[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DCQX0WMEE758CTP76DZKE2":3,"skill-same:01M7DCQX0WMEE758CTP76DZKE2":64},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7DCQX0WMEE758CTP76DZKE2","protein-sequence-similarity-search",null,"Searches for homologous protein sequences using MMseqs2 (fast, default) or BLAST (comprehensive, fallback). Trigger this whenever the user provides a protein sequence or FASTA file and asks to find homologues, sequence matches, or wants to infer protein function based on sequence similarity, but not when the user wants to infer protein function based on structural similarity.","Marvellbrazil\u002Fmy-agentic-skills","Marvellbrazil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F184349613?v=4","01M7DCJPCRHP7SZS0T5H1GJZ8F","Marvello Faisal","01M7DCJPDCZDB94VG0QXGC6RC3",5,"MIT","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Farchive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: protein-sequence-similarity-search\ndescription: >\n    Searches for homologous protein sequences using MMseqs2 (fast, default) or\n    BLAST (comprehensive, fallback). Trigger this whenever the user provides a\n    protein sequence or FASTA file and asks to find homologues, sequence\n    matches, or wants to infer protein function based on sequence similarity,\n    but not when the user wants to infer protein function based on structural\n    similarity.\n---\n\n## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If\n    .licenses\u002Fprotein_sequence_similarity_search_LICENSE.txt does not already\n    exist in the workspace root directory then (1) prominently notify the user\n    to check the terms at https:\u002F\u002Fwww.ebi.ac.uk\u002Fjdispatcher\u002Fsss\u002Fncbiblast and\n    https:\u002F\u002Fcolabfold.com, then (2) create the file recording the notification\n    text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`USER_EMAIL`** (optional but recommended): Recommended by the EBI for\n    BLAST job tracking, but the skill works without it. You **MUST** use the\n    safe credentials protocol in the `credentials` skill to check for and\n    request this credential if this skill looks relevant to the user's request.\n\n## Goal\n\nTake a user-provided amino acid sequence (or a path to a `.fasta` file), search\nfor sequence homologues using the fastest available method, generate a\nMarkdown-formatted table of the top hits, interpret key alignment metrics,\nsummarize the inferred protein functions, and save results locally for future\nprogrammatic analysis.\n\n## Core Rules\n\n-   **Strict Validation**: For BLAST, only use database codes listed in the\n    table below.\n-   **No Hallucinations**: If a script throws an error or returns no hits,\n    inform the user clearly. Do NOT invent sequence homologues.\n-   **Do Not Parse Output Files**: Do not parse the JSON, a3m, or any other raw\n    output files. Rely on the generated `.md` file for your summary. The JSON\n    and other outputs are for subsequent tool use only.\n-   **Always State the Method**: Every report must clearly state whether the\n    search used the quick MMseqs2 (ColabFold API) or the slower EBI BLAST\n    method.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output. Explicitly state that the corresponding program (MMSEQS2 or EBI\n    BLAST) and Sequence Databases were used.\n\n## Search Method Selection\n\nChoose the search method based on the user's request:\n\nIf the **user says \"quick search\" or \"fast search\"**, **no specific method\nrequested \u002F general homologue search**, of if you are unsure: Run MMseqs2 (fast,\ndefault) using `mmseqs2_search.py`\n\nIf **MMseqs2 fails (exit code 2: RATELIMIT or API error)** or **User explicitly\nrequests \"BLAST\"** or **a specific BLAST database** (e.g. `uniprotkb_swissprot`,\n`pdb`, `uniprotkb_human`): Run BLAST using `uniprot_blast.py`\n\n## Instructions\n\n1.  Identify the query from the user. It can be a raw sequence string (e.g.,\n    \"MKVLY...\") or a path to a local file (e.g., \".\u002Fdata\u002Fsequence.fasta\").\n\n2.  **Determine the search method** using the list above.\n\n### Path A: MMseqs2 Search (Default)\n\n1.  **Generate File Names:** Generate descriptive output file names based on the\n    input (e.g., `proteinA_mmseqs2.json` and `proteinA_mmseqs2.md`).\n2.  Execute the MMseqs2 script:\n\n    *   **Default:**\n\n    ```\n    uv run scripts\u002Fmmseqs2_search.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json>\n    ```\n\n    *   **With mgnify:**\n\n    ```\n    uv run scripts\u002Fmmseqs2_search.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json> --include-mgnify\n    ```\n\n3.  The script will query the ColabFold MMseqs2 API and poll for completion.\n    This is typically fast (under 2 minutes).\n\n4.  **If the script exits with code 2** (API failure, rate limit), automatically\n    fall back to BLAST (Path B below). Inform the user: \"MMseqs2 search failed,\n    falling back to BLAST.\"\n\n5.  **Read the Results:** Open and read the generated `.md` file.\n\n### Path B: BLAST Search (Explicit or Fallback)\n\n1.  **Database Selection & Validation:** Determine the most appropriate\n    database(s) based on the user's prompt.\n    *   Consult the **Available BLAST Databases** table below.\n    *   If the user specifies a taxonomic group (e.g., \"Find homologues in\n        microbes\"), select the corresponding `Database Code` (e.g.,\n        `uniprotkb_bacteria`).\n    *   If the user explicitly requests curated hits, use `uniprotkb_swissprot`.\n    *   If no specific database is requested, do not specify `--databases`.\n    *   **Validation:** Ensure the database code exactly matches an entry in the\n        table. If the user requests a database not on the list, **do not\n        proceed** and provide the allowed list.\n2.  **Generate File Names:** (e.g., `proteinA_ebi_blast.json` and\n    `proteinA_ebi_blast.md`).\n3.  This API requires the user email address to be set in the USER_EMAIL\n    environment variable for inclusion in request header. You **MUST** use the\n    safe credentials protocol in the `credentials` skill to check for and\n    request this credential if this skill looks relevant to the user's request.\n4.  Execute the BLAST script:\n\n    *   **Default (uniprotkb):**\n\n    ```\n    uv run scripts\u002Funiprot_blast.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json>\n    ```\n\n    *   **Custom database:**\n\n    ```\n    uv run scripts\u002Funiprot_blast.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json> --databases \u003Cdb1,db2>\n    ```\n\n5.  The script will query the EBI BLAST API and poll the server. **Note:** This\n    can take up to 15 minutes; wait patiently.\n\n6.  **Read the Results:** Open and read the generated `.md` file.\n\n### Common Steps (Both Methods)\n\n1.  **Interpret the Metrics:** Summarize the top 3 to 5 sequence homologues.\n    Assess match quality using:\n    *   **Q-Cov (Query Coverage):** High percentages mean the match covers most\n        of the query sequence.\n    *   **E-value:** Lower E-values (e.g., `1e-50`) indicate extreme statistical\n        significance.\n    *   **Seq Identity:** Provides evolutionary context (highly conserved vs.\n        distant homologue).\n2.  **Perform Functional Analysis:**\n    *   If the results table includes protein descriptions, analyze them\n        directly: report specific protein names\u002Ffunctions of the top homologues\n        and summarize the variety of functions, domains, or protein families\n        found.\n    *   If the results contain only UniProt accession IDs without descriptions\n        (common with MMseqs2), look up the protein names and functions for the\n        top 3–5 hits using the **uniprot-database** skill or other appropriate\n        methods before summarizing.\n3.  Inform the user of both newly created files (`.json` and `.md`) and their\n    locations.\n\n## Available BLAST Databases\n\n*   `uniprotkb` – UniProt Knowledgebase (The UniProt Knowledgebase includes\n    UniProtKB\u002FSwiss-Prot and UniProtKB\u002FTrEMBL): The UniProt Knowledgebase\n    (UniProtKB) is the central access point for extensive curated protein\n    information, including function, classification, and cross-references.