everyinc/compound-engineering-plugin
Overview
This skill generates grounded, ranked improvement ideas for your current project and critically filters them to a concise set worth exploring. It focuses on scanning the codebase and existing learnings, producing a diverse candidate pool, applying adversarial critique, and returning the top survivors for user review. Use it before deep brainstorming or planning to pick high-leverage directions.
How this skill works
I first gather a quick code-and-docs grounding so every idea links to real signals rather than abstract advice. Then I run parallel ideation frames to produce many candidates, merge and dedupe them, and run adversarial filtering to reject weak options. The result is a short ranked set of survivor ideas, each with rationale, downsides, confidence, and complexity estimates for your review.
When to use it
- You want strong, repository-grounded improvement directions before detailed brainstorming
- You ask “what should I improve” or “give me ideas” for a project or subsystem
- You want surprising, high-leverage suggestions beyond obvious fixes
- You need a vetted short-list to choose a direction for planning
- You want the AI to proactively suggest which ideas merit deeper work
Best practices
- Provide an optional focus hint (concept, path, constraint, or volume) to bias results usefully
- Allow a short ground-truth scan step — I need to read top-level docs and layout to stay grounded
- Choose a survivor count or volume override if you need more or fewer ideas (e.g., top 3, top 7, 100 ideas)
- Answer the single select follow-up question when requested so I can continue the workflow
- Use this skill to pick directions; follow with a dedicated brainstorming or planning step for execution details
Example use cases
- “Surprise me with improvements to the plugin platform that are high-leverage and low-cost”
- “What should I improve in plugins/compound-engineering to help maintainers?”
- “Give me top 5 ideas focused on developer DX and onboarding”
- “Ideate on reducing test flakiness for this TypeScript project”
- “Generate candidates, prioritize them, then hand one to brainstorming for requirements”
FAQ
By default I generate many candidates across frames and present a ranked set of about 5–7 survivors; tell me a volume override if you need more or fewer.
Do you produce implementation plans or code?
No. This skill produces only ranked ideation results and critiques. Use the follow-up brainstorming and planning skills to turn a chosen idea into requirements and code.
30 skills
This skill resolves all TODO comments in parallel by orchestrating targeted subagents, reducing wait time and accelerating codebase completion.
This skill helps generate strongly grounded improvement ideas for the current project by analyzing codebase context and proposing ranked, actionable directions.
This skill coordinates multi-agent swarms using TeammateTool and Task system to orchestrate parallel reviews and divide-and-conquer workflows.
This skill helps you verify Claude Code Skill content accuracy by auditing SKILL.md and references, ensuring claims stay current.
This skill helps you design agent-native systems where agents are first-class, enabling atomic tools, loop execution, and open-ended capability.
This skill helps you manage Git worktrees safely and efficiently by creating, listing, switching, and cleaning up isolated environments via a unified workflow.
This skill automates web interactions using a CLI browser to fill forms, click elements, take screenshots, and extract data.
This skill crafts distinctive, production-grade frontend interfaces with bold aesthetics, delivering polished components, pages, or apps that avoid generic AI
This skill helps you quickly shape product ideas into durable requirements through guided collaboration and clear decisions.
This skill records a feature walkthrough video, uploads it, and adds an embedded link to the PR description for easy reviewer access.
This skill helps you create, edit, and share Proof markdown documents via web API or local bridge, enabling seamless collaboration.
This skill helps configure which review agents run for your project by auto-detecting stack and writing compound-engineering.local.md.
This skill resolves all PR comments in parallel by spawning dedicated agents for each thread, accelerating review feedback resolution.
This skill helps you build type-safe, modular, testable LLM apps in Ruby using DSPy.rb to define signatures, tools, and optimized prompts.
This skill helps you write clean, production-ready Ruby gems following Andrew Kane's patterns with zero or minimal dependencies.
This skill reviews and edits copy for Every's style guide, delivering precise line-by-line corrections to improve clarity and consistency.
This skill automates rclone uploads, syncing, and remote storage management across S3, Cloudflare R2, Backblaze B2, Google Drive, and more, ensuring reliable
This skill personalizes coding tutorials using your real codebase to build a progressive, trackable learning path with spaced repetition.
This skill applies DHH's Rails conventions to Ruby and Rails code, emphasizes fat models, RESTful controllers, and Turbo-driven views for clarity.
This skill helps you generate and edit images using the Gemini API, enabling prompts-driven visuals, style transfers, and multi-turn refinements.
This skill enhances an existing plan by assigning parallel research agents to each section, delivering depth, best practices, and concrete implementation
This skill orchestrates a full autonomous engineering workflow, planning, deepening plans when needed, and executing end-to-end implementation across
This skill converts feature descriptions into well-structured project plans that follow conventions and accelerate team alignment and delivery.
This skill validates and preps project docs for GitHub Pages deployment, ensuring HTML existence, JSON validity, and ready workflow setup.
This skill builds, installs, and tests iOS apps on a simulator using XcodeBuildMCP, captures logs and screens to verify app behavior.
This skill helps you execute work plans efficiently, shipping complete features while preserving quality and aligning with project patterns.
This skill runs end-to-end browser tests on pages affected by a PR or branch using the agent-browser CLI.
This skill automatically fixes outdated SKILL.md files by analyzing interactions, proposing precise edits, and applying changes with optional commits.
This skill orchestrates swarm-enabled autonomous engineering workflows to plan, deepen, and execute tasks in parallel, accelerating delivery and reducing risks.
This skill helps you brainstorm effectively before features, clarifying intent, exploring options, and guiding design decisions to align with user goals.
