crew
Dispatch visible T3 Code worker threads across your configured providers, then verify and integrate their reports.
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
goal-prompting
Use when creating, rewriting, reviewing, or optimizing prompts for /goal, goal mode, Codex goal mode, long-running coding agents, autonomous coding tasks, or…
fast-track-ai-init
Installs the fast-track-ai tree into a target repo, idempotently. Use whenever starting fast-track-ai in a new or existing repo, the user says "setup…
token-usage-cost-report
Use when an agent must produce an auditable token-usage and cost report from structured runtime evidence, normalized usage bundles, or repository-level report…
logic-extract
Traces a specific business logic flow across multiple repositories from user-provided starting points. Explores only prompt-relevant code, discovers repos the…
update-team
Analyze the current project and reconcile the Codex agent team. Use when the user asks to update the agent team, add or remove agents, re-analyze project…
mcp-server-best-practices
Best practices for using the Judgment MCP server effectively. Covers when to use MCP vs other tools, how to use search_traces with batching, and general usage…
your-skill-name
Brief description of what this skill does. Include specific triggers - when should Claude use this skill? Example triggers, file types, or keywords that…
caveman-manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
pua
This skill should be used when the user asks to "use PUA to manage AI", "supervise AI under high pressure", "make AI reflect after being scolded", "strictly pressure AI into execution", "PUA AI agent", or requests a no-excuse accountability mode where…
thumbnail-skill
Deterministic thumbnail rendering execution Skill for the AI Video Production Ecosystem. Use it when a caller (normally video-production-agent) has already…
judgment-training
Call when the user needs to make directional judgments, assess "which way to go / is this reliable," or wants to improve decision-making ability. Core idea: Judgment (knowing the long-term consequences of actions) matters more than effort; clear thinking = rebuilding reasoning from foundational disciplines; collect mental models (compounding / principal-agent / falsifiability / basic mathematics). Not applicable to: specific task steps that need immediate execution. Triggers:…
eve
Build durable backend AI agents with the eve framework. Use when creating, editing, or debugging an eve project — agent instructions, skills, tools, connections, channels, sandboxes, subagents, schedules, or evals.
setup-payments
Sell Kelviq plans and manage subscribers — checkout sessions, subscriptions, trials, the customer portal, upgrades, and discounts — via the kelviq MCP tools.…
handoff
Compact the current conversation into a handoff document for another agent to pick up.
enhance-web-conversion
Conversion pass for landing, pricing, and upgrade paths: positioned hero, one CTA, real proof, anchored tiers, upgrade prompts at value moments. Use when…
ask-kent
Ask which kcd-skills flow fits your situation. A router over the skills in this repo. Use when you don't know which Kent skill to run, or which order.
conduct
Coordinate a fleet of cloud agents across separate environments for large multi-track programs (migrations, purges, upgrades). The conductor audits,…
netra-decorator-instrumentation
Create custom Netra tracing instrumentation using decorators. Use when choosing between auto-instrumentation, decorators, and manual tracing in Python or…
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to…
find-skill
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
radar
Adds high-value tests, fixes flaky tests, and improves coverage with minimal and reliable changes. Use when tests are missing, unstable, or insufficient.
pi-logs
Query pi agent session logs using Nushell's structured data pipeline. Use when debugging sessions, analyzing tool usage, finding commands run, or tracking file…
pi-session-logs
Query pi agent session logs as JSON Lines using Nushell pipelines. Use when debugging agent sessions, analyzing tool calls, or tracking file access in session…