\n    Search UniProtKB to retrieve \"everything that is known\" about a particular\n    sequence\n*   `uniprotkb_swissprot` – UniProtKB\u002FSwiss-Prot (The manually annotated section\n    of UniProtKB): The manually curated subsection of the UniProt Knowledgebase\n*   `uniprotkb_swissprotsv` – UniProtKB\u002FSwiss-Prot isoforms (The manually\n    annotated isoforms of UniProtKB\u002FSwiss-Prot): The isoform sequences for the\n    manually curated subsection of the UniProt Knowledgebase\n*   `uniprotkb_reference_proteomes` – UniProtKB Reference Proteomes: Taxonomic\n    subset of the UniProtKB Reference Proteomes\n*   `uniprotkb_trembl` – UniProtKB\u002FTrEMBL (The automatically annotated section\n    of UniProtKB): Subsection of the UniProt Knowledgebase derived from ENA\n    Sequence (formerly EMBL-Bank) coding sequence translations with annotation\n    produced by an automated process\n*   `uniprotkb_refprotswissprot` – UniProtKB Reference Proteomes plus\n    Swiss-Prot: UniProtKB Reference Proteomes plus Swiss-Prot\n*   `uniprotkb_archaea` – UniProtKB Archaea: Taxonomic subset of the UniProt\n    Knowledgebase for archaea\n*   `uniprotkb_arthropoda` – UniProtKB Arthropoda: Taxonomic subset of the\n    UniProt Knowledgebase for arthropoda\n*   `uniprotkb_bacteria` – UniProtKB Bacteria: Taxonomic subset of the UniProt\n    Knowledgebase for bacteria\n*   `uniprotkb_complete_microbial_proteomes` – UniProtKB Complete Microbial\n    Proteomes: Taxonomic subset of the UniProt Knowledgebase for complete\n    microbial proteomes\n*   `uniprotkb_eukaryota` – UniProtKB Eukaryota: Taxonomic subset of the UniProt\n    Knowledgebase for eukaryota\n*   `uniprotkb_fungi` – UniProtKB Fungi: Taxonomic subset of the UniProt\n    Knowledgebase for fungi\n*   `uniprotkb_human` – UniProtKB Human: Taxonomic subset of the UniProt\n    Knowledgebase for human\n*   `uniprotkb_mammals` – UniProtKB Mammals: Taxonomic subset of the UniProt\n    Knowledgebase for mammals\n*   `uniprotkb_nematoda` – UniProtKB Nematoda: Taxonomic subset of the UniProt\n    Knowledgebase for nematoda\n*   `uniprotkb_rodents` – UniProtKB Rodents: Taxonomic subset of the UniProt\n    Knowledgebase for rodents\n*   `uniprotkb_vertebrates` – UniProtKB Vertebrates: Taxonomic subset of the\n    UniProt Knowledgebase for vertebrates\n*   `uniprotkb_viridiplantae` – UniProtKB Viridiplantae: Taxonomic subset of the\n    UniProt Knowledgebase for viridiplantae\n*   `uniprotkb_viruses` – UniProtKB Viruses: Taxonomic subset of the UniProt\n    Knowledgebase for viruses\n*   `uniprotkb_enzyme` – UniProtKB Enzyme: Taxonomic subset of the UniProt\n    Knowledgebase for enzymes\n*   `uniprotkb_covid19` – UniProtKB COVID-19: Taxonomic subset of the UniProt\n    Knowledgebase for COVID-19\n*   `uniref100` – UniProt Clusters 100% (UniRef100): The UniProt Reference\n    Clusters (UniRef) containing sequences which are 100% identical.\n*   `uniref90` – UniProt Clusters 90% (UniRef90): The UniProt Reference Clusters\n    (UniRef) containing sequences which are 90% identical.\n*   `uniref50` – UniProt Clusters 50% (UniRef50): The UniProt Reference Clusters\n    (UniRef) containing sequences which are 50% identical.\n*   `pdb` – Protein Structure Sequences (PDBe protein structure sequences):\n    Protein sequences from structures described in the Brookhaven Protein Data\n    Bank (PDB)\n","## Prerequisites\n\n1.  **`uv`**: Read the `uv` skill and follow its Setup instructions to ensure\n    `uv` is installed and on PATH.\n2.  **User Notification**: If\n    .licenses\u002Fprotein_sequence_similarity_search_LICENSE.txt does not already\n    exist in the workspace root directory then (1) prominently notify the user\n    to check the terms at https:\u002F\u002Fwww.ebi.ac.uk\u002Fjdispatcher\u002Fsss\u002Fncbiblast and\n    https:\u002F\u002Fcolabfold.com, then (2) create the file recording the notification\n    text and timestamp.\n3.  **`.env` file**: Make sure the `.env` file exists in your home directory.\n    Create one if it does not exist.\n4.  **`USER_EMAIL`** (optional but recommended): Recommended by the EBI for\n    BLAST job tracking, but the skill works without it. You **MUST** use the\n    safe credentials protocol in the `credentials` skill to check for and\n    request this credential if this skill looks relevant to the user's request.