prompt-engineering-patterns
Prompt patterns with code: chain-of-thought with few-shot examples, structured output with Pydantic and instructor, ReAct agents with tool calls, prompt…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-13 00:15
Agents & models
26,212 results
rag-architecture
RAG reference across all seven layers: chunking decision tree, hybrid retrieval with reciprocal rank fusion, reranking, grounded generation prompts, retrieval…
team-dispatch
Turns a plan phase into a PhaseSpec v1 and dispatches it to a specialist subagent via the Agent tool. Subagent reads files itself, returns a structured result,…
open-responses-agent-dev
Build autonomous agents using Open Responses API via HuggingFace Inference Providers. Single unified endpoint with multi-provider routing via model suffixes.…
cc-actions
Configure Claude Code GitHub Actions workflows effectively. Covers automatic mode detection, event routing, subagent coordination, hooks for quality gates, MCP…
askme
Verbalized Sampling (VS) protocol for deep intent exploration before planning. Use when starting ambiguous or complex tasks, when multiple interpretations…
inits
Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a repository and capturing hard-to-rediscover…
parallel-launch
Decompose a task into independent concerns and execute them through broadly parallel, specialized agent groups. Use when a request involves multiple…
system-prompt-curator
Create or improve production-grade system prompts for autonomous coding agents using evidence-gated workflow, explicit tool contracts, and completion criteria.…
unlazy
Gate-file discipline over a task decomposition: prove done instead of claiming it. Use on explicit invocation ("unlazy", "depth tree", "gates", "do not stop…
ai-collab-protocols
Surface in-task-collaboration protocols when the user describes an AI workflow informally — URL-as-entity-reference, PR-comment threads as session memory.…
duet
Two-party posture — user as director, agent as executor; every fork, tradeoff, or choice surfaced via batched AskUserQuestion with a recommended default. Use…
generate-my-taste
Evidence-first generator for a personal <name>-taste Claude Code skill. Mines local memories and agent histories for influences, slop bans, and overkill bans;…
github-triage
Triage GitHub issues through a configurable label-based state machine. Use when user wants to triage incoming issues, prepare issues for an autonomous agent,…
grill-ai-mastery
Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by…
inits
Analyze a codebase and create or improve an AGENTS.md file for future agent instances. Use when onboarding to a repository and capturing hard-to-rediscover…
llm-self-loop
Restructure Web-UI / human-triggered tasks into CLI + file-output loops the LLM can iterate alone, with structured logs and addressable scratchpads. Apply…
memory-update
Scan agent's session-history transcripts for save-worthy signals (corrections, preferences, decisions, references), propose and write auto-memory files with…
parallel-launch
Decompose a task into independent concerns and execute them through broadly parallel, specialized agent groups. Use when a request involves multiple…
strict-validation-setup
One-shot bootstrap of strict-mode tooling per ecosystem plus per-task GOALS.md scaffolding so an agentic loop can self-verify. Writes…
write-a-skill
Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progressive-disclosure conventions. Trigger…
write-a-skill
Author a single new skill — produce a SKILL.md plus optional bundled references and scripts following Anthropic's progressive-disclosure conventions. Trigger…
backlog-manager
Manage an engineering backlog for humans and AI agents: review the whole loop, classify issues, improve issue quality, sync pull-request state, and label safe…
army-agent-contract
Writes the session contract for a fleet agent - what it may read, what it may write, what it owns, what it produces, and when it is done - and fixes agents…