All skills

An operations skill that wires messaging channels to nanoclaw agent groups and configures isolation, mention and threading policies.

An interactive skill for adding channels, MCP integrations, personas, and deployment changes to a NanoClaw bot.

Routes a NanoClaw agent group to a local Ollama model instead of the Anthropic API via env overrides and a model setting.

Walks an operator through creating the first NanoClaw DM agent and verifies end-to-end delivery with a welcome message.

Detects an existing OpenClaw install and walks you conversationally through moving identity, channel tokens, scheduled tasks and MCP config into NanoClaw v2's entity model.

Extracts your NanoClaw fork's customizations into a replayable migration guide, then upgrades by reapplying them on a clean upstream checkout — no merge conflicts.

An AI/ML-specific security skill that scans for prompt injection and jailbreaks, scores model inversion and data poisoning risk, and maps findings to MITRE ATLAS.

Installs OneCLI and migrates your NanoClaw project's .env API credentials into the Agent Vault gateway.

An autonomous edit-measure-keep/revert loop that optimizes any file against a measurable metric using git as the safety net.

Wires OpenCode (OpenRouter, DeepSeek, Zen, Anthropic) in as a per-group agent backend for NanoClaw instead of the Anthropic Agent SDK.

Walks Claude through the human-judgment half of a NanoClaw v1→v2 upgrade: owner seeding, legacy memory, container config, and fork triage.

A strict operating contract for building, updating and recalling evidence-grounded person profiles through Distilly's exact five MCP tools.

x

Design and review PyLabRobot 0.2.1 liquid-handling protocols offline, with every physical device command locked behind an explicit operator safety gate.

Runs bounded one-hop and endpoint-pinned two-hop TRAPI queries against the NCATS Translator ARAX API and returns typed, provenance-rich biomedical relationships.

A rigorous workflow skill for planning, validating, restarting, and analyzing FluidSim 0.9 pseudospectral CFD runs with explicit numerical and HPC safety gates.

Scans protein sequences for N-/O-glycosylation sites and guides glycan engineering strategies for antibodies and vaccine antigens.

Runs DiffDock/DiffDock-L to predict protein–small-molecule binding poses and interprets the confidence scores.

Runs the standard phylogenetics workflow — MAFFT alignment, IQ-TREE 2/FastTree inference, and ETE3 tree analysis and rendering.

An expert skill for building, tuning, evaluating, and reporting right-censored and competing-risk survival models with scikit-survival, without data leakage.