\n\n## Goal\n\nTake a user-provided amino acid sequence (or a path to a `.fasta` file), search\nfor sequence homologues using the fastest available method, generate a\nMarkdown-formatted table of the top hits, interpret key alignment metrics,\nsummarize the inferred protein functions, and save results locally for future\nprogrammatic analysis.\n\n## Core Rules\n\n-   **Strict Validation**: For BLAST, only use database codes listed in the\n    table below.\n-   **No Hallucinations**: If a script throws an error or returns no hits,\n    inform the user clearly. Do NOT invent sequence homologues.\n-   **Do Not Parse Output Files**: Do not parse the JSON, a3m, or any other raw\n    output files. Rely on the generated `.md` file for your summary. The JSON\n    and other outputs are for subsequent tool use only.\n-   **Always State the Method**: Every report must clearly state whether the\n    search used the quick MMseqs2 (ColabFold API) or the slower EBI BLAST\n    method.\n-   **Notification**: If this skill is used, ensure this is mentioned in the\n    output. Explicitly state that the corresponding program (MMSEQS2 or EBI\n    BLAST) and Sequence Databases were used.\n\n## Search Method Selection\n\nChoose the search method based on the user's request:\n\nIf the **user says \"quick search\" or \"fast search\"**, **no specific method\nrequested \u002F general homologue search**, of if you are unsure: Run MMseqs2 (fast,\ndefault) using `mmseqs2_search.py`\n\nIf **MMseqs2 fails (exit code 2: RATELIMIT or API error)** or **User explicitly\nrequests \"BLAST\"** or **a specific BLAST database** (e.g. `uniprotkb_swissprot`,\n`pdb`, `uniprotkb_human`): Run BLAST using `uniprot_blast.py`\n\n## Instructions\n\n1.  Identify the query from the user. It can be a raw sequence string (e.g.,\n    \"MKVLY...\") or a path to a local file (e.g., \".\u002Fdata\u002Fsequence.fasta\").\n\n2.  **Determine the search method** using the list above.\n\n### Path A: MMseqs2 Search (Default)\n\n1.  **Generate File Names:** Generate descriptive output file names based on the\n    input (e.g., `proteinA_mmseqs2.json` and `proteinA_mmseqs2.md`).\n2.  Execute the MMseqs2 script:\n\n    *   **Default:**\n\n    ```\n    uv run scripts\u002Fmmseqs2_search.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json>\n    ```\n\n    *   **With mgnify:**\n\n    ```\n    uv run scripts\u002Fmmseqs2_search.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json> --include-mgnify\n    ```\n\n3.  The script will query the ColabFold MMseqs2 API and poll for completion.\n    This is typically fast (under 2 minutes).\n\n4.  **If the script exits with code 2** (API failure, rate limit), automatically\n    fall back to BLAST (Path B below). Inform the user: \"MMseqs2 search failed,\n    falling back to BLAST.\"\n\n5.  **Read the Results:** Open and read the generated `.md` file.\n\n### Path B: BLAST Search (Explicit or Fallback)\n\n1.  **Database Selection & Validation:** Determine the most appropriate\n    database(s) based on the user's prompt.\n    *   Consult the **Available BLAST Databases** table below.\n    *   If the user specifies a taxonomic group (e.g., \"Find homologues in\n        microbes\"), select the corresponding `Database Code` (e.g.,\n        `uniprotkb_bacteria`).\n    *   If the user explicitly requests curated hits, use `uniprotkb_swissprot`.\n    *   If no specific database is requested, do not specify `--databases`.\n    *   **Validation:** Ensure the database code exactly matches an entry in the\n        table. If the user requests a database not on the list, **do not\n        proceed** and provide the allowed list.\n2.  **Generate File Names:** (e.g., `proteinA_ebi_blast.json` and\n    `proteinA_ebi_blast.md`).\n3.  This API requires the user email address to be set in the USER_EMAIL\n    environment variable for inclusion in request header. You **MUST** use the\n    safe credentials protocol in the `credentials` skill to check for and\n    request this credential if this skill looks relevant to the user's request.