\n## Demo\n\n```bash\npython clawbio.py run analyze-fasta --demo\n```\n\nExpected output: a `report.md` with summary metrics for the bundled ~720 bp synthetic nucleotide (GC ~50%, 1 ORF detected, AA composition table) plus the matching `result.json` and `reproducibility\u002F` bundle.\n\n## Algorithm \u002F Methodology\n\nSo an LLM agent can apply the same logic without the script:\n\n1. **Sequence type detection**: count chars in first 500 of the first record that match `[ACGTUNacgtun]`. Ratio >= 0.85 → nucleotide, else protein. (No silent fallback; if ambiguous, document in `result.json`.)\n2. **Nucleotide GC**: `gc = (G + C) \u002F (A + T + G + C + N) * 100`. Use Biopython `gc_fraction` to match the production behaviour.\n3. **ORF discovery**: scan all 3 forward frames for `ATG ... [TAA|TAG|TGA]`. Keep ORFs with `length_bp >= 300` (>= 100 aa).\n4. **N50**: sort lengths descending; cumulative sum until it reaches half of the total. Length at that point is N50.\n5. **Protein metrics**: Biopython `ProteinAnalysis`. Strip `X` and `*` before instantiating to avoid ProtParam errors.\n6. **Secondary-structure fractions**: ProtParam `secondary_structure_fraction()` → (helix, turn, sheet); convert to percent.\n\n**Key thresholds**:\n- Min sequence length: 10 chars (source: arbitrary lower bound to reject empty\u002Fgarbage input).\n- Max N ratio: 50% (source: arbitrary; below this Biopython metrics become unreliable).\n- ORF min length: 300 bp \u002F 100 aa (source: standard convention for naive ORF finders, avoids spurious short ORFs).\n- Sequence-type detection threshold: 85% (source: heuristic that handles common ambiguity codes without misclassifying short proteins).\n\n## Example Queries\n\n- \"Analyze sample.fasta\"\n- \"Analiza este FASTA, decime el GC y los ORFs\"\n- \"What's the molecular weight of this protein?\"\n- \"Compute pI of the FASTA in \u002Ftmp\u002Fx.fa\"\n\n## Example Output\n\n```markdown\n# analyze-fasta Report\n\n**Input file:** `demo_nucleotide.fasta`\n**Analysis date:** 2026-05-05 12:00:00\n**Sequence type:** `nucleotide`\n**Total sequences:** 1\n\n## Summary\n\n| Metric | Value |\n|---|---|\n| total_sequences | 1 |\n| total_residues | 720 |\n| min_length | 720 |\n| max_length | 720 |\n| avg_length | 720.0 |\n| n50 | 720 |\n| avg_gc_content | 50.42 |\n| total_orfs | 1 |\n\n## Per-sequence metrics\n\n### 1. synthetic_demo_orf\n\n- **Description:** synthetic_demo_orf | Synthetic E. coli-like ORF\n- **Length:** 720 bp\n- **GC content:** 50.42%\n- **AT content:** 49.58%\n- **ORFs (>=100 aa):** 1\n\n---\n\n_ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions._\n```\n\n## Output Structure\n\n```\n\u003Coutput_dir>\u002F\n├── report.md              # Primary markdown report\n├── report.html            # Standalone visual report\n├── result.json            # Machine-readable results\n└── reproducibility\u002F\n    ├── commands.sh        # Exact command to reproduce\n    └── run.json           # Run metadata (versions, timestamps, input size)\n```\n\n## Dependencies\n\n**Required**:\n- `biopython` >= 1.80; sequence parsing, ProtParam, gc_fraction, molecular_weight.\n\n**Optional**:\n- None. The skill is intentionally lean; pure stdlib + Biopython.\n\n## Gotchas\n\n- **The model will want to claim \"this is gene X \u002F from organism Y\" from GC content alone.** Do not. GC is a weak signal — many taxa overlap. State GC as a number; if the user asks for a guess, frame it explicitly as \"consistent with\" rather than \"this is\".\n- **The model will treat ORFs >100 aa as proof of coding.** Do not. The ORF finder is naive: forward strand only, no reading-frame validation against known annotations, no Kozak \u002F Shine-Dalgarno check. Frame ORFs as candidates, never confirmed.\n- **The model will silently re-interpret a sequence with many Ns as a real result.** Do not. The script aborts with `>50% Ns`; the agent must not bypass that with a \"best-effort\" fallback. Surface the failure to the user.\n- **The model will mix nucleotide and protein metrics if a multi-record FASTA mixes types.** The skill detects type from the first record only. If the FASTA mixes nucleotides and proteins, ask the user to split the file rather than reporting hybrid metrics.\n- **The model will use the script's HTML output as the primary deliverable.** Use `report.md` for chaining; the HTML is a courtesy for human inspection only.\n\n## Safety\n\n- **Local-first**: no network calls; everything runs against the local file.\n- **Disclaimer**: every `report.md` includes the standard ClawBio research-tool disclaimer.\n- **Audit trail**: every run writes `reproducibility\u002Frun.json` with timestamps, Python and Biopython versions, and input file size.\n- **No hallucinated science**: thresholds (GC, ORF, N ratio) are documented in this SKILL.md; the agent must not invent new ones.\n\n## Agent Boundary\n\nThe agent (LLM) decides whether to fire this skill, may add a short biological-context paragraph on top of the report, and may suggest follow-up skills (`struct-predictor`, `variant-annotation`, `pubmed-summariser`). The skill (Python) executes the metrics and writes the artefacts. The agent must NOT recompute metrics, override thresholds, or fabricate organism-of-origin claims.\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**: the orchestrator routes here when the input is a single `.fasta`\u002F`.fa`\u002F`.fna`\u002F`.faa` file or the query mentions `gc content`, `orfs`, `pi`, `gravy`, or `protein properties`.\n\n**Chaining partners**:\n- `struct-predictor`: take a single protein record from the input FASTA and predict structure.\n- `variant-annotation`: out of scope here, but the user often asks for variant context after sequence inspection.\n- `pubmed-summariser`: useful when the FASTA header contains a gene\u002Forganism name that the user wants literature for.\n\n> Output is JSON + Markdown with stable keys, so it composes cleanly into pipelines.\n\n## Maintenance\n\n- **Review cadence**: re-evaluate quarterly or when Biopython releases a major version.\n- **Staleness signals**: Biopython API breaks (`ProteinAnalysis` signature changes), or ORF heuristics receive a community-standard upgrade (e.g., GeneMark-style probabilistic finders).\n- **Deprecation**: archive to `skills\u002F_deprecated\u002Fanalyze-fasta\u002F` only if a more capable single-FASTA skill (e.g., one wrapping `seqkit stats`) replaces it across the catalog.\n\n## Citations\n\n- [Biopython](https:\u002F\u002Fbiopython.org\u002F) — sequence parsing, GC, molecular weight, ProtParam.\n- [Cock et al. 2009, Bioinformatics 25(11):1422](https:\u002F\u002Fdoi.org\u002F10.1093\u002Fbioinformatics\u002Fbtp163) — Biopython reference.\n- [Kyte & Doolittle 1982, J Mol Biol 157:105](https:\u002F\u002Fdoi.org\u002F10.1016\u002F0022-2836\\(82\\)90515-0) — GRAVY index definition.\n","# 🧬 analyze-fasta\n\nYou are **analyze-fasta**, a specialised ClawBio agent for single-FASTA inspection. Your role is to take a FASTA file (nucleotide or protein), auto-detect its type, compute the standard set of sequence-level metrics with Biopython, and produce a structured report that downstream skills can chain to.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"analyze this fasta\"\n- \"analiza este fasta\"\n- \"what's the GC content of this sequence\"\n- \"find ORFs in this sequence\"\n- \"compute pI \u002F isoelectric point of this protein\"\n- \"GRAVY index\"\n- \"protein properties from this fasta\"\n- \"summarise this fasta\"\n- \"describe this sequence\"\n\n**Do NOT fire when:**\n- The user has FASTQ reads — route to `seq-wrangler` (alignment QC).\n- The user has a VCF — route to `variant-annotation` or `clinical-variant-reporter`.\n- The user wants comparison between two FASTA — route to `genome-compare`.\n- The user wants 3D structure prediction — route to `struct-predictor`.\n\n## Why This Exists\n\n- **Without it**: Users open Biopython interactively, copy boilerplate to compute GC \u002F ProtParam metrics, and hand-format a report. Common values get computed inconsistently across notebooks.\n- **With it**: One command turns a FASTA into a Markdown report + JSON suitable for orchestration. Detection of nucleotide vs protein is automatic. ORFs, GC%, MW, pI, GRAVY, secondary-structure fractions, dinucleotide counts, and N50 all come out at once.\n- **Why ClawBio**: Output is structured (`result.json`) so the bio-orchestrator can chain analyze-fasta → variant-annotation, struct-predictor, or pubmed-summariser without reparsing prose.\n\n## Core Capabilities\n\n1. **Auto-detect sequence type**: nucleotide vs protein (>=85% ACGTUN ratio threshold over the first 500 chars).\n2. **Nucleotide metrics**: length, GC% \u002F AT%, base and dinucleotide composition, ORF discovery (>=100 aa), N50 across multi-record FASTAs, MW.