[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-google-deepmind-agentic-ecology-camera-traps":3,"mdc-bf6cag-key":32,"related-org-google-deepmind-agentic-ecology-camera-traps":313,"related-repo-google-deepmind-agentic-ecology-camera-traps":487},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":30,"mdContent":31},"agentic-ecology-camera-traps","classify and search camera trap images","Provides capabilities to run SpeciesNet detector and classifier on camera trap images, extract crop-level feature embeddings, and populate a Hoplite vector database for downstream search and agile modeling.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"google-deepmind","Google DeepMind","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fgoogle-deepmind.png",[12,16,19],{"name":13,"slug":14,"type":15},"Data Analysis","data-analysis","tag",{"name":17,"slug":18,"type":15},"Search","search",{"name":20,"slug":21,"type":15},"Computer Vision","computer-vision",2,"https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fagentic_ecology","2026-08-29T09:48:07.220771",null,0,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":25},[],"https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fagentic_ecology\u002Ftree\u002FHEAD\u002Fskills\u002Fagentic-ecology-camera-traps","---\nname: agentic-ecology-camera-traps\ndescription: >-\n  Provides capabilities to run SpeciesNet detector and classifier on camera trap\n  images, extract crop-level feature embeddings, and populate a Hoplite vector\n  database for downstream search and agile modeling.\n---\n\n# Camera Traps Skill\n\nUse this skill when you need to process a collection of camera trap images, run\nspecies classification, extract vector representation embeddings, and store them\ninside a Hoplite vector database.\n\n## Workflow Overview\n\nFollow these sequential steps:\n\n1.  **Identify Dataset and Limits**:\n    *   Locate the target camera trap images directory.\n    *   Assess if a GPU is available on the system. If running on CPU-only,\n        discuss with the user or apply a processing limit (e.g., first 1000\n        images) to prevent the ingestion pipeline from running excessively long.\n2.  **Initialize Hoplite Database**:\n    *   Create a Hoplite database (`SQLiteUSearchDB`) at the destination folder.\n    *   Configure it with an embedding dimension of `1280` (EfficientNet-V2 M\n        feature size), the metric set to `Cos`, and the data type set to\n        `float16`.\n3.  **Run Ingestion Pipeline**:\n    *   Instantiate the `SpeciesNetDetector` and `SpeciesNetClassifier` models\n        (if running in an environment with pre-mounted read-only models like\n        `\u002Fkaggle\u002Finput\u002F` on Colab, copy the model directory to a local writable\n        path first; see the technical reference).\n    *   Register a PyTorch forward hook on the classifier's average pooling\n        layer (`SpeciesNet\u002Fefficientnetv2-m\u002Favg_pool\u002FMean_Squeeze__3825`) to\n        intercept raw embeddings.\n    *   For each image:\n        *   Insert it into the database as a recording.\n        *   Run the detector model to get bounding box coords for animal\n            detections.\n        *   Crop the PIL image to the bounding box, preprocess it, and run the\n            classifier to extract the 1280-dim embedding vector.\n        *   Cast the vector to `float16` and insert it into the database as a\n            window.\n4.  **Agile Modeling and Search**:\n    *   Once populated, use the Hoplite database to perform vector searches\n        (ranking by similarity) or train active learning classifiers on top of\n        the embeddings.\n5.  **Camera Trap Visualization Guidelines (M3 UI)**:\n    *   **Context Preservation**: Avoid displaying raw cropped images in the\n        result cards. Instead, display the original (uncropped) image inside the\n        card container and draw the animal detection as a red border box overlay\n        dynamically using CSS absolute positioning and percentages (e.g., `left:\n        xmin * 100%`, `top: ymin * 100%`, etc.).