assistant-ui-tools
Guide for tool registration and tool UI in assistant-ui. Use when implementing LLM tools, tool call rendering, or human-in-the-loop patterns.
178 repo starsObserved in 1 repos
Agent Building
Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
cy-loop-tasks
Task-graph execution loop for Compozy specs — self-healing checkpoint driver that ships a techspec end to end by executing its authored task graph (_tasks.md + task_NN.md), one atomic commit per Phase B task, QA, then deep-review peer-review rounds until SHIP. Use for continuous codex-loop goal runs over a .compozy/tasks/<slug> whose work is decomposed into task files, or with --frontend to delegate frontend tasks to herdr workers. Do not use for one-off tasks, PRD/TechSpec authoring, or a slug with spec documents but no task graph (use cy-implement-spec).
178 repo starsObserved in 1 repos
Agent Building
cy-spec-preflight
Loads the AGH spec authoring playbook plus relevant lessons, standing directives, glossary, and active context before cy-create-prd, cy-create-techspec, or cy-create-tasks runs. Applies phase-specific checks: PRDs stay business-focused, TechSpecs carry the six quality markers, and every spec/task captures extensibility integration, agent-manageability, config lifecycle, QA tail coverage, and Web/Docs Impact. Use whenever an AGH spec authoring skill is about to run. Do not use for spec execution, review remediation, or non-spec brainstorming output.
178 repo starsObserved in 1 repos
Agent Building
Use llamactl - a CLI tool for LlamaAgents
Use llamactl to initialize, locally preview, deploy and manage LlamaIndex workflows as LlamaAgents. Required llama-index-workflows and llamactl to be installed in the environment.
177 repo starsObserved in 3 repos
Agent Building
distil-cli
Train task-specific small language models (SLMs) using the Distil Labs CLI and platform. Activate this skill when the user asks about: distil labs, distil CLI, the distil command, training small language models, knowledge distillation, creating SLMs from production traces, data preparation for model training, fine-tuning student models from teacher models, deploying trained SLMs, model evaluation metrics, task-specific model training, classification/QA/tool-calling model training, synthetic data generation for training, or any question about the distil platform, its configuration, or its workflows. Also activate when the user mentions: distil model, distil login, distil register, uploading training data, teacher evaluation, model retuning, model deployment with llama-cpp or vLLM, or when working with config.yaml / job_description.json / train.csv files for model training.
177 repo starsObserved in 1 repos
Agent Building
mainline
Use for coding-agent work in Git repos that use or may need Mainline, or when users mention Mainline, intents, agent autonomy, agent_authority, max_autonomy, stop lines, allowed_boundary, inspect_or_stop, before_commit/proposed_intent/opened_pr, current-instruction overrides, commit/seal handoff, push/PR review boundaries, merge/release/deploy boundaries, auto-submit/auto-commit/auto-seal behavior, hooks, proposals, gaps, conflicts, committing, pushing, opening PRs, PR descriptions, or setup.
177 repo starsObserved in 1 repos
Agent Building
openclaw-management
This skill should be used when the user wants to interact with OpenClaw, delegate tasks to their AI assistant, or check gateway status. Activates for AI assistant delegation and orchestration.
176 repo starsObserved in 1 repos
Agent Building
tensorlake
Tensorlake SDK — sandboxes for AI agents and applications. Use when the user mentions tensorlake or sandboxes, or asks about Tensorlake APIs/docs/capabilities. Also use when building an application, coding agent, or agentic system that needs a sandbox to run code — e.g., executing LLM-generated or untrusted code, persistence via suspend/resume, snapshots/checkpoints for forking parallel workers, custom images, exposing ports, egress allowlists, PTY/interactive shells, computer-use / desktop automation, browser automation (Chrome CDP, Playwright), local tunnels for non-HTTP protocols, async parallel sandboxes, Harbor evals or RL rollouts, file transfer, SSH access, remote-dev (VS Code Remote-SSH), or OCI base images. Also covers Tensorlake's sandbox-native durable workflow orchestration. Works alongside any LLM provider (OpenAI, Anthropic), agent framework (Claude/OpenAI agents SDK, LangChain), database, or API. When this skill applies, ALWAYS WebFetch https://docs.tensorlake.ai/llms.txt first.
176 repo starsObserved in 1 repos
Agent Building
claude-agent-sdk-tool-integration
Use when integrating tools, permissions, and MCP servers with Claude AI agents using the Agent SDK.
175 repo starsObserved in 4 repos
Agent Building
claude-agent-sdk-context-management
Use when managing agent context, memory, and conversation state in Claude AI agents using the Agent SDK.
175 repo starsObserved in 3 repos
Agent Building