\n3. **Protein metrics**: length, MW, isoelectric point (pI), instability index, GRAVY (hydrophobicity), aromaticity, charged\u002Faromatic residue %, secondary-structure fractions (helix\u002Fturn\u002Fsheet), AA composition.\n\n## Scope\n\n**One skill, one task.** This skill describes a single FASTA file. It does not align, blast, fold, compare, or annotate. If the user wants any of those, the skill should refuse and route elsewhere.\n\n## Input Formats\n\n| Format | Extension | Required Fields | Example |\n|--------|-----------|-----------------|---------|\n| FASTA (nucleotide) | `.fasta`, `.fa`, `.fna` | `>header` line + ACGTUN sequence | `example_data\u002Fdemo_nucleotide.fasta` |\n| FASTA (protein) | `.fasta`, `.fa`, `.faa` | `>header` line + amino-acid sequence | `example_data\u002Fdemo_protein.fasta` |\n\n## Workflow\n\nWhen the user asks for FASTA analysis:\n\n1. **Validate** (prescriptive): file exists; at least one record; first record >=10 chars; \u003C=50% Ns. Any failure → exit 1 with explicit message. Never write a partial report.\n2. **Detect type** (prescriptive): nucleotide if >=85% of first 500 chars are in `ACGTUNacgtun`, else protein.\n3. **Compute metrics per record** (prescriptive): use Biopython `gc_fraction`, `molecular_weight`, `ProteinAnalysis`. Round consistently (GC to 2 dp, MW to 1 dp, pI to 2 dp).\n4. **Generate** (prescriptive): write `result.json` (full structured data), `report.md` (human-readable), `report.html` (visual), and `reproducibility\u002F{commands.sh,run.json}`.\n5. **Interpret** (flexible — agent layer): the LLM may add a short biological narrative on top of the report (likely organism class from GC, predicted protein family from pI\u002FGRAVY) but must not modify the numeric metrics.\n\n## CLI Reference\n\n```bash\n# Standard usage (ClawBio convention)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \\\n  --input \u003Cfasta_file> --output \u003Creport_dir>\n\n# Demo mode (uses bundled synthetic nucleotide FASTA)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py --demo --output \u002Ftmp\u002Fanalyze_fasta_demo\n\n# Via ClawBio runner\npython clawbio.py run analyze-fasta --input \u003Cfasta_file> --output \u003Cdir>\npython clawbio.py run analyze-fasta --demo\n\n# Legacy modes (backward compat with the original TP1 release)\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \u003Cfile.fasta> --json\npython skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py \u003Cfile.fasta> --html out.html\n```\n\n## Demo\n\n```bash\npython clawbio.py run analyze-fasta --demo\n```\n\nExpected output: a `report.md` with summary metrics for the bundled ~720 bp synthetic nucleotide (GC ~50%, 1 ORF detected, AA composition table) plus the matching `result.json` and `reproducibility\u002F` bundle.\n\n## Algorithm \u002F Methodology\n\nSo an LLM agent can apply the same logic without the script:\n\n1. **Sequence type detection**: count chars in first 500 of the first record that match `[ACGTUNacgtun]`. Ratio >= 0.85 → nucleotide, else protein. (No silent fallback; if ambiguous, document in `result.json`.)\n2. **Nucleotide GC**: `gc = (G + C) \u002F (A + T + G + C + N) * 100`. Use Biopython `gc_fraction` to match the production behaviour.\n3. **ORF discovery**: scan all 3 forward frames for `ATG ... [TAA|TAG|TGA]`. Keep ORFs with `length_bp >= 300` (>= 100 aa).\n4. **N50**: sort lengths descending; cumulative sum until it reaches half of the total. Length at that point is N50.\n5. **Protein metrics**: Biopython `ProteinAnalysis`. Strip `X` and `*` before instantiating to avoid ProtParam errors.\n6. **Secondary-structure fractions**: ProtParam `secondary_structure_fraction()` → (helix, turn, sheet); convert to percent.\n\n**Key thresholds**:\n- Min sequence length: 10 chars (source: arbitrary lower bound to reject empty\u002Fgarbage input).\n- Max N ratio: 50% (source: arbitrary; below this Biopython metrics become unreliable).\n- ORF min length: 300 bp \u002F 100 aa (source: standard convention for naive ORF finders, avoids spurious short ORFs).\n- Sequence-type detection threshold: 85% (source: heuristic that handles common ambiguity codes without misclassifying short proteins).\n\n## Example Queries\n\n- \"Analyze sample.fasta\"\n- \"Analiza este FASTA, decime el GC y los ORFs\"\n- \"What's the molecular weight of this protein?