310 tagged open-source, measured the same way as everything else here.
Browse within: claude-code-skill 54marketing-automation 32ai-marketing 29ai-ops 27cybersecurity 27devsecops 27gemini 24meta-prompting 24ai-assisted 23fit-files 23fitness 23workout 23ai-development 16project-template 16
Agent
Read-only review agent for axial-decomposition drift. Parses the project's axial ADR (axial: true frontmatter) and reviews a diff or spec for drift along the non-primary axis (N×M trap). Emits Conventional Comments findings tagged with the canonical target-axis-trap class. Invoked by /spec (Step 4 — Expert Review) or…
Agent Codex
You are a research analyst. Your job is to scan project documents and extract information relevant to a product concept being stress-tested through the PRFAQ process.
Agent Codex
You are a market research analyst. Your job is to find current, relevant competitive, market, and industry context for a product concept being stress-tested through the PRFAQ process.
SafetyMP/Autonomous-EHS-Management
Agent Cursor
Defines site gates and SLOs, runs the current oracle, and independently reviews evidence.
SafetyMP/Autonomous-EHS-Management
Agent Cursor
Decomposes a verified corporate handoff into ADR work and integrates site evidence.
SafetyMP/Autonomous-EHS-Management
Agent Cursor
Implements one ADR-scoped packet and returns exact command evidence.
Agent
General development agent — TDD, code quality, architecture fitness, approach-first, debug checkpoint, scope guardian. Use with claude --agent dev for feature work outside sprints.
Agent
Sprint item executor — TDD implementation agent. Receives a spec, runs in an isolated git worktree, writes tests, implements, and reports done or blocked.
Agent
Sprint orchestrator — lightweight state machine that routes to specialist agents per phase. Use with claude --agent sprint-master or via sprint-runner.
rogerSuperBuilderAlpha/hult-cohort-program
Agent
You are a development agent.
rogerSuperBuilderAlpha/hult-cohort-program
Agent
You are a QA agent. Assume the developer missed edge cases. Given this PR diff and the app's stated requirements.
rogerSuperBuilderAlpha/hult-cohort-program
Agent
You are a research agent. Do not write production code. Goal: map this codebase for a new contributor in 30 minutes. Output.
Agent Claude Code
Reviews code changes for quality, accessibility, and ImpactMojo conventions. Use PROACTIVELY when reviewing PRs, checking for bugs, or validating implementations before merging.
Agent Claude Code
Audits content consistency across the platform — counts, links, search index, docs. Use when verifying content integrity, before releases, or when running /project:audit.
Agent
Dispatch to stress-test a product, pitch, landing page, or message against a specific target customer before spending money or talking to real ones - when the founder says "react as my customer", "would they buy this", "is this message clear", or wants Mom-Test-honest feedback. Simulates a specific [ICP] reacting…
Agent
Dispatch when a first-time founder is stuck, overwhelmed, unsure what to do next, or spinning on busywork - the default advisor for routing, unblocking, and keeping the founder honest about the riskiest assumption. Use when they ask "what should I do next", "I'm overwhelmed", "am I working on the right thing", or are…
Agent
Dispatch to red-team a pitch, deck, model, or market claim before a real investor sees it - when the founder says "poke holes in this", "is this fundable", "what will they ask", or is preparing to fundraise. A sharp seed/VC who demands evidence, attacks the numbers, and surfaces the questions a real investor will ask.…
Agent
Backend specialist. Reliable APIs, DB schemas, server logic. Zod validation, full error handling, no hardcoded secrets.
Agent
Premium UI specialist. Builds production-grade React/Next.js with taste-soft-skill — glassmorphism, spring motion, refined typography. Auto-invoked for UI changes.
Agent
You create assets that look like they were made by a designer who codes. One job: make ystack look real, credible, and worth starring. No AI slop. No stock photo energy. No generic gradients. No corporate speak.
Agent Claude Code
Chief executive agent. Assesses the product, makes strategic decisions, defines priorities, and writes actionable plans to the CEO log. Does not write code or delegate — produces strategic output that the orchestrator uses to drive implementation.
Agent Claude Code
Product discovery and improvement specialist. Runs independently to analyze the codebase, MCP ecosystem, and developer experience, then identifies improvement opportunities, new feature ideas, integration strategies, and overall ways to make Ember better. Browses the internet to research the MCP ecosystem and…
Agent Claude Code
Test writing specialist for vitest unit tests. Use after implementation is complete to add test coverage for new features, database queries, tool handlers, formatters, and utilities.
nextgentrainingacademy88-max/open-generative-studio
Agent
This library uses next-themes to manage light and dark modes. For the theme switching buttons to work correctly, you must wrap your application with the provided AgentThemeProvider.