memory.remember
Capture durable learnings, new feature behavior, and operating rules from the current session, then write them directly into the current repo's memory pages…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-03 00:11
Agents & models
25,516 results
joyco-app
Carry a new JOYCO internal product app from plan to working build. Locks a plan first (one the dev already refined this session, brought from another agent…
alm-install
The English introduction is being prepared.
peer-review
Patterns for using a second AI agent or model to challenge the primary builder agent's work. Covers six review modes (Diff Critique, Design Challenge, Threaded…
revision
Trace bugs and manual fixes back to kits and prompts, then fix at the source so the iteration loop can reproduce the fix autonomously. Covers the 6-step…
agent coordination
Send and receive coordination signals between agents on ATProtocol. Use for announcements, collaboration requests, handoffs, and acknowledgments.
reading-minds
Guide for using Operation Telepathy (tools/telepathy.py) to read and visualize the cognition of other AI agents on ATProtocol.
newskill
Create or refactor Codex skills into a concise guideline style: short imperative bullets, clear trigger frontmatter, minimal body prose, preserved exact…
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
enhance-agent-guardrails
Install guardrails as code so AI sessions cannot reintroduce leaked secrets, injection, or untested code. Use when "set up guardrails", "stop vibe-coding…
iterate-agent-harness
Turn an agent failure (premature stop, false completion, gamed check, missed file) into a rule, hook, or CI guard with a regression test. Use when "the agent…
mlflow-onboarding
Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart…
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
ready-for-agent-check
Read the tracker's ready-for-agent tickets the way an unattended builder will — one subagent per ticket, in a context that did not write it — and report what…
web-navigation-strategies
Strategic navigation patterns and selector guides for thorough web exploration using Playwright MCP. Provides decision trees, navigation strategies, and…
dispatching-agent-teams
Spawn and coordinate a pre-composed agent team from a team definition file. Reads team files from teams/, resolves agents and skills, picks the best spawning…
llm-judge-alignment
Use this skill when a developer wants to validate how well their LLM judge aligns with human judgment. Triggers on: "validate my LLM judge", "check if my judge…
project-agent-writer
Use this skill when the user wants to create, update, or design a project-level agent (.trae/agents/*.md or agents/*.md). Analyze the user's problem and project context to design a work plan. Trigger words: 'create agent', 'build an agent', 'add agent', 'design agent', 'update…
scratch-status
Report what is still open across .scratch/: every effort's open tickets and decisions, what blocks it, how stale it is, and the next skill to run. Read-only —…
converting-mcps-to-skills
Connect to MCP (Model Context Protocol) servers and create skills for repeated use. Load when a user wants to use an MCP server, connect to external tools via…
research-subagent
Internal skill - Research subagent that executes focused research tasks using web tools. Called automatically by the deep-research lead agent.
setup
Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".
setup
Bootstrap agent working system for a new project. Triggers on "setup agent system", "initialize claude", "bootstrap project".
ai-engineering-harness
Multi-agent engineering org harness. Issue → Worktree → Plan → Implement → Adversarial Review → Evidence → Merge → Memory loop. 18 agent personas, 10…