Skills for your AI
Loads and runs Hugging Face transformer models for pipeline inference, tokenization, text generation, fine-tuning, dataset preparation, model inspection, translation, summarization, and audio/vision tasks. Use when the user asks to run a model, fine-tune on a
Plans transportation technology integration, from software selection and data integration to automation, security, fleet telematics, routing, and driver tools. Use when choosing transportation management software, integrating GPS or traffic data, finding autom
Builds labelled eval sets, sweeps criteria wordings and thresholds, and calibrates confidence gates for typed-decision models. Use when evaluating a typed-decision model, comparing criteria configs or models, choosing a score threshold, testing a confidence ga
Reduces high-dimensional data to 2D/3D embeddings with UMAP for visualization, clustering preprocessing, supervised separation, and feature engineering. Use when the user supplies a high-dimensional dataset and wants an embedding, parameter tuning, HDBSCAN pre
Use for web scraping, crawling, document extraction, API parsing, or building validation-heavy data pipelines using Firecrawl or local Python scripts.
Analyzes warehouse inventory, space, slotting, traffic, safety, equipment, automation, and expansion data to produce layout optimization reports and plans. Use when a logistics coordinator needs layout analysis, slotting, congestion, safety, equipment, automat
Adds Cisco Webex channel support to a NanoClaw service by copying and registering the Webex adapter, installing the pinned dependency, validating build and tests, and guiding bot setup and credential storage. Use when the owner wants Webex chat integration, ne
Identifies, evaluates, and rolls out workflow automation for operations managers, covering opportunity analysis, tool and cost recommendations, implementation plans, risk mitigation, training, performance monitoring, and trend summaries. Use when the user asks
Designs and implements automated process workflows covering data extraction, decision rules, document generation, notifications, monitoring, integration, task assignment, error handling, optimization, compliance, quality, maintenance, inventory, and customer c
Analyzes operations workflows, researches automation tools, and produces implementation, training, monitoring, task assignment, approvals, communication, inventory, quality, billing, HR, and compliance automation plans. Use when an operations manager wants to
Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipe
Manages and triggers documented Zapier webhook workflows and MCP tool patterns, and records new ones in reference files. Use when the user asks to run a named Zap or automation, orchestrate MCP tools, save a webhook URL or tool preference, or check readiness b
Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when creating or updating Actor output schemas.
Curated upstream guidance for Apify Integration Development; use when the workflow matches the user goal.
Curated upstream guidance for Hf Cli; use when the workflow matches the user goal.
Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.
Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.
Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.
Secure AI coding agents (Claude Code, Cursor, Codex, Copilot) with permission boundaries, secret protection, code review gates, and safe sandbox configurations for team environments.
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
Harden AI/LLM deployments against prompt injection, data exfiltration, model theft, and supply chain attacks.
Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.
This skill is for educational purposes or authorized security assessments only.
Route enumerable judgment steps - did it work, which option, how risky, is this safe to run - to the Jev judgment model through the jev_judge and jev_gate MCP tools, batched into one call per state.