\n    *   **Full-Resolution Modal Preview**: Implement a click handler on the card\n        media that triggers a floating fullscreen modal containing the uncropped\n        image and the aligned bounding box overlay to allow the user to verify\n        low-confidence detections.\n    *   **Custom Query Search Support**: The backend server supporting the Web\n        UI must implement on-the-fly embedding extraction for custom HTTP\u002FS\n        query URIs by downloading the image, running the detector to identify\n        target bounding boxes, preprocessing the crop, and capturing the\n        embedding vector using the PyTorch forward hook on the classifier.\n",{"data":33,"body":34},{"name":4,"description":6},{"type":35,"children":36},"root",[37,46,52,59,64],{"type":38,"tag":39,"props":40,"children":42},"element","h1",{"id":41},"camera-traps-skill",[43],{"type":44,"value":45},"text","Camera Traps Skill",{"type":38,"tag":47,"props":48,"children":49},"p",{},[50],{"type":44,"value":51},"Use this skill when you need to process a collection of camera trap images, run\nspecies classification, extract vector representation embeddings, and store them\ninside a Hoplite vector database.",{"type":38,"tag":53,"props":54,"children":56},"h2",{"id":55},"workflow-overview",[57],{"type":44,"value":58},"Workflow Overview",{"type":38,"tag":47,"props":60,"children":61},{},[62],{"type":44,"value":63},"Follow these sequential steps:",{"type":38,"tag":65,"props":66,"children":67},"ol",{},[68,94,149,238,255],{"type":38,"tag":69,"props":70,"children":71},"li",{},[72,78,80],{"type":38,"tag":73,"props":74,"children":75},"strong",{},[76],{"type":44,"value":77},"Identify Dataset and Limits",{"type":44,"value":79},":\n",{"type":38,"tag":81,"props":82,"children":83},"ul",{},[84,89],{"type":38,"tag":69,"props":85,"children":86},{},[87],{"type":44,"value":88},"Locate the target camera trap images directory.",{"type":38,"tag":69,"props":90,"children":91},{},[92],{"type":44,"value":93},"Assess if a GPU is available on the system. If running on CPU-only,\ndiscuss with the user or apply a processing limit (e.g., first 1000\nimages) to prevent the ingestion pipeline from running excessively long.",{"type":38,"tag":69,"props":95,"children":96},{},[97,102,103],{"type":38,"tag":73,"props":98,"children":99},{},[100],{"type":44,"value":101},"Initialize Hoplite Database",{"type":44,"value":79},{"type":38,"tag":81,"props":104,"children":105},{},[106,120],{"type":38,"tag":69,"props":107,"children":108},{},[109,111,118],{"type":44,"value":110},"Create a Hoplite database (",{"type":38,"tag":112,"props":113,"children":115},"code",{"className":114},[],[116],{"type":44,"value":117},"SQLiteUSearchDB",{"type":44,"value":119},") at the destination folder.",{"type":38,"tag":69,"props":121,"children":122},{},[123,125,131,133,139,141,147],{"type":44,"value":124},"Configure it with an embedding dimension of ",{"type":38,"tag":112,"props":126,"children":128},{"className":127},[],[129],{"type":44,"value":130},"1280",{"type":44,"value":132}," (EfficientNet-V2 M\nfeature size), the metric set to ",{"type":38,"tag":112,"props":134,"children":136},{"className":135},[],[137],{"type":44,"value":138},"Cos",{"type":44,"value":140},", and the data type set to\n",{"type":38,"tag":112,"props":142,"children":144},{"className":143},[],[145],{"type":44,"value":146},"float16",{"type":44,"value":148},".",{"type":38,"tag":69,"props":150,"children":151},{},[152,157,158],{"type":38,"tag":73,"props":153,"children":154},{},[155],{"type":44,"value":156},"Run Ingestion Pipeline",{"type":44,"value":79},{"type":38,"tag":81,"props":159,"children":160},{},[161,190,203],{"type":38,"tag":69,"props":162,"children":163},{},[164,166,172,174,180,182,188],{"type":44,"value":165},"Instantiate the ",{"type":38,"tag":112,"props":167,"children":169},{"className":168},[],[170],{"type":44,"value":171},"SpeciesNetDetector",{"type":44,"value":173}," and ",{"type":38,"tag":112,"props":175,"children":177},{"className":176},[],[178],{"type":44,"value":179},"SpeciesNetClassifier",{"type":44,"value":181}," models\n(if running in an environment with pre-mounted read-only models like\n",{"type":38,"tag":112,"props":183,"children":185},{"className":184},[],[186],{"type":44,"value":187},"\u002Fkaggle\u002Finput\u002F",{"type":44,"value":189}," on Colab, copy the model directory to a local writable\npath first; see the technical reference).",{"type":38,"tag":69,"props":191,"children":192},{},[193,195,201],{"type":44,"value":194},"Register a PyTorch forward hook on the classifier's average pooling\nlayer (",{"type":38,"tag":112,"props":196,"children":198},{"className":197},[],[199],{"type":44,"value":200},"SpeciesNet\u002Fefficientnetv2-m\u002Favg_pool\u002FMean_Squeeze__3825",{"type":44,"value":202},") to\nintercept raw embeddings.",{"type":38,"tag":69,"props":204,"children":205},{},[206,208],{"type":44,"value":207},"For each image:\n",{"type":38,"tag":81,"props":209,"children":210},{},[211,216,221,226],{"type":38,"tag":69,"props":212,"children":213},{},[214],{"type":44,"value":215},"Insert it into the database as a recording.",{"type":38,"tag":69,"props":217,"children":218},{},[219],{"type":44,"value":220},"Run the detector model to get bounding box coords for animal\ndetections.",{"type":38,"tag":69,"props":222,"children":223},{},[224],{"type":44,"value":225},"Crop the PIL image to the bounding box, preprocess it, and run the\nclassifier to extract the 1280-dim embedding vector.",{"type":38,"tag":69,"props":227,"children":228},{},[229,231,236],{"type":44,"value":230},"Cast the vector to ",{"type":38,"tag":112,"props":232,"children":234},{"className":233},[],[235],{"type":44,"value":146},{"type":44,"value":237}," and insert it into the database as a\nwindow.",{"type":38,"tag":69,"props":239,"children":240},{},[241,246,247],{"type":38,"tag":73,"props":242,"children":243},{},[244],{"type":44,"value":245},"Agile Modeling and Search",{"type":44,"value":79},{"type":38,"tag":81,"props":248,"children":249},{},[250],{"type":38,"tag":69,"props":251,"children":252},{},[253],{"type":44,"value":254},"Once populated, use the Hoplite database to perform vector searches\n(ranking by similarity) or train active learning classifiers on top of\nthe embeddings.",{"type":38,"tag":69,"props":256,"children":257},{},[258,263,264],{"type":38,"tag":73,"props":259,"children":260},{},[261],{"type":44,"value":262},"Camera Trap Visualization Guidelines (M3 UI)",{"type":44,"value":79},{"type":38,"tag":81,"props":265,"children":266},{},[267,293,303],{"type":38,"tag":69,"props":268,"children":269},{},[270,275,277,283,285,291],{"type":38,"tag":73,"props":271,"children":272},{},[273],{"type":44,"value":274},"Context Preservation",{"type":44,"value":276},": Avoid displaying raw cropped images in the\nresult cards. Instead, display the original (uncropped) image inside the\ncard container and draw the animal detection as a red border box overlay\ndynamically using CSS absolute positioning and percentages (e.g., ",{"type":38,"tag":112,"props":278,"children":280},{"className":279},[],[281],{"type":44,"value":282},"left: xmin * 100%",{"type":44,"value":284},", ",{"type":38,"tag":112,"props":286,"children":288},{"className":287},[],[289],{"type":44,"value":290},"top: ymin * 100%",{"type":44,"value":292},", etc.).",{"type":38,"tag":69,"props":294,"children":295},{},[296,301],{"type":38,"tag":73,"props":297,"children":298},{},[299],{"type":44,"value":300},"Full-Resolution Modal Preview",{"type":44,"value":302},": Implement a click handler on the card\nmedia that triggers a floating fullscreen modal containing the uncropped\nimage and the aligned bounding box overlay to allow the user to verify\nlow-confidence