Loading...
Loading...
Found 357 Skills
Comprehensive BD intelligence research skill for KServe's business development team. Use this skill whenever a user provides a company name (and optionally a website or address) and wants to research that company as a potential outsourcing client. Triggers on phrases like "research [company]", "look up [company]", "get me info on [company]", "do a BD profile for [company]", "check out this company", or any request to investigate a prospect company for sales or outreach purposes. Always use this skill when the context is about finding potential clients for KServe's BPO services.
Enterprise session state management, token budget optimization, runtime tracking, session handoff protocols, context continuity for Claude Sonnet 4.5 and Haiku 4.5 with context awareness features
Open a new context session at the start of a leader agent workflow. Records agentName, storyId, and phase in wint.contextSessions, emitting a structured SESSION CREATED block for downstream workers to inherit.
Hypothesis-driven deep research swarm. Spawns specialist sub-agents to investigate a task across codebase patterns, web sources, MCP tools, installed skills, and project dependencies — with evidence grading and adversarial challenge. Activates on: research, investigate, discover, deep research, how should I, what's the best way, explore options, analyze approaches, scout, prior art, feasibility.
Orchestrates parallel KB generation using spatial analysis and a map-reduce architecture with incremental update support.
Initialize a long-running project with a structured docs workflow, or update an existing project (new features, bug fixes, refactors, requirement changes). Use this skill whenever the user wants to start a new project, kick off a long-running build task, set up project documentation structure, or says things like "new project", "start a project", "init project", "project setup", or "I want to build something from scratch". Also use when the user mentions wanting a milestone-based plan, structured execution workflow, or asks to scaffold documentation for a complex multi-step build. Additionally, use this skill when the user wants to modify an existing project that already has a `docs/` directory — e.g., "add a new feature", "fix this bug", "refactor X", "I want to change how Y works", "new feature request".
Durable asynchronous messaging channel for inter-agent communication. Implements write-once read-many filesystem mail using atomic writes and directory-based mailboxes.
Standalone squad manager — creates, inspects, validates, and manages squads (multi-agent teams). Scaffolds directories, agents, tasks, workflows. Registers squads for slash commands. Works independently without AIOS. Activates on: create squad, list squads, add agent, validate squad, run workflow, inspect squad, manage squad.
Classify user requests and route to the correct agent + skill combination. Use for any user request that needs delegation: code changes, debugging, reviews, content creation, research, or multi-step workflows. Invoked as the primary entry point via "/do [request]". Do NOT handle code changes directly - always route to a domain agent. Do NOT skip routing for anything beyond pure fact lookups or single read commands.
Agent skill for swarm - invoke with $agent-swarm
Use when executing multi-task plans where each task can be implemented independently by a subagent. Triggers when a plan has 3+ independent tasks, when speed of execution is important, when tasks have clear acceptance criteria suitable for delegation, or when two-stage review gates (spec compliance and code quality) are needed for iterative fix cycles.
Use when a task has multiple independent subtasks that can be executed concurrently by separate agents. Triggers when decomposed work has 2+ subtasks with no data dependencies, when subtasks operate on different files or codebase sections, when serial execution time would be significantly longer than parallel, or when independent analyses or deliverables need concurrent generation.