@skills · Owner

Agent skills by everyinc

53 skills indexed from github.com/everyinc. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• agent-only-skill · Skill · 24,076 stars

  An agent-only skill not intended for direct user invocation

• ce-babysit-pr · Skill · 24,076 stars

  Babysits an open GitHub PR until merge-ready. Use when asked to watch a PR over time — not for one-shot comment resolution or one CI failure. GitHub (incl.

• ce-brainstorm · Skill · 24,076 stars

  Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, scope what to build, or needs co

• ce-code-review · Skill · 24,076 stars

  Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked to review code. Use when the user asks to apply this revie

• ce-commit · Skill · 24,076 stars

  Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate mes

• ce-commit-push-pr · Skill · 24,076 stars

  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.

• ce-compound · Skill · 