dependency-planner
Use this skill whenever a NeuroClaw skill, model, or sub-agent reports a missing dependency (e.g. ImportError, ModuleNotFoundError, command not found), or when the user explicitly requests to install, setup, configure, or fix any library, package, compiler, CUDA toolkit, conda environment, system tool, or git-based repository. Triggers include: 'install', 'setup', 'missing dependency', 'fix import error', 'install torch cuda', 'conda create environment', 'pip install from git', 'install nnU-Net', 'setup gcc nvcc', 'prepare environment for deep learning', 'handle dep error', or any phrase indic
npx skills add BioTender-max/awesome-bio-agent-skills --skill dependency-planner --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Dependency Installation Planner (Tool Layer) ## Overview Many NeuroClaw skills (especially deep-learning, neuroimaging, and custom model execution skills) fail due to missing dependencies — a key pain point identified in the MedicalClaw / OpenClaw-Medical-Skills evaluation. This skill acts as the **interface-layer planner** that ensures safe, reproducible, auditable, and user-approved installations across the entire NeuroClaw hierarchy (interface → subagent → base tool). **Strict workflow (never bypassed):** 1. Parse the exact dependency/dependencies from the user request or error message. 2. Automatically detect the local environment: OS family & version, architecture, Python version, conda/pip/virtualenv status, GCC version, NVCC/CUDA version (if GPU-relevant), available disk space & RAM. 3. For each required package/tool, invoke the already-existing `multi-search-engine` skill (with **Google search priority**) to retrieve the **latest official installation instructions** from the authoritative source (e.g. pytorch.org, conda-forge, nvidia.com, github.com releases page, official docs). 4. Perform compatibility analysis against the detected local system (CUDA/driver match, Pytho
- Overview
- Quick Reference
- Installation
- Usage Examples
- Example 1: “My model says torch is missing and I have an RTX 4090”
- Example 2: “Install latest nnU-Net from github for segmentation skill”
- NeuroClaw recommended wrapper script (placed inside the skill folder)
- Harness-Aware Dependency Version Locking
- Auto-Generated Lockfile Strategy
- Environment Reproducibility Verification
- Backward Compatibility & Safe Upgrades
- Integration with Harness Checkpointing
- Important Notes & Limitations
- When to Call This Skill
Place files in: skills/dependency-planner/ Update SOUL.md and/or USER.md to include trigger phrases and skill name
What does the dependency-planner skill do?
Use this skill whenever a NeuroClaw skill, model, or sub-agent reports a missing dependency (e.g. ImportError, ModuleNotFoundError, command not found), or when the user explicitly requests to install, setup, configure, or fix any library, package, compiler, CUDA toolkit, conda environment, system tool, or git-based repository. Triggers include: 'install', 'setup', 'missing dependency', 'fix import error', 'install torch cuda', 'conda create environment', 'pip install from git', 'install nnU-Net', 'setup gcc nvcc', 'prepare environment for deep learning', 'handle dep error', or any phrase indic
How do I install it?
Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill dependency-planner --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From BioTender-max/awesome-bio-agent-skills, a repository with 135 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.