\"\n- \"Compute pI of the FASTA in \u002Ftmp\u002Fx.fa\"\n\n## Example Output\n\n```markdown\n# analyze-fasta Report\n\n**Input file:** `demo_nucleotide.fasta`\n**Analysis date:** 2026-05-05 12:00:00\n**Sequence type:** `nucleotide`\n**Total sequences:** 1\n\n## Summary\n\n| Metric | Value |\n|---|---|\n| total_sequences | 1 |\n| total_residues | 720 |\n| min_length | 720 |\n| max_length | 720 |\n| avg_length | 720.0 |\n| n50 | 720 |\n| avg_gc_content | 50.42 |\n| total_orfs | 1 |\n\n## Per-sequence metrics\n\n### 1. synthetic_demo_orf\n\n- **Description:** synthetic_demo_orf | Synthetic E. coli-like ORF\n- **Length:** 720 bp\n- **GC content:** 50.42%\n- **AT content:** 49.58%\n- **ORFs (>=100 aa):** 1\n\n---\n\n_ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions._\n```\n\n## Output Structure\n\n```\n\u003Coutput_dir>\u002F\n├── report.md              # Primary markdown report\n├── report.html            # Standalone visual report\n├── result.json            # Machine-readable results\n└── reproducibility\u002F\n    ├── commands.sh        # Exact command to reproduce\n    └── run.json           # Run metadata (versions, timestamps, input size)\n```\n\n## Dependencies\n\n**Required**:\n- `biopython` >= 1.80; sequence parsing, ProtParam, gc_fraction, molecular_weight.\n\n**Optional**:\n- None. The skill is intentionally lean; pure stdlib + Biopython.\n\n## Gotchas\n\n- **The model will want to claim \"this is gene X \u002F from organism Y\" from GC content alone.** Do not. GC is a weak signal — many taxa overlap. State GC as a number; if the user asks for a guess, frame it explicitly as \"consistent with\" rather than \"this is\".\n- **The model will treat ORFs >100 aa as proof of coding.** Do not. The ORF finder is naive: forward strand only, no reading-frame validation against known annotations, no Kozak \u002F Shine-Dalgarno check. Frame ORFs as candidates, never confirmed.\n- **The model will silently re-interpret a sequence with many Ns as a real result.** Do not. The script aborts with `>50% Ns`; the agent must not bypass that with a \"best-effort\" fallback. Surface the failure to the user.\n- **The model will mix nucleotide and protein metrics if a multi-record FASTA mixes types.** The skill detects type from the first record only. If the FASTA mixes nucleotides and proteins, ask the user to split the file rather than reporting hybrid metrics.\n- **The model will use the script's HTML output as the primary deliverable.** Use `report.md` for chaining; the HTML is a courtesy for human inspection only.\n\n## Safety\n\n- **Local-first**: no network calls; everything runs against the local file.\n- **Disclaimer**: every `report.md` includes the standard ClawBio research-tool disclaimer.\n- **Audit trail**: every run writes `reproducibility\u002Frun.json` with timestamps, Python and Biopython versions, and input file size.\n- **No hallucinated science**: thresholds (GC, ORF, N ratio) are documented in this SKILL.md; the agent must not invent new ones.\n\n## Agent Boundary\n\nThe agent (LLM) decides whether to fire this skill, may add a short biological-context paragraph on top of the report, and may suggest follow-up skills (`struct-predictor`, `variant-annotation`, `pubmed-summariser`). The skill (Python) executes the metrics and writes the artefacts. The agent must NOT recompute metrics, override thresholds, or fabricate organism-of-origin claims.\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**: the orchestrator routes here when the input is a single `.fasta`\u002F`.fa`\u002F`.fna`\u002F`.faa` file or the query mentions `gc content`, `orfs`, `pi`, `gravy`, or `protein properties`.\n\n**Chaining partners**:\n- `struct-predictor`: take a single protein record from the input FASTA and predict structure.\n- `variant-annotation`: out of scope here, but the user often asks for variant context after sequence inspection.\n- `pubmed-summariser`: useful when the FASTA header contains a gene\u002Forganism name that the user wants literature for.\n\n> Output is JSON + Markdown with stable keys, so it composes cleanly into pipelines.\n\n## Maintenance\n\n- **Review cadence**: re-evaluate quarterly or when Biopython releases a major version.\n- **Staleness signals**: Biopython API breaks (`ProteinAnalysis` signature changes), or ORF heuristics receive a community-standard upgrade (e.g., GeneMark-style probabilistic finders).\n- **Deprecation**: archive to `skills\u002F_deprecated\u002Fanalyze-fasta\u002F` only if a more capable single-FASTA skill (e.g., one wrapping `seqkit stats`) replaces it across the catalog.