tighten-file
File-level tightening pass on an instruction file (CLAUDE.md, skill, agent prompt, style guide) using `tighten-instruction` as the lens. TRIGGER when: user…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,390 results
fix-demos
Fix InboxMate demos flagged as NEEDS_FIX during QA review. Reads review issues from CRM, applies fixes via MCP (colors, prompts, knowledge, questions), and…
pytensor-workflows
Build, differentiate, compile, and debug PyTensor symbolic computations for models. Use for symbolic tensor shape or dtype errors, named dimensions, indexing…
nav-install-multi-claude
DEPRECATED. The multi-Claude orchestration scripts are deprecated in favor of native Claude Code Workflows; no installation is needed. Auto-invokes on "install…
harness-skill-creator
Use when bootstrapping or tightening the smallest harness-oriented skill from an existing repository, workflow, evaluation corpus, or harness-analysis chain.…
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
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…
agent-native-audit
Run comprehensive agent-native architecture review with scored principles
every-style-editor-2
Use this agent when you need to review and edit text content to conform to Every's specific style guide. This includes reviewing articles, blog posts,…
plan_review
Have multiple specialized agents review a plan in parallel
macos-resource-optimizer
macOS system resource optimization with 40 specialized agents for memory, disk, CPU, and process management
write-a-skill
Creates new agent skills with proper structure, progressive disclosure, and bundled resources. Use when the user wants to create, write, or build a new skill.
subagent-delegation
How to scope, brief and choose sub-agents when delegating work with the Agent tool - named vs forked agents, file ownership boundaries, model selection, and…
integrate-agentkit
Integrates AgentKit so an agent can create a connected account, authorize it, then call one tool through Scalekit. Use when the user wants AgentKit in app…
croc-strategy
CROC — Funding rate arbitrage. Scans all assets for extreme funding rates and enters against the crowd to collect funding payments while positioning for the…
grizzly-horribilis-strategy
GRIZZLY HORRIBILIS v2.1 — BTC Contrarian Sniper (recalibrated). Fades exhausted SM consensus moves on BTC with conviction-scaled leverage (7x at score 10-11,…
arena
Runs N parallel candidates at the same task, picks a base, and grafts the best parts of the others into it. Use for arena this, or when one attempt would lock…
claude code x - autonomous execution subagent
Execute Claude Code autonomously in the background for well-defined tasks, enabling parallel execution of up to 5 concurrent sessions while the user continues…
agent-tool-builder
Define agent tools using the fail-closed design pattern — unified name/schema/security/execution in one class, with three-layer execution (validate →…
adversarial-committee
Committee of personas with opposing propensities forcing genuine debate
data-flow
Rooms as pipeline nodes, exits as edges, objects as messages
manufacturing-intelligence
The slogan unpacked — seven readings of 'Manufacturing Intelligence'
agent-ui
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.…