@everyinc

ce-demo-reel captures real product usage (CLI, web UI, API calls) as visual evidence for pull requests, rejecting test output substitutes and enforcing credential hygiene in recordings.

every-style-editor provides a four-phase systematic review process (assessment, line edit, mechanics check, recommendations) for validating copy against every's style conventions. structured output format with detailed corrections, rule citations, and recurring issue patterns.

ce-gemini-imagegen wraps the Gemini API for image generation and editing, covering resolution/aspect ratio selection, multi-turn refinement, and grounding with google search. includes working code samples and format gotchas.

ce-code-review dispatches layered persona agents to review code diffs, merges findings by severity and autofix class, and routes work to downstream resolvers or in-skill fixers based on mode (interactive, autofix, report-only, headless).

ce-debug guides systematic root cause analysis before proposing fixes, emphasizing causal chain validation and test-first discipline with single-change hypothesis testing.

andrew-kane-gem-writer codifies structural patterns from 100+ production gems, emphasizing minimal dependencies and explicit code over metaprogramming. covers entry point organization and philosophical scaffolding for ruby gem development.

git-worktree manages parallel development branches via worktree creation, listing, switching, and cleanup with interactive confirmations and automatic .gitignore/.env handling.

ce-strategy guides creation and maintenance of STRATEGY.md, a structured product anchor capturing problem, persona, success metrics, and investment priorities. downstream skills depend on it for grounding.

ce-slack-research queries slack message history to extract organizational decisions and discussion patterns, returning a ranked digest with source attribution and cross-cutting analysis.

ce-commit crafts a single well-formed git commit from working-tree changes. gathers context via git commands to infer repo state, detects unborn repos and detached heads, then stages and commits with a value-communicating message.

ce-report-bug collects structured bug details from users via platform-native questioning tools and creates github issues. procedure is sequential but incomplete. lacks explicit error handling and output validation.

ce-optimize runs metric-driven iterative loops to converge on measurable improvements. covers goal definition, measurement scaffolding, and parallel experiment orchestration across multiple platform harnesses.

dhh-rails-style codifies 37signals conventions for rails development: fat models, thin controllers, vanilla tooling (minitest, fixtures, solid queue), and rest-first design. emphasizes clarity and domain richness over framework abstractions.

ce-plan transforms requirements into implementation-ready structured plans for software and non-software tasks. it enriches brainstorm outputs with detailed execution paths and enforces mandatory handoff workflows.

ce-worktree automates isolated git worktree creation with environment variable copying, direnv trust management, and cross-platform script invocation to avoid disrupting the main checkout.

agent-browser wraps chromium automation via cdp for ai agents navigating and interacting with web pages through snapshot-driven element references. installation and core workflow documented but lacks depth on error handling.

ce-release-notes queries github release history for the compound-engineering plugin, summarizing recent releases or answering targeted questions about when features were introduced.

ce-compound-refresh audits documentation against codebase state, identifying stale or drifted learnings and refreshing dependent pattern docs. supports interactive and headless modes for different operator contexts.

ce-polish-beta stages a dev server and opens a feature in the browser for iterative feedback and fixes. it supports branch checkout, launch configuration, and project auto-detection.

ce-resolve-pr-feedback evaluates and fixes pr review comments by spawning parallel agents per thread, with explicit guidance on when to decline fixes and handling untrusted input.

ce-setup guides users through compound-engineering environment diagnosis and configuration via platform-native question tools, detecting plugin versions and running health checks with fallbacks for constrained environments.

frontend-design guides production-grade web interface creation across landing pages, apps, and dashboards. emphasizes design intentionality over generic ai output, with context detection, planning, build, and visual verification as core stages.

ce-product-pulse aggregates usage, performance, and error signals over a specified time window and renders a single-page report to docs/pulse-reports/, surfacing key insights in chat without mutating external systems.

ce-riffrec-feedback-analysis routes riffrec session bundles (screen, voice, events) into three analysis paths: setup guidance, quick bug reports, or extensive multi-issue analysis with downstream brainstorm handoff. depends on reference files not included in this skill definition.

ce-ideate generates and ranks improvement ideas for exploration. it precedes brainstorm and produces ideation artifacts without requirements or code, relying on platform-specific blocking question tools to gather context.

gemini-imagegen wraps google's gemini api for text-to-image generation and editing with configurable resolution and aspect ratios, but lacks procedural clarity and failure handling.

ce-test-browser orchestrates end-to-end browser tests against pages changed in a pr or branch, routing all automation through the agent-browser cli. requires local dev server and git repo setup.

rclone provides a setup check and partial procedure for file transfers across cloud providers, but lacks complete operation workflows, clear decision logic, and robust error handling documentation.

ce-dhh-rails-style captures 37signals philosophy for vanilla rails development, emphasizing domain models, crud controllers, and minimal dependencies over service objects and redis.

ce-doc-review dispatches parallel persona agents to surface role-specific document issues, with configurable routing for findings through safe auto-fixes, per-finding walkthroughs, or open-question tracking.

ce-agent-native-architecture outlines design principles for applications where agents operate autonomously via tools rather than traditional function calls, emphasizing prompt-driven behavior and emergent capabilities.

charlie teaches unit economics and capital discipline for bootstrapped startups through conceptual frameworks, but lacks decision-making procedures and executable guidance for actual financial operations.

ce-work-beta attempts work execution with optional codex delegation for token efficiency, but the specification is incomplete and lacks procedural clarity beyond input parsing declaration.

setup is a placeholder skill that redirects users to ce:review for automated review agent selection and project context files. it reserves namespace for future configuration features.

Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that…

Execute a plan or concrete work prompt end-to-end. Use when implementing from a plan document, a spec path, or a clear build request; use ce-debug for…

Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch…

Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decide what to…

Simplify recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. Use for tidy/refactor passes; use ce-debug for bugs.

Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.

Publish, read, comment on, or edit markdown in Proof. Use for Proof links, sharing specs/plans/drafts, or publish handoffs from planning workflows; avoid…

Build and test iOS apps on simulator with XcodeBuildMCP.

Check if the compound-engineering plugin is up to date and recommend the update command if not. Use when the user says "update compound engineering", "check…

Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before,…

Clean up local branches whose remote tracking branch is gone. Use when the user says "clean up branches", "delete gone branches", "prune local branches",…

Run comprehensive agent-native architecture review with scored principles

Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components,…

compound-docs — an installable skill for AI agents, published by everyinc/compound-engineering-plugin.

Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing…

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status…

This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design…

Create, edit, comment on, share, and run human-in-the-loop iteration loops over markdown documents via Proof's web API. Use when asked to "proof", "share a…

This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents,…

document-review — an installable skill for AI agents, published by everyinc/compound-engineering-plugin.

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying…