skill-builder
Interactive guide for creating new agent skills from scratch. Use this skill when the user wants to create a skill, write a SKILL.md, package a skill folder,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-04 00:13
Agents & models
25,613 results
connector-manager
Data source connector management — the Agent automatically helps users query, configure, create, and test data connectors
financial-modeling
Investment-Banking-Grade Financial Modeling Engine — Formula-Driven Multi-Sheet Professional DCF/Valuation Model
jev
Use TypeSafe Jev for typed judgments (Choice, Score, Noul) instead of asking a chat model to classify. Pair with a generative model for prose. Use when…
jev-guardrail
Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Use for jailbreak, prompt…
orthogonal
Access premium APIs and curated skills via Orthogonal marketplace. Use when you need external data (scraping, enrichment, search), want to discover new…
unstuck-scaling
Use when AI agents frequently hit dead ends, when reliability is the main constraint on scaling utility, or when general model improvements don't solve…
loom-usage
Meta-orchestration skill for Claude driving loom itself. Use when running plans, interpreting loom status, debugging failed or blocked stages, managing…
coval-eval-start
Choose the next useful step for evaluating a voice or chat agent with Coval. Use for getting started or deciding what to do next; use a specific skill directly…
ai-strategist
Use when evaluating AI tools and agentic workflows against workflow gaps, when conducting quarterly landscape scans, or when assessing integration feasibility…
skill-editor
Use when creating, modifying, or refactoring Claude Code skills that require structured multi-agent review and quality validation
push-skills
Push skills and global AGENTS.md to the private repo and verify the public mirror. Use only when the user explicitly invokes /push-skills.
agent-first-screenshots
Agent-first screenshots — an agent drives the real app via CDP and produces clean, defect-free product screenshots (newsletters, landing pages, social, decks,…
llm-council
Multi-model consensus using Karpathy LLM Council pattern for critical decisions
agent-orchestration
Multi-agent orchestration and state management.
ai-engineer
Principal AI Architect and Machine Learning Engineer.
auto
End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention…
review
Comprehensive code review orchestrator. Runs multiple focused review analyses (bugs, types, maintainability, simplicity, coverage, docs, AGENTS.md) and…
mixseek-orchestrator-config
Generates the MixSeek orchestrator configuration file (orchestrator.toml). Use it for requests such as "configure the orchestrator", "team competition settings", "have multiple teams compete", and "multi-team execution settings". It defines settings for running multiple teams in parallel and selecting the best result.
connecting-im-bot
Use when configuring or connecting IM channel bots such as WeChat, WeCom, DingTalk, or Lark, including requests about setting up bots, connecting to IM, or…
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…
worktree-dispatch
Delegate tasks to parallel worktree agents using worktrunk (wt). Use when asked to "spawn agents", "run in parallel", "delegate to worktrees", or split work…
video-script-builder
Convert a Chinese video voiceover script (verbatim transcript, spoken script) into a precise, renderer-bound storyboard specification for HyperFrames or Remotion, or revise an existing…
account-contact-shortlist
Contact data skill for Claude Code and Codex: build a ranked shortlist of decision-makers and contacts at a target company for outbound prospecting, deal…