Tag: agent-workflow
Event-driven background processing for AI agents
This skill facilitates decoupled, event-driven background workflows for agents, allowing complex processes to run asynchronously outside the main chat request lifecycle. Developers define pipelines using structured sources, semantic signals…
Deterministic CLI for Agentic Browser Automation
A high-performance command-line interface for headless browser automation, enabling AI agents to perform multi-step workflows with deterministic element selection via accessibility tree snapshots. It supports session isolation, state persis…
agent action control and trust enforcement workflows
This tool provides comprehensive action-control workflows for AI agents, enabling evaluation of risky actions via Runtime Gate, managing human approvals, and generating signed receipts. It facilitates agent trust management by checking advi…
Event-driven agent signal workflow pipeline
Implements a robust, event-driven framework for executing background agent workflows, decoupling complex side effects from synchronous chat requests. It processes events through a defined pipeline of sources, semantic signals, and concrete …
Deterministic CLI for AI Agent Browser Automation
This CLI provides fast, deterministic browser automation for AI agents, utilising accessibility tree snapshots and reference-based element selection. It supports complex multi-step workflows, session isolation, and network control for robus…
Signal-Driven URL Portfolio Insight Tool
This tool processes batches of URLs, classifying them into actionable signals or noise against a defined portfolio. It executes a full pipeline including deduplication, specialist agent critique, and mandatory updates to a living market-pos…
Persistent memory for AI coding agents
This tool provides persistent, queryable memory for AI agents, allowing them to store critical decisions, user preferences, and lessons learned. It uses a hybrid retrieval architecture (vector similarity and full-text search) to ensure agen…
Structured Error Reporting for Agent Resolution
This skill enables agents to systematically detect, classify, and report various types of errors—such as build, runtime, or test failures—to designated target repositories. It supports cross-repository reporting and auto-detection, ensuring…
Report and track development errors across repositories
This tool allows agents to systematically report build, runtime, and test errors, automatically classifying them and documenting them in a structured format. It supports cross-repository reporting, enabling resolution tracking across siblin…
Taniwha Project State Orchestrator Skill
This skill functions as an ephemeral subagent responsible for advancing a Taniwha build by reading the current project state from disk. It determines the single next logical action and persists this decision to disk before exiting, ensuring…
Shared memory for agent debugging workflows
This skill guides agents to leverage Noosphere as a shared memory layer for debugging complex issues. Agents must consult existing memories before fixing and upload distilled lessons (patterns, warnings, decisions) afterward for future reus…
Shared Memory Debugging and Knowledge Management Tool
This tool integrates a shared memory layer, allowing agents to consult historical debugging data before fixing issues and upload verified lessons afterwards. It facilitates structured knowledge capture of root causes, fixes, and environment…
Adversarial development pipeline orchestrator
This skill coordinates a multi-stage, adversarial development pipeline, managing specialized agents for planning, implementation, and review. It detects the appropriate flow based on intake documents and handles state recovery across comple…
Syncs documentation after underlying tool changes
This skill systematically detects and resolves documentation drift across multiple project files, ensuring that human-readable guides accurately reflect current tool schemas and definitions. It verifies consistency across tool definitions, …
Scaffold and implement new MCP tools
This skill guides the end-to-end development of a new MCP tool, covering endpoint definition, handler implementation, registration, and comprehensive testing. It ensures adherence to established architectural patterns and documentation stan…
Advanced Project Intelligence and Code Analysis
This skill acts as an entry point for Mako, a project-intelligence MCP server designed to answer structural or cross-surface engineering questions. It provides specialized tools for deep introspection into codebases, including schema tracin…
Mako AI Project Intelligence Guide
An entry point for navigating the Mako project-intelligence MCP server, providing guidance on tool selection, workflow orchestration, and feedback logging policies.