decision-watcher
Watches for architectural decisions during a bencium-loop session and nudges the user to log them via /bencium-decide. Triggers when the conversation involves…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-08 00:04
Agents & models
25,900 results
dotnet-mvc
Expert guidance for developing ASP.NET Core MVC applications. Supports modern development patterns from .NET 6 (LTS) to .NET 10 (LTS), covering best practices for view models, tag helpers, view components, and server-side rendering.
bitlysis-ai-agents-llm
Apply best practices for LLM applications, AI agents, RAG pipelines, and evaluations in Bitlysis. Use when building agentic workflows, integrating LLM APIs,…
bitlysis-project-core
Apply Bitlysis core project standards — tech stack validation, naming conventions, quality gates, and specialist agent routing. Use this skill before starting…
engineering-mobile-app-builder
Use when Codex should act as the Mobile App Builder specialist from Agency Agents. Specialized mobile application developer with expertise in native…
engineering-prompt-engineer
Use when Codex should act as the Prompt Engineer specialist from Agency Agents. Specialist in crafting, testing, and systematically optimizing prompts for LLMs…
engineering-voice-ai-integration-engineer
Use when Codex should act as the Voice AI Integration Engineer specialist from Agency Agents. Expert in building end-to-end speech transcription pipelines…
senior-ml-engineer
ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs. Covers model deployment, feature stores, drift monitoring, RAG…
technical-artist
Use when Codex should act as the Technical Artist specialist from Agency Agents. Art-to-engine pipeline specialist - Masters shaders, VFX systems, LOD…
btst-ai-context
Patterns for registering page-level AI context in BTST plugin pages so the AI chat widget understands the current page and can act on it. Use when adding…
council
Summon a council of subagents to scrutinise a proposal, PR, idea, architecture decision, or any opinion. Each agent reviews from fresh context with a different…
github-cli
Encourages proactive use of GitHub CLI (gh) for gathering context on PRs, issues, comments, and repository information when working with GitHub-related tasks.
octocode
Drive the `octocode` CLI to research code from a terminal without wiring MCP — across LOCAL files and EXTERNAL GitHub/npm with one toolset. Use when the user…
octocode-loop
Use when a clear research or code goal needs grounded Act→Observe→Learn→Repeat loops over Octocode (MCP/CLI) until evidence converges — research, local…
carocut-shared-schema
Protocol definitions shared by all agents. Includes the resource type registry, storyboard schema, dispatch context schema, and amendment action types. Planner follows them when writing, Media validates against them when processing, Builder references them when implementing, and Orchestrator constructs them when dispatching.
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-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…
bridgic-amphibious
Build agents with the Bridgic Amphibious dual-mode framework — combining LLM-driven (agent) and deterministic (workflow) execution with automatic fallback and…
bridgic-llms
LLM provider initialization for bridgic projects. Use when: (1) initializing OpenAILlm, OpenAILikeLlm, or VllmServerLlm, (2) configuring…
jb-preferred-skills
Compatibility alias for jb-agent-env, JB's preferred agent-environment registry workflow. Use when the user refers to preferred skills, preferred skill…
claude-subagent-creator
Author, validate, and install custom Claude Code subagents as .claude/agents Markdown files. Use when the user asks to create a subagent, custom agent, or…
fan-out
Delegates work to bounded subagents and synthesizes their evidence. Use when asked to delegate, fan out, parallelize, or spawn subagents, or when a task splits…
blink-agent
List and manage Blink Claw agents in the workspace. Check agent status, set the active agent context, and bootstrap other agents with secrets. Enables the…
budget-grill
Wallet-aware grilling — interview me about a plan one question at a time, with each branch of the decision tree framed as a USDC cost impact