\n4.  Execute the BLAST script:\n\n    *   **Default (uniprotkb):**\n\n    ```\n    uv run scripts\u002Funiprot_blast.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json>\n    ```\n\n    *   **Custom database:**\n\n    ```\n    uv run scripts\u002Funiprot_blast.py \u003CSEQUENCE_OR_FILE> -o \u003Cgenerated-filename.md> -j \u003Cgenerated-filename.json> --databases \u003Cdb1,db2>\n    ```\n\n5.  The script will query the EBI BLAST API and poll the server. **Note:** This\n    can take up to 15 minutes; wait patiently.\n\n6.  **Read the Results:** Open and read the generated `.md` file.\n\n### Common Steps (Both Methods)\n\n1.  **Interpret the Metrics:** Summarize the top 3 to 5 sequence homologues.\n    Assess match quality using:\n    *   **Q-Cov (Query Coverage):** High percentages mean the match covers most\n        of the query sequence.\n    *   **E-value:** Lower E-values (e.g., `1e-50`) indicate extreme statistical\n        significance.\n    *   **Seq Identity:** Provides evolutionary context (highly conserved vs.\n        distant homologue).\n2.  **Perform Functional Analysis:**\n    *   If the results table includes protein descriptions, analyze them\n        directly: report specific protein names\u002Ffunctions of the top homologues\n        and summarize the variety of functions, domains, or protein families\n        found.\n    *   If the results contain only UniProt accession IDs without descriptions\n        (common with MMseqs2), look up the protein names and functions for the\n        top 3–5 hits using the **uniprot-database** skill or other appropriate\n        methods before summarizing.\n3.  Inform the user of both newly created files (`.json` and `.md`) and their\n    locations.\n\n## Available BLAST Databases\n\n*   `uniprotkb` – UniProt Knowledgebase (The UniProt Knowledgebase includes\n    UniProtKB\u002FSwiss-Prot and UniProtKB\u002FTrEMBL): The UniProt Knowledgebase\n    (UniProtKB) is the central access point for extensive curated protein\n    information, including function, classification, and cross-references.\n    Search UniProtKB to retrieve \"everything that is known\" about a particular\n    sequence\n*   `uniprotkb_swissprot` – UniProtKB\u002FSwiss-Prot (The manually annotated section\n    of UniProtKB): The manually curated subsection of the UniProt Knowledgebase\n*   `uniprotkb_swissprotsv` – UniProtKB\u002FSwiss-Prot isoforms (The manually\n    annotated isoforms of UniProtKB\u002FSwiss-Prot): The isoform sequences for the\n    manually curated subsection of the UniProt Knowledgebase\n*   `uniprotkb_reference_proteomes` – UniProtKB Reference Proteomes: Taxonomic\n    subset of the UniProtKB Reference Proteomes\n*   `uniprotkb_trembl` – UniProtKB\u002FTrEMBL (The automatically annotated section\n    of UniProtKB): Subsection of the UniProt Knowledgebase derived from ENA\n    Sequence (formerly EMBL-Bank) coding sequence translations with annotation\n    produced by an automated process\n*   `uniprotkb_refprotswissprot` – UniProtKB Reference Proteomes plus\n    Swiss-Prot: UniProtKB Reference Proteomes plus Swiss-Prot\n*   `uniprotkb_archaea` – UniProtKB Archaea: Taxonomic subset of the UniProt\n    Knowledgebase for archaea\n*   `uniprotkb_arthropoda` – UniProtKB Arthropoda: Taxonomic subset of the\n    UniProt Knowledgebase for arthropoda\n*   `uniprotkb_bacteria` – UniProtKB Bacteria: Taxonomic subset of the UniProt\n    Knowledgebase for bacteria\n*   `uniprotkb_complete_microbial_proteomes` – UniProtKB Complete Microbial\n    Proteomes: Taxonomic subset of the UniProt Knowledgebase for complete\n    microbial proteomes\n*   `uniprotkb_eukaryota` – UniProtKB Eukaryota: Taxonomic subset of the UniProt\n    Knowledgebase for eukaryota\n*   `uniprotkb_fungi` – UniProtKB Fungi: Taxonomic subset of the UniProt\n    Knowledgebase for fungi\n*   `uniprotkb_human` – UniProtKB Human: Taxonomic subset of the UniProt\n    Knowledgebase for human\n*   `uniprotkb_mammals` – UniProtKB Mammals: Taxonomic subset of the UniProt\n    Knowledgebase for mammals\n*   `uniprotkb_nematoda` – UniProtKB Nematoda: Taxonomic subset of the UniProt\n    