detections.",{"type":38,"tag":69,"props":304,"children":305},{},[306,311],{"type":38,"tag":73,"props":307,"children":308},{},[309],{"type":44,"value":310},"Custom Query Search Support",{"type":44,"value":312},": The backend server supporting the Web\nUI must implement on-the-fly embedding extraction for custom HTTP\u002FS\nquery URIs by downloading the image, running the detector to identify\ntarget bounding boxes, preprocessing the crop, and capturing the\nembedding vector using the PyTorch forward hook on the classifier.",{"items":314,"total":486},[315,336,351,371,383,398,414,427,439,454,465,475],{"slug":316,"name":316,"fn":317,"description":318,"org":319,"tags":320,"stars":333,"repoUrl":334,"updatedAt":335},"alphafold-database-fetch-and-analyze","retrieve and analyze AlphaFold protein structures","Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[321,324,327,330],{"name":322,"slug":323,"type":15},"Bioinformatics","bioinformatics",{"name":325,"slug":326,"type":15},"Genomics","genomics",{"name":328,"slug":329,"type":15},"Life Sciences","life-sciences",{"name":331,"slug":332,"type":15},"Research","research",2690,"https:\u002F\u002Fgithub.com\u002Fgoogle-deepmind\u002Fscience-skills","2026-07-12T07:51:51.827211",{"slug":337,"name":337,"fn":338,"description":339,"org":340,"tags":341,"stars":333,"repoUrl":334,"updatedAt":350},"alphagenome-single-variant-analysis","analyze genetic variant effects with AlphaGenome","Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue\u002Fcell-type ontologies (UBERON\u002FCL) or analyzing variants in chr:pos:ref>alt format.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[342,343,346,347],{"name":322,"slug":323,"type":15},{"name":344,"slug":345,"type":15},"Genetics","genetics",{"name":331,"slug":332,"type":15},{"name":348,"slug":349,"type":15},"RNA-seq","rna-seq","2026-07-12T07:51:39.494803",{"slug":352,"name":352,"fn":353,"description":354,"org":355,"tags":356,"stars":333,"repoUrl":334,"updatedAt":370},"chembl-database","query ChEMBL database for bioactive molecules","Query the ChEMBL database for bioactive molecules, drug targets, bioactivity data, approved drugs, and chemical structures. Use when the user asks about compounds, targets, IC50\u002FKi values, drug mechanisms, or structure searches.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[357,360,363,366,369],{"name":358,"slug":359,"type":15},"ChEMBL","chembl",{"name":361,"slug":362,"type":15},"Chemistry","chemistry",{"name":364,"slug":365,"type":15},"Database","database",{"name":367,"slug":368,"type":15},"Pharmacology","pharmacology",{"name":331,"slug":332,"type":15},"2026-07-12T07:51:35.544306",{"slug":372,"name":372,"fn":373,"description":374,"org":375,"tags":376,"stars":333,"repoUrl":334,"updatedAt":382},"clinical-trials-database","query clinical trial data","Query ClinicalTrials.gov via APIv2. Use when you want to search for trials by condition, drug, location, status, or phase; retrieve trial details by NCT ID; check eligibility\u002Finclusion criteria; count trials across conditions or time periods; identify a sponsor's trial portfolio; find recruiting trials for patient matching.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[377,380,381],{"name":378,"slug":379,"type":15},"Clinical Trials","clinical-trials",{"name":328,"slug":329,"type":15},{"name":331,"slug":332,"type":15},"2026-07-12T07:52:06.846705",{"slug":384,"name":384,"fn":385,"description":386,"org":387,"tags":388,"stars":333,"repoUrl":334,"updatedAt":397},"clinvar-database","retrieve clinical significance from ClinVar database","Use when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding \"hard positive\" benchmark controls for human genomic variants.