dspy-ragas
Use Ragas to evaluate DSPy RAG pipelines with decomposed metrics. Use when you want to evaluate RAG quality, measure faithfulness, context precision, context…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
dspy-retrieval
DSPy retrieval modules (dspy.Retrieve, dspy.ColBERTv2, dspy.Embedder, dspy.retrievers.Embeddings) for searching documents, computing embeddings, and building…
dspy-vizpy
Use VizPy as a drop-in prompt optimizer for DSPy. Use when you want to try VizPy, vizops, ContraPromptOptimizer, PromptGradOptimizer, a commercial alternative…
dspy-vllm
Use vLLM for high-throughput production serving of self-hosted models with DSPy. Use when you want production LLM serving, tensor parallelism, multi-GPU…
agent-mail
Coordinate with other AI agents via project-local Maildir messaging. Use when operating in tandem mode with Claude, Gemini, or other agents. Enables claiming…
context-continuity
High-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful…
agent-update-manager
The English introduction is being prepared.
awesome-free-llm-apis
Reference guide for permanent free-tier LLM APIs with rate limits, model lists, and OpenAI-compatible integration patterns.
creating-extensions
Creates and edits trusted local Letta Code extensions, including extension tools, slash commands, lifecycle/turn events, scoped conversation helpers, panels,…
alera-agent-canvas
Publish structured Agent Canvas updates for the current Alera terminal and wait for durable decisions.
geo
Complete GEO (Generative Engine Optimization) service pipeline: given a product website URL and introductory materials, perform site diagnosis and AI answer sampling, generate execution work orders with acceptance criteria, produce directly deployable assets (llms.txt / JSON-LD / definition blocks / FAQ / content outlines and drafts), automatically verify whether the work orders are closed-loop, …
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn…
spec-driven-dev-v2
Use when an agent will work for hours or days across many files and multiple vertical slices. Drives a three-level Project → Sprint → Task hierarchy with…
agent-environment
Set up, audit, reconcile, verify, or migrate a person's user-level coding-agent environment across devices and tools such as Codex, Cursor, and Claude Code.…
setup-lidessen-skills
Operational deployer for the lidessen skills collection — wires harness config (CLAUDE.md / AGENTS.md / .cursor/) in a target project, injects cross-cutting…
agent-environment
Set up, audit, reconcile, verify, or migrate a person's user-level coding-agent environment across devices and tools such as Codex, Cursor, and Claude Code.…
export
Extract your persona into CLAUDE.md or AGENTS.md for use in any AI agent
introduce
Inject your persona into the current session
batch-task-executor
Experimental workflow skill for coordinating many related tasks from any source. Use when the user asks to mass-process, batch-execute, fan out, parallelize,…
s3-upload
S3-compatible object storage CLI (upload, list, find, download, delete, public URL) via scripts/s3-cli.js with env-backed config aligned to this repo. Use when…
movie-maker-skill
Docs-first AgentSkill for generating 10-60s mini-movies locally. Provides rules for scripts, shotlists, timing, prompting, providers, rendering…
dsh-search-plugin
Search the public dshfind plugin gateway and return ranked, evidence-tagged DSH plugins matching a goal. Triggers: find DSH plugins / search plugins / find a plugin / search plugins.
tgravity-work-goal
TGravity Work goal prompt specification Skill. Used to rewrite chaotic, vague, half-formed goals, problems, or Agent delegations into clear, checkable goal prompts that can be handed to an Agent; it only defines the goal, does not break down tasks, does not assign work, and does not generate execution plans. Trigger methods: goal prompt, goal specification, goal clarification, make the goal clear, help me define the goal, I don't know how to describe the goal, how should this goal...
tgravity-work-prompt-architect
TGravity Work prompt architecture Skill. Used to review the role positioning, workflow backbone, classification branches, judgment criteria, boundary rules, and execution paths of an existing prompt, or to generate an executable agent prompt framework based on corpus, role description, and output examples; does not do ordinary copy polishing. Trigger methods: prompt architecture, prompt review, review prompt, evaluate prompt, optimize prompt architecture, generate prompt framework, reverse-engineer prompt, write a...