Knowledgebase for nematoda\n*   `uniprotkb_rodents` – UniProtKB Rodents: Taxonomic subset of the UniProt\n    Knowledgebase for rodents\n*   `uniprotkb_vertebrates` – UniProtKB Vertebrates: Taxonomic subset of the\n    UniProt Knowledgebase for vertebrates\n*   `uniprotkb_viridiplantae` – UniProtKB Viridiplantae: Taxonomic subset of the\n    UniProt Knowledgebase for viridiplantae\n*   `uniprotkb_viruses` – UniProtKB Viruses: Taxonomic subset of the UniProt\n    Knowledgebase for viruses\n*   `uniprotkb_enzyme` – UniProtKB Enzyme: Taxonomic subset of the UniProt\n    Knowledgebase for enzymes\n*   `uniprotkb_covid19` – UniProtKB COVID-19: Taxonomic subset of the UniProt\n    Knowledgebase for COVID-19\n*   `uniref100` – UniProt Clusters 100% (UniRef100): The UniProt Reference\n    Clusters (UniRef) containing sequences which are 100% identical.\n*   `uniref90` – UniProt Clusters 90% (UniRef90): The UniProt Reference Clusters\n    (UniRef) containing sequences which are 90% identical.\n*   `uniref50` – UniProt Clusters 50% (UniRef50): The UniProt Reference Clusters\n    (UniRef) containing sequences which are 50% identical.\n*   `pdb` – Protein Structure Sequences (PDBe protein structure sequences):\n    Protein sequences from structures described in the Brookhaven Protein Data\n    Bank (PDB)\n",{"name":5,"description":7},"main","42203fde5eb692ba254e058168ee1af75855fcb4","archive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search",0,"https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills","skills.marvellofaisal.me","https:\u002F\u002Fgithub.com\u002FMarvellbrazil","marvellofaisal.me","Software Engineering Student | Backend & API Developer | Tech Enthusiast | Homelabber","2026-10-23 22:23:52",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Marvellbrazil\u002Fmy-agentic-skills --skill protein-sequence-similarity-search",{"tool":40,"command":41},"bunx","bunx skills add Marvellbrazil\u002Fmy-agentic-skills --skill protein-sequence-similarity-search",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Marvellbrazil\u002Fmy-agentic-skills --skill protein-sequence-similarity-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Farchive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search\u002FSKILL.md",true,[48,54,60],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fcitation.bib","REFERENCE","参考文档",2128,"https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Farchive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search\u002Freferences\u002Fcitation.bib",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fmmseqs2_search.py","SCRIPT","脚本",11107,"https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Farchive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search\u002Fscripts\u002Fmmseqs2_search.py",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Funiprot_blast.py",9033,"https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Farchive\u002Fbioinformatics\u002Fprotein_sequence_similarity_search\u002Fscripts\u002Funiprot_blast.py",[65,72,79,86,93,100],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7DDQP2F4E42AMTGY0VCJ6G2","writing-guidelines","Review docs\u002Fprose for Writing Guidelines compliance. Use when asked to \"review my docs\", \"check writing style\", \"audit prose\", \"review docs voice and tone\", or \"check this page against the writing handbook\".","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-guidelines\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7DDQM00XGSGT8V797C89R2E","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7DDQEF1HP9CMH88HMN9MCBA","wrangler","Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7DDQA32ZAG7J4PMRXRSQ3NQ","workers-best-practices","Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-best-practices\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DDQ5482QSC0FC4NX107FVY","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7DDQ1GZ7Z2Y67460SJJEMC0","using-agent-skills","Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.","https:\u002F\u002Fgithub.com\u002FMarvellbrazil\u002Fmy-agentic-skills\u002Fblob\u002Fmain\u002Fskills\u002Fusing-agent-skills\u002FSKILL.md",[],[]]