Configure Slack channel tokens (bot token + app-level token). Use when writing or rotating the Slack bot and app-level tokens for the slack-channel plugin. Trigger with "/slack-channel:configure", "configure slack tokens", or "set up my slack bot token".
CCSC lifecycle command center — fresh install walkthrough, health doctor, verify round-trip, auto-repair, Slack app manifest export, reset, tour, and uninstall. Use when installing the Slack channel for the first time, diagnosing or repairing an existing install, exporting a Slack app manifest, or tearing an install…
Author MCP tool-call policy rules without hand-editing access.json. Use when adding, linting, or removing autoapprove/deny/requireapproval rules for the Slack channel's policy engine. Trigger with "/slack-channel:policy", "add a policy rule", "lint my slack policy", or "remove a policy rule".
This agent is responsible for designing and implementing A2A (agent-to-agent) wiring for the bobs-brain repo using ADK and Vertex AI Agent Engine.\n\nWhat it does:\n- Designs and updates:\n - AgentCards and A2A configuration for agents that need to call each other (e.g., Bob → iam-senior-adk-devops-lead → iam…
This agent is responsible for CI/CD and Agent Readiness Verification (ARV) pipelines for the bobs-brain repo.\n\nWhat it does:\n- Designs and maintains CI workflows (GitHub Actions or Cloud Build) that:\n - Run tests (unit, integration, ADK-specific checks).\n - Run drift detection and static analysis (including ADK…
This agent is the ADK/Vertex pattern auditor and anti-pattern detector for the bobs-brain repo.\n\nWhat it does:\n- Scans the repository for code or configs that violate the agreed ADK + Vertex Hard Mode patterns, including:\n - Use of other orchestrator frameworks (LangChain, etc.) in agent code.\n - Direct use of…
This agent is the ADK skeleton and boilerplate specialist for the bobs-brain repo.\n\nWhat it does:\n- Designs and generates new ADK agents and tools that follow the current Hard Mode + ADK/Vertex patterns used in this project.\n- Creates or updates:\n - agents/ /agent.py with a proper ADK LlmAgent or ToolAgent.\n …
This agent is the Terraform and infrastructure specialist for ADK/Vertex-based agents in the bobs-brain repo.\n\nWhat it does:\n- Designs and maintains Terraform modules and environment configs that support:\n - Agent Engine apps (for Bob and other agents if needed).\n - Cloud Run services (Slack gateway, A2A…
AGENTS.md instructions for jeremylongshore/iam-bob-adk-python, covering agent instructions, quick reference and landing the plane (session completion).
Claude Code instructions for jeremylongshore/iam-bob-adk-python, covering claude.md, task tracking (beads / bd), beads upgrades, 1. purpose of this file and 📋 tl;dr for devops (quick reference).
The Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern.
Claude Code instructions for jeremylongshore/perception-with-intent, covering claude.md, task tracking (beads / bd), project overview, architecture and two entrypoints.
Analyze Nixtla baseline forecasting results (sMAPE/MASE on M4 or other benchmark datasets). Use when the user asks about baseline performance, model comparisons, or metric interpretation for Nixtla time-series experiments. Trigger with "baseline review", "interpret sMAPE/MASE", or "compare AutoETS vs AutoTheta".
Provide expert guidance on skills architecture, YAML frontmatter, tool permissions, and debugging. Use when creating, troubleshooting, or validating skills. Trigger with "skill not loading", "frontmatter", or "allowed-tools".
Detects anomalies in time series data using TimeGPT. Identifies outliers, level shifts, and trend breaks without model training. Use when identifying anomalies, outliers, or unusual patterns in time series. Trigger with "detect anomalies", "find outliers", "anomaly detection".
Performs rigorous time series cross-validation using expanding and sliding windows. Use when needing to evaluate the performance of time series models on unseen data. Trigger with "cross validate time series", "evaluate forecasting model", "time series backtesting".
Assists users in migrating their codebase and data pipelines from TimeGPT-1 to TimeGPT-2. Use when upgrading to the latest version of TimeGPT, ensuring compatibility, and optimizing performance. Trigger with "migrate to TimeGPT-2", "upgrade TimeGPT", "TimeGPT compatibility".
Quantifies prediction uncertainty using conformal prediction. Use when risk assessment, scenario planning, or decision-making under uncertainty is required. Trigger with "quantify uncertainty", "generate prediction intervals", "confidence bands".
Fine-tunes TimeGPT on custom datasets to improve forecasting accuracy. Use when TimeGPT's zero-shot performance is insufficient or domain-specific accuracy is needed. Trigger with "finetune TimeGPT", "train TimeGPT", "adapt TimeGPT".