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[389,392,393,396],{"name":390,"slug":391,"type":15},"ClinVar","clinvar",{"name":344,"slug":345,"type":15},{"name":394,"slug":395,"type":15},"Healthcare","healthcare",{"name":331,"slug":332,"type":15},"2026-07-12T07:51:36.86094",{"slug":399,"name":399,"fn":400,"description":401,"org":402,"tags":403,"stars":333,"repoUrl":334,"updatedAt":413},"credentials","manage and verify API credentials safely","Instructions for handling API keys and credentials safely, verifying their presence, and prompting the user to add them if missing using a safe protocol.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[404,407,410],{"name":405,"slug":406,"type":15},"Compliance","compliance",{"name":408,"slug":409,"type":15},"Operations","operations",{"name":411,"slug":412,"type":15},"Security","security","2026-07-12T07:52:17.355491",{"slug":415,"name":415,"fn":416,"description":417,"org":418,"tags":419,"stars":333,"repoUrl":334,"updatedAt":426},"dbsnp-database","search genetic variants in dbSNP database","Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[420,421,422,425],{"name":322,"slug":323,"type":15},{"name":344,"slug":345,"type":15},{"name":423,"slug":424,"type":15},"NCBI","ncbi",{"name":331,"slug":332,"type":15},"2026-07-12T07:51:33.054229",{"slug":428,"name":428,"fn":429,"description":430,"org":431,"tags":432,"stars":333,"repoUrl":334,"updatedAt":438},"embl-ebi-ols","search biomedical ontologies in EMBL-EBI OLS","Query and search the EMBL-EBI Ontology Lookup Service (OLS) for biomedical ontology terms, definitions, and hierarchies across 250+ ontologies (e.g., GO, DOID, HP). Use when the user asks to search for terms, retrieve details, navigate hierarchies (parents, children, ancestors), look up properties and individuals, get autocomplete suggestions, or access ontology metadata and statistics.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[433,434,437],{"name":322,"slug":323,"type":15},{"name":435,"slug":436,"type":15},"Ontology","ontology",{"name":331,"slug":332,"type":15},"2026-07-12T07:51:59.368324",{"slug":440,"name":440,"fn":441,"description":442,"org":443,"tags":444,"stars":333,"repoUrl":334,"updatedAt":453},"encode-ccres-database","query ENCODE regulatory and experimental data","Query the ENCODE Registry of cis-Regulatory Elements (cCREs) via the SCREEN GraphQL API, or make custom queries to the ENCODE Portal REST API for experiments and files (ChIP-seq peaks, etc.). Use when you want to query regulatory annotations or raw experimental data across human cell types.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[445,446,449,450],{"name":322,"slug":323,"type":15},{"name":447,"slug":448,"type":15},"GraphQL","graphql",{"name":331,"slug":332,"type":15},{"name":451,"slug":452,"type":15},"REST API","rest-api","2026-07-12T07:52:10.597139",{"slug":455,"name":455,"fn":456,"description":457,"org":458,"tags":459,"stars":333,"repoUrl":334,"updatedAt":464},"ensembl-database","query genomic and protein data from Ensembl","Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[460,461,462,463],{"name":322,"slug":323,"type":15},{"name":344,"slug":345,"type":15},{"name":328,"slug":329,"type":15},{"name":331,"slug":332,"type":15},"2026-07-12T07:51:41.645835",{"slug":466,"name":466,"fn":467,"description":468,"org":469,"tags":470,"stars":333,"repoUrl":334,"updatedAt":474},"foldseek-structural-search","perform 3D protein structural searches","Performs 3D structural searches of proteins against various databases (PDB, AlphaFold, CATH, MGnify, etc.) using the Foldseek API. Use ONLY when the user provides a physical 3D coordinate file (.cif, .mmcif, or .pdb) and wants to find structurally similar proteins. Do NOT use if the user only provides a protein sequence, gene name, or UniProt ID.