\n\n## Citations\n\n- [Biopython](https:\u002F\u002Fbiopython.org\u002F) — sequence parsing, GC, molecular weight, ProtParam.\n- [Cock et al. 2009, Bioinformatics 25(11):1422](https:\u002F\u002Fdoi.org\u002F10.1093\u002Fbioinformatics\u002Fbtp163) — Biopython reference.\n- [Kyte & Doolittle 1982, J Mol Biol 157:105](https:\u002F\u002Fdoi.org\u002F10.1016\u002F0022-2836\\(82\\)90515-0) — GRAVY index definition.\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"author":34,"domain":35,"inputs":36,"outputs":46,"version":66,"openclaw":67,"demo_data":92,"endpoints":99,"dependencies":101},[26,27,28,29,30,31,32,33],"fasta","biopython","sequence-analysis","gc-content","orf","protein-properties","isoelectric-point","gravy","Santiago Rodriguez Salinas","genomics",[37],{"name":38,"type":39,"format":40,"required":44,"description":45},"input","file",[26,41,42,43],"fa","fna","faa",true,"Single FASTA file with one or more nucleotide or protein records",[47,52,57,62],{"name":48,"type":39,"format":49,"description":51},"report",[50],"md","Markdown report with summary table, per-sequence metrics, and disclaimer",{"name":53,"type":39,"format":54,"description":56},"result",[55],"json","Machine-readable analysis results (sequence type, per-record metrics, summary)",{"name":58,"type":39,"format":59,"description":61},"report_html",[60],"html","Standalone HTML rendering of the same report for visual inspection",{"name":63,"type":64,"description":65},"reproducibility","directory","Directory with commands.sh and run.json describing the exact run","0.1.0",{"os":68,"emoji":71,"always":20,"install":72,"homepage":75,"requires":76,"trigger_keywords":79},[69,70],"darwin","linux","🧬",[73],{"bins":6,"kind":74,"package":27},"pip","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"env":6,"bins":77,"config":6},[78],"python3",[26,80,81,82,83,84,85,86,87,88,89,90,91],"analyze fasta","analiza fasta","sequence analysis","gc content","find orfs","orf finder","protein properties","isoelectric point","gravy index","protparam","molecular weight protein","molecular weight dna",[93,96],{"path":94,"description":95},"example_data\u002Fdemo_nucleotide.fasta","Synthetic ~720 bp nucleotide sequence with a small ORF (CC0, no real organism)",{"path":97,"description":98},"example_data\u002Fdemo_protein.fasta","Synthetic ~120 aa protein sequence (CC0, no real organism)",{"cli":100},"python skills\u002Fanalyze-fasta\u002Fanalyze_fasta.py --input {input_file} --output {output_dir}",{"python":102,"packages":103},">=3.10",[104],"biopython>=1.80","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fanalyze-fasta",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":114,"prompt":124,"zipAvailable":44},[115,118,121],{"tool":116,"command":117},"npx","npx skills add stanfish06\u002Fskillquarium --skill analyze-fasta",{"tool":119,"command":120},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill analyze-fasta",{"tool":122,"command":123},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill analyze-fasta","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002FSKILL.md",[126,132,137,140,146],{"path":127,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":130,"sourceHtmlUrl":131},"analyze_fasta.py","SCRIPT","脚本",45826,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002Fanalyze_fasta.py",{"path":94,"resourceType":133,"resourceTypeDesc":134,"sizeBytes":135,"sourceHtmlUrl":136},"OTHER","其他",801,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002Fexample_data\u002Fdemo_nucleotide.fasta",{"path":97,"resourceType":133,"resourceTypeDesc":134,"sizeBytes":138,"sourceHtmlUrl":139},225,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002Fexample_data\u002Fdemo_protein.fasta",{"path":141,"resourceType":142,"resourceTypeDesc":143,"sizeBytes":144,"sourceHtmlUrl":145},"INTENTS.json","REFERENCE","参考文档",692,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002FINTENTS.json",{"path":147,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":148,"sourceHtmlUrl":149},"tests\u002Ftest_analyze_fasta.py",11489,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fanalyze-fasta\u002Ftests\u002Ftest_analyze_fasta.py",[151,158,167,174,181,188],{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":162,"licenseFileUrl":192,"sourceHtmlUrl":193,"categories":194,"keywords":195,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]