# Send LobsterBio - Dev to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "lobster-bio-dev", "name": "LobsterBio - Dev", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/cewinharhar/lobster-bio-dev", "canonicalUrl": "https://clawhub.ai/cewinharhar/lobster-bio-dev", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/lobster-bio-dev", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lobster-bio-dev", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "references/architecture.md", "references/cli.md", "references/creating-services.md", "references/testing.md", "references/code-layout.md", "references/creating-agents.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "lobster-bio-dev", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T05:45:58.762Z", "expiresAt": "2026-05-09T05:45:58.762Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lobster-bio-dev", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lobster-bio-dev", "contentDisposition": "attachment; filename=\"lobster-bio-dev-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "lobster-bio-dev" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/lobster-bio-dev" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/lobster-bio-dev", "downloadUrl": "https://openagent3.xyz/downloads/lobster-bio-dev", "agentUrl": "https://openagent3.xyz/skills/lobster-bio-dev/agent", "manifestUrl": "https://openagent3.xyz/skills/lobster-bio-dev/agent.json", "briefUrl": "https://openagent3.xyz/skills/lobster-bio-dev/agent.md" } } ``` ## Documentation ### Lobster AI Development Guide Lobster AI is a multi-agent bioinformatics platform using LangGraph for orchestration. This skill teaches you how to work with, extend, and contribute to the codebase. ### Quick Navigation TaskDocumentationArchitecture overviewreferences/architecture.mdCreating new agentsreferences/creating-agents.mdCreating new servicesreferences/creating-services.mdCode layout & finding filesreferences/code-layout.mdTesting patternsreferences/testing.mdCLI referencereferences/cli.md ### Critical Rules ComponentRegistry is truth — Agents discovered via entry points, NOT hardcoded AGENT_CONFIG at module top — Define before heavy imports for <50ms discovery Services return 3-tuple — (AnnData, Dict, AnalysisStep) always Always pass ir — log_tool_usage(..., ir=ir) for reproducibility No lobster/__init__.py — PEP 420 namespace package ### Package Structure lobster/ ├── packages/ # Agent packages (PEP 420) │ ├── lobster-transcriptomics/ # transcriptomics_expert, annotation_expert, de_analysis_expert │ ├── lobster-research/ # research_agent, data_expert_agent │ ├── lobster-visualization/ # visualization_expert │ ├── lobster-metadata/ # metadata_assistant │ ├── lobster-structural-viz/ # protein_structure_visualization_expert │ ├── lobster-genomics/ # genomics_expert │ ├── lobster-proteomics/ # proteomics_expert │ └── lobster-ml/ # machine_learning_expert └── lobster/ # Core SDK ├── agents/supervisor.py # Supervisor (stays in core) ├── agents/graph.py # LangGraph builder ├── core/ # Infrastructure (registry, data_manager, provenance) ├── services/ # Analysis services └── tools/ # Agent tools ### Quick Commands # Setup (development) make dev-install # Full dev setup with editable install make test # Run all tests make format # black + isort # Setup (end-user testing via uv tool) uv tool install 'lobster-ai[full,anthropic]' # Install as users see it uv tool upgrade lobster-ai # Upgrade to latest # Running lobster chat # Interactive mode lobster query "your request" # Single-turn # Testing pytest tests/unit/ # Fast unit tests pytest tests/integration/ # Integration tests ### Service Pattern (Essential) All services return a 3-tuple: def analyze(self, adata, **params) -> Tuple[AnnData, Dict, AnalysisStep]: # Your analysis logic stats = {"n_cells": adata.n_obs, "status": "complete"} ir = AnalysisStep( activity_type="analyze", inputs={"n_obs": adata.n_obs}, outputs=stats, params=params ) return processed_adata, stats, ir Tools wrap services: @tool def analyze_modality(modality_name: str, **params) -> str: result, stats, ir = service.analyze(adata, **params) data_manager.log_tool_usage("analyze", params, stats, ir=ir) # IR mandatory! return f"Complete: {stats}" ### Agent Registration (Entry Points) Agents register via pyproject.toml: [project.entry-points."lobster.agents"] my_agent = "lobster.agents.my_domain.my_agent:AGENT_CONFIG" AGENT_CONFIG must be defined at module top (before imports): # lobster/agents/mydomain/my_agent.py from lobster.config.agent_registry import AgentRegistryConfig AGENT_CONFIG = AgentRegistryConfig( name="my_agent", display_name="My Expert Agent", description="What this agent does", factory_function="lobster.agents.mydomain.my_agent.my_agent", handoff_tool_name="handoff_to_my_agent", handoff_tool_description="Assign tasks for my domain analysis", tier_requirement="free", # All official agents are free ) # Heavy imports AFTER config from lobster.core.data_manager_v2 import DataManagerV2 # ... rest of implementation ### Key Files FilePurposelobster/agents/graph.pyLangGraph orchestrationlobster/core/component_registry.pyAgent discoverylobster/core/data_manager_v2.pyData/workspace managementlobster/core/provenance.pyW3C-PROV trackinglobster/cli.pyCLI implementation ### Online Documentation Full documentation at docs.omics-os.com (or local docs-site/): Getting Started: docs/getting-started/ Core SDK: docs/core/ Agents: docs/agents/ Developer Guide: docs/developer/ API Reference: docs/api-reference/ ### Adding a New Agent Create package: packages/lobster-mydomain/ Define AGENT_CONFIG at top of agent file Register entry point in pyproject.toml Implement agent with tools Add tests in tests/unit/agents/ See references/creating-agents.md for full guide. ### Adding a New Service Create service class in appropriate package Implement 3-tuple return pattern Wrap in tool with log_tool_usage Add unit tests See references/creating-services.md for full guide. ### Understanding Data Flow User Query → CLI → LobsterClientAdapter → AgentClient ↓ LangGraph (supervisor → agents) ↓ Services → DataManagerV2 ↓ Results + Provenance ### Testing # Unit tests (fast, no external deps) pytest tests/unit/ -v # Integration tests (may need env vars) pytest tests/integration/ -v # Specific test pytest tests/unit/test_my_feature.py -v # With coverage pytest --cov=lobster tests/ ### Contributing Fork the repository Create feature branch: git checkout -b feature/my-feature Make changes following patterns above Run tests: make test Format code: make format Submit PR with clear description ## Trust - Source: tencent - Verification: Indexed source record - Publisher: cewinharhar - Version: 1.0.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-02T05:45:58.762Z - Expires at: 2026-05-09T05:45:58.762Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/lobster-bio-dev) - [Send to Agent page](https://openagent3.xyz/skills/lobster-bio-dev/agent) - [JSON manifest](https://openagent3.xyz/skills/lobster-bio-dev/agent.json) - [Markdown brief](https://openagent3.xyz/skills/lobster-bio-dev/agent.md) - [Download page](https://openagent3.xyz/downloads/lobster-bio-dev)