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[471,472,473],{"name":322,"slug":323,"type":15},{"name":328,"slug":329,"type":15},{"name":331,"slug":332,"type":15},"2026-07-12T07:52:09.354992",{"slug":476,"name":476,"fn":477,"description":478,"org":479,"tags":480,"stars":333,"repoUrl":334,"updatedAt":485},"gnomad-database","query genetic variant data from gnomAD","Query the Genome Aggregation Database (gnomAD). Use when determining the rarity or allele frequency of specific genetic variants, retrieving gene constraint metrics (pLI, LOEUF) to assess loss-of-function intolerance, finding variants in a genomic region or gene, or querying structural variants. Don't use for analyzing individual patient genomes, tracking somatic mutations in cancer (use COSMIC), or requesting raw sequencing reads (use ENA).\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[481,482,483,484],{"name":322,"slug":323,"type":15},{"name":344,"slug":345,"type":15},{"name":328,"slug":329,"type":15},{"name":331,"slug":332,"type":15},"2026-07-12T07:51:38.213009",43,{"items":488,"total":554},[489,501,507,521,537],{"slug":490,"name":490,"fn":491,"description":492,"org":493,"tags":494,"stars":22,"repoUrl":23,"updatedAt":500},"agentic-ecology-bioacoustics","perform bioacoustic analysis for ecological research","Provides bioacoustic analysis capabilities for ecologists and researchers using the perch-hoplite Python package. A typical use case is to use agile modeling to bootstrap the creation and deployment of a bespoke detector for targeted species on an existing collection of passive acoustic monitoring recordings.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[495,496,499],{"name":13,"slug":14,"type":15},{"name":497,"slug":498,"type":15},"Python","python",{"name":331,"slug":332,"type":15},"2026-08-29T09:48:06.668897",{"slug":4,"name":4,"fn":5,"description":6,"org":502,"tags":503,"stars":22,"repoUrl":23,"updatedAt":24},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[504,505,506],{"name":20,"slug":21,"type":15},{"name":13,"slug":14,"type":15},{"name":17,"slug":18,"type":15},{"slug":508,"name":508,"fn":509,"description":510,"org":511,"tags":512,"stars":22,"repoUrl":23,"updatedAt":520},"agentic-ecology-init","initialize Python projects for agentic ecology","Initializes a local uv-managed project directory for agentic ecology workloads. Sets up Python dependencies using reference pyproject.toml and uv.lock, configures workspace rules, and ensures Agentic Ecology skills are discoverable.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[513,516,519],{"name":514,"slug":515,"type":15},"Engineering","engineering",{"name":517,"slug":518,"type":15},"Local Development","local-development",{"name":497,"slug":498,"type":15},"2026-08-29T09:48:06.14295",{"slug":522,"name":522,"fn":523,"description":524,"org":525,"tags":526,"stars":22,"repoUrl":23,"updatedAt":536},"agentic-ecology-storage","upload local data to cloud storage","Provides guidelines and reference implementations for uploading local data (such as audio recordings or datasets) to cloud storage systems, focusing on Google Drive via rclone as the primary target.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[527,530,533],{"name":528,"slug":529,"type":15},"Data Engineering","data-engineering",{"name":531,"slug":532,"type":15},"Google Drive","google-drive",{"name":534,"slug":535,"type":15},"Storage","storage","2026-08-29T09:48:13.00055",{"slug":538,"name":538,"fn":539,"description":540,"org":541,"tags":542,"stars":22,"repoUrl":23,"updatedAt":553},"agentic-ecology-ui","visualize and annotate vector database results","Guidelines and templates for creating a generic web UI to visualize, rank, filter, and annotate vector databases. The UI has a hierarchical structure covering database selection, label selection\u002Fdefinition, ranking\u002Ffiltering configuration, and row visualization\u002Fannotation. Meant to be copied and adapted for specific downstream tasks like bioacoustics or camera traps.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[543,546,549,550],{"name":544,"slug":545,"type":15},"Dashboards","dashboards",{"name":547,"slug":548,"type":15},"Data Visualization","data-visualization",{"name":17,"slug":18,"type":15},{"name":551,"slug":552,"type":15},"UI Components","ui-components","2026-08-29T09:48:03.400711",5]