aizynthfinder-retrosynthesis
AiZynthFinder retrosynthetic route planning (CASP) from AstraZeneca Molecular AI. Monte Carlo tree search guided by a template-based neural expansion policy…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,653 results
sf-ai-agentforce-legacy
[DEPRECATED] Creates Agentforce agents using Agent Script syntax with 100-point scoring. For new agent development, use sf-ai-agentscript instead. This skill…
duel
Have an OpenAI model challenge Claude's answer, then defend or revise it through a short evidence-led debate. Use for "duel this with ChatGPT", "face off this…
mcp-neo4j-memory-ops
Use Neo4j memory MCP for creating/updating linked memories (entities, relations), de-duplication (DRY), and retrieval queries for project continuity. Use when…
assist-sessions
Search past Claude sessions for context. Use when asked "where did we leave off?", "what did we discuss about X?", "find a previous conversation", or when…
skills-expert
Audit, debug, and improve Agent Skills without conflating the portable base format with repository-specific marketplace rules. Use when creating or repairing…
yolo
Sets up and launches a Claude Code devcontainer with --dangerously-skip-permissions for fully autonomous, unattended operation inside a sandboxed environment.…
exploring-cursor-history
Finds and explores Cursor IDE conversation history stored locally in SQLite databases and plaintext agent transcripts. Use when the user asks to find, search,…
agent-discovery
Optimize websites, docs, and product surfaces for agent discoverability and operator UX. Use when working on agent SEO/AEO/GEO, crawl policy, markdown or JSON…
agent-workloads
Compatibility alias for the canonical `workflow-rig` front door. Use when older prompts mention `agent-workloads` or when you need the legacy workload-planning…
workflow
Creates durable, resumable workflows using Vercel's Workflow DevKit. Use when building workflows that need to survive restarts, pause for external events,…
operator-handoff
Job-file handoff between a requesting agent and the Operator — a human-supervised computer-use agent driving the machine's real desktop and browser. Use when a…
ft-intent
Draft the intent of a new request from the conversation, with interactive clarification and autonomous artifact generation. Chains to spec on user…
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security,…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
skill-developer
Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger…
workflow-automation
Design and implement automated workflows combining visual logic with custom code. Create multi-step automations, integrate APIs, and build AI-native pipelines.…
ml-feasibility
Use when a user wants to systematically assess whether an AI project is worth investing in, combining the two dimensions of concept simplicity and data sufficiency. Activated when the user asks "Is this idea feasible?", "How much data do we need?", or "Can this be done technically?". Not applicable to: pure data science insight projects, exploratory analysis, or scenarios already clearly identified as not requiring AI.
one-second-rule
Used when a user wants to quickly determine whether a task can be automated by current AI technology. Activated when the user asks "Can this AI do it?", "Is it technically feasible?", or "Can X be automated with AI?" Not applicable to: project evaluations requiring in-depth feasibility analysis, creative tasks involving emotional resonance or complex reasoning, and long-form text generation scenarios in the LLM era.
statistical-acceptance
Apply the "Statistical Acceptance Criteria — Don't Pursue 100% Accuracy" methodology distilled from AI for Everyone. Use when the user needs practical guidance, diagnosis, workflow design, decision support, or an action plan…
loop-worthiness-test
Four decision criteria for judging whether a task is worth turning into a Loop. Use when the user is agonizing over "should this thing be automated," "should I use a loop," or "why is my loop not worth the cost." Not applicable to: the design phase after already deciding to build a loop, or one-off tasks. Key trigger: "is this thing worth doing a loop for," "should it be automated," "loop...
orchestration
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
evolve
Research-driven self-upgrade pipeline for the Elle personal assistant. Fetches latest Claude Code features, audits Elle's architecture, plans upgrades,…
opfor-run
Run red-team attacks and generate a report for an agent target.