pattern-capture
This skill should be used when the user asks to 'find repeated feedback', 'what do I keep correcting', 'capture this pattern', 'DRY my prompting', 'stop…
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
skill-creator
This skill should be used when the user asks to 'create a skill', 'improve a skill', 'edit a skill', 'add a skill to a plugin', 'add enforcement patterns',…
workshop
ALWAYS use when the deliverable is a research talk - Typst slides and teleprompter speaker notes built from a paper. Use when the user says "create workshop…
agent-audit
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates…
obsidian-vault-init
Initialises an Obsidian vault for Claude Code workflows. Sets up folder structure, frontmatter conventions, templates, starter .base views, and a CLAUDE.md…
handoff-prompt
Draft a self-contained implementation prompt for zero-context handoff. Use when: "draft a prompt", "write a handoff", "make a prompt I can copy-paste", "create…
verify-open-pstack
Verify an Open Pstack PR's exact candidate head in native Claude Code and Codex sessions, judge them with machine-checked assertions, and publish the exact-SHA…
continuous-learning-v3
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into…
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
arbor
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree…
agent-repellent
Assess your codebase's resistance to AI-assisted development tools.
opencode-agent-creator
Expert guidance for creating, configuring, and refining OpenCode agents. Use when working with agent files, authoring new agents, improving existing agents, or…
page-actions
Configure @farming-labs/docs page actions for Copy Markdown, Open in LLM, one-click MCP connection, and Agent Skills installation. Use for copyMarkdown,…
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
rpi
General RPI (Research, Plan, Implement, Iterate) execution skill. Used for engineering tasks where the user requests "research first, then plan, then implement, and finally iterate," or when the task is highly complex, high-risk, or has an unclear scope of impact. This skill does not depend on any specific command-line tool or platform and is applicable to any AI agent that supports a skill mechanism.
plan-rollout
Adds a multi-environment change-monitoring section to the agent's plan: enumerates target environments (staging, prod, regions, BYOC tenants), picks SLIs…
lbo-model
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment…
token-audit
Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan. Use when hitting rate limits, experiencing early…
eval-loop
Single scaffold and ledger entrypoint for measurable strategy -> execution -> evaluation cycles. Use when the user wants an eval-loop, autoresearch-style…
delegate
Delegates a self-contained task to a Google Gemini Managed Agent (Antigravity) running in a remote sandbox with code execution, web search, and URL reading.…
supabase
Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client…
AgentDB Advanced Features
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems…
AgentDB Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and…
AgentDB Memory Patterns
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use…