В каталоге 182 820 навыков в 14 категориях.
Stores and retrieves per-user, per-project preferences for AI skills via a unified JSON-backed CLI. Loaded by consumer s...
Agent Skill design knowledge base — mechanisms, philosophy, patterns, pitfalls. Use when: designing new skills, reviewin...
Agent Skills portable format router. Use when creating cross-client skills, validating portable frontmatter, packaging s...
Use when the user wants to find, evaluate, audit, or install an open-source AI agent skill or MCP server — e.g. "find an...
Run, verify, and troubleshoot the Antigravity Agent Skills Vault & Skill.Sea automation pipeline (update.py, skillssh.py...
Audit AND optimize a CLAUDE.md / AGENTS.md instruction file — score it against the five high-leverage patterns, flag ant...
Generate or update repository-specific AGENTS.md instruction files from real repo evidence. Use when asked to create, de...
Cross-framework enhancement overlay for choosing a multi-agent topology BEFORE writing any agent. A binary-question rubr...
SOP for terminal-based, git-native AI pair programming with Aider (git work-tree + tree-sitter repo-map + edit-format +...
Screens biomedical / life-science papers for signs of data fabrication, image manipulation, and statistical anomalies, u...
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, t...
Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~...
SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .cl...
Split a multi-call LM workflow by cognitive load, not by accuracy: let one strong model make the few reasoning decisions...
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, m...
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace...
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public ben...
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Acti...
Neutral, framework-agnostic decision tree for project kickoff: "which agent / RAG / LLM framework should I reach for?" S...
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the...
Enhancement-overlay SOP for adding sparse (BM25 / keyword) retrieval alongside dense (embedding) retrieval. Activate whe...
Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipe...
Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is...
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agen...
Enhancement overlay — version the WHOLE deployable LLM-app artifact as one bundle: prompts + compiled programs + model s...
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-L...
Decision protocol for making side-effectful agent tools idempotent — so when an LLM tool call is retried (timeout, frame...
Decision protocol for the map-reduce / dynamic fan-out pattern in LM pipelines — "given list L, run f(item) for each ite...
ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / Prog...
Security-first SOP for multi-tenant RAG systems. Activate when a calling agent is building, reviewing, or debugging any...
Designs multiscale chunking for RAG by embedding small units for retrieval precision and returning larger context for sy...
Enhancement-overlay skill — the DECISION + WIRING layer for LM observability that the single-backend skills [[langsmith]...
Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitiv...
Lifecycle SOP for **per-model prompt artifacts** — the compiled prompts, instructions, few-shot demos, edit-format pins,...
The compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (D...
Tool skill — the *first move* in any LM-debugging session: dump the actual rendered prompt the framework sent to the mod...
Routes heterogeneous queries to the appropriate index, tool, or answering engine before retrieval. Use when one endpoint...
Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code chan...
Symbol-level code context for LLM coder-agents: tree-sitter extracts symbols, PageRank ranks them over the cross-file re...
A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace...
Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appe...
Project-kickoff rubric for the self-host vs managed-cloud decision — when is running your own inference engine / LLM pla...
Decision protocol for managing the context/session state of an AI coding tool: when to /clear, when to keep context, and...
Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dsp...
Tool skill for declaring reducers on LangGraph state keys so parallel writes merge instead of crashing. Activates whenev...
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the *backend*, not...
Decide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instruct...
Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test →...
Enhancement overlay for multi-agent / tool-using coder agents. Encodes the per-agent tool- scoping discipline that role-...
SOP for distilling reusable semantic operators (data-science operation skills) from agent execution trajectories: read a...
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs...
Direct and implement programmatic videos from a natural-language sentence: brief, shots, style, timeline, assets, engine...
Use when a task involves sharing or handing off selected workspace files through an authorized cloud workspace-sharing s...
See what your AI agent is doing, from anywhere. The agent keeps writing — logs, code, generated outputs, screenshots, ar...
Logic-based agent programming language implementing BDI architecture for practical autonomous agent development
Instructions for debugging agentstack-server during development
agent.system.main
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI...
Live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what...
Display the API key for the currently authenticated user. Requires authentication. Use for managing authentication crede...
Logout of the Agentuity Cloud Platform. Use for managing authentication credentials
Set up machine authentication by uploading a public key for self-hosted infrastructure. Requires authentication. Use for...
Show the current default organization. Use for managing authentication credentials
Clear the default organization preference. Use for managing authentication credentials
Add an SSH public key to your account (reads from file or stdin). Requires authentication. Use for managing authenticati...
Delete an SSH key from your account. Requires authentication. Use for managing authentication credentials
List all SSH keys on your account. Requires authentication. Use for managing authentication credentials
Display information about the currently authenticated user. Requires authentication. Use for managing authentication cre...
Build Agentuity application for deployment
Get details about a specific agent. Requires authentication. Use for Agentuity cloud platform operations
List agents for a project. Requires authentication. Use for Agentuity cloud platform operations
Create a new API key. Requires authentication. Use for Agentuity cloud platform operations
Delete an API key (soft delete). Requires authentication. Use for Agentuity cloud platform operations
Get a specific API key by id. Requires authentication. Use for Agentuity cloud platform operations
List all API keys. Requires authentication. Use for Agentuity cloud platform operations
Create a new database resource. Requires authentication. Use for Agentuity cloud platform operations
Delete a database resource. Requires authentication. Use for Agentuity cloud platform operations
Show details about a specific database. Requires authentication. Use for Agentuity cloud platform operations
List database resources. Requires authentication. Use for Agentuity cloud platform operations
Get query logs for a specific database. Requires authentication. Use for Agentuity cloud platform operations
Execute SQL query on a database. Requires authentication. Use for Agentuity cloud platform operations
Deploy project to the Agentuity Cloud. Requires authentication. Use for Agentuity cloud platform operations
List deployments. Requires authentication. Use for Agentuity cloud platform operations
View logs for a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
Remove a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
Rollback the latest to the previous deployment. Requires authentication. Use for Agentuity cloud platform operations
Show details about a specific deployment. Requires authentication. Use for Agentuity cloud platform operations
Undeploy the latest deployment. Requires authentication. Use for Agentuity cloud platform operations
Delete an environment variable. Requires authentication. Use for Agentuity cloud platform operations
Get an environment variable value. Requires authentication. Use for Agentuity cloud platform operations
Import environment variables from a file to cloud and local .env.production. Requires authentication. Use for Agentuity...
Import environment variables from a file to cloud and local .env. Requires authentication. Use for Agentuity cloud platf...
List all environment variables. Requires authentication. Use for Agentuity cloud platform operations
Pull environment variables from cloud to local .env.production file. Requires authentication. Use for Agentuity cloud pl...
Push environment variables from local .env.production file to cloud. Requires authentication. Use for Agentuity cloud pl...
Push environment variables from local .env file to cloud. Requires authentication. Use for Agentuity cloud platform oper...
Set an environment variable. Requires authentication. Use for Agentuity cloud platform operations
Get details about a specific eval. Requires authentication. Use for Agentuity cloud platform operations
List evals. Requires authentication. Use for Agentuity cloud platform operations
Get details about a specific eval run. Requires authentication. Use for Agentuity cloud platform operations