37,011 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Use when a user's request is vague, ambiguous, or underspecified. Runs recon-first clarification — codebase exploration before questions, then one bundled question round with defensible defaults — and outputs a Goal Contract for the durable /goal runtime. Triggers on "I want to...", "I need...", "let's build...", "can…
Skill Claude CodeCodex
A guide for turning a product or feature idea into a structured product requirements document (PRD), or reviewing and improving an existing one. It is aimed at people who are not product managers.
AkoliteZA/hermes-agent-idea-workflow
Skill Claude CodeCodex
Use when running the full idea workflow: capture a rough idea, expand it into design/UI/implementation docs, research similar products, and generate build-ready Markdown artifacts.
GTM-Strategist/gtm-strategist-skills
Plugin Claude Code
Bundles 12 skills · 1,013 tokens together
12 GTM skills based on the GTM Strategist methodology by Maja Voje. Covers the complete go-to-market journey from foundations to scaling sales — 100 tasks across 12 phases.
prassanna-ravishankar/repowire
Plugin Claude Code
Bundles 14 skills, 1 plugin · 601 tokens together
Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.
Agent Claude Code
You are a spec tasks document expert. Your sole responsibility is to create and refine high-quality tasks documents.
Skill Codex
A text format for organising ideas in a 3×3 grid, with one central topic and eight surrounding directions. It uses short titles, fixed Chinese-character layouts, and optional grid-reading orders.
Skill Claude CodeCodex
Enables a secondary AI model to advise the primary when it gets stuck, fails repeatedly, or needs upfront planning.
Skill Claude CodeCodex
Advanced om-auto-continue-pr for PRs started by om-auto-create-pr-loop — claims the PR, resumes from the first non-done PLAN.md Tasks row in an isolated worktree, keeps the per-step commit and checkpoint discipline (integration tests + screenshots for UI), runs the full gate at completion, keeps spec-only design PRs…
Plugin Claude Code
Bundles 26 skills, 2 commands, 4 agents · 3,066 tokens together
4-phase epistemic transaction workflow (PREFLIGHT → CHECK → POSTFLIGHT → POST-TEST) with noetic firewall, dual-track calibration, and grounded verification for Claude Code.
Skill Claude CodeCodex
Inspect or show a local Codex task trajectory, including turns, approximate model steps, assistant messages, reasoning summaries, tool calls, failures, compaction, token usage, and timing. Use when the user asks for a trajectory, execution trace, task timeline, slow-tool analysis, current-task timing distribution…
Skill Claude Code
Use when implementing a task - follow the plan, check ACs, track progress.
Skill Claude CodeCodex
Use when coordinating multiple coding agents, delegating independent software work, managing OpenCode Ensemble teams, choosing teammate roles or models, reviewing teammate output, or deciding whether parallel execution is appropriate.
Skill Claude Code
Use this skill for the task format and the spec-driven development reference — the spec→build→document cycle and spec file structure — and for inspecting or editing existing tasks in .md files (read, edit, rewrite, list, find, filter, summarize, check status). Use when writing a spec or looking up the task/spec…
Skill Claude CodeCodex
An agent skill for planning trips from user constraints, researching places and restaurants through Dianping and Xiaohongshu, and building a mobile-friendly interactive map with a timeline. Dianping is a Chinese restaurant and local-services review platform; Xiaohongshu is a Chinese social platform.
Skill Claude CodeCodex
Turn a business question into the exact numbers that would answer it, before any are computed.
AtlasCloudAI/awesome-seedance-2.5-prompts-skills
Skill Claude CodeCodex
Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0 today, with a Seedance 2.5 route when available. Use for consistent people, products, objects, food, or scenes; storyboard-to- video; reference-to-video; first-and-last-frame image-to-video; extensions; and Atlas Cloud…
Command Claude Code
You are tasked with analyzing the software project to determine its current status, readiness for deployment, and any remaining development work. Follow these steps carefully to provide a comprehensive assessment.
Skill Claude CodeCodex needs its repo
A tool that turns a written approval process into BPMN 2.0 workflow data for Flowable, a system for running business processes, and creates it in JeecgBoot through an API.
Skill Claude CodeCodex
Corporate-governance practice playbook: board composition, three lines of defense, audit/compensation/nomination committee operations, independent-director governance, stakeholder communication, IPO governance upgrade, and family-business professionalization. Use for board-structure design, independent-director…
Command Claude Code
Multi-LLM workflow orchestrator with lineage-weighted quorum. Routes to plan / implement / major-bug / minor-bug modes. Builds XML packs, fans to 3 reviewers (1 codex + 1 gemini + 1 opencode), waits event-driven (zero token burn) for ## DONE, loops on disagreement. Auto-modifies git; asks before merge.
johnku2011/boilerplates-with-ai-skills
Skill Claude CodeCodex
Use before scaffolding a bwai project — runs the full startup-goal workflow then recommends the right boilerplate and outputs the exact bwai new command to run.
Skill Claude Code
Creates C4 architecture diagrams for designing, documenting, or understanding software architecture. Use when working through system design, mapping existing codebases, or visualizing structure at any level from system landscape down to code.
shinpr/ai-coding-project-boilerplate
Skill Claude Code
Selects implementation strategy (vertical slice, horizontal, or hybrid) with risk assessment. Use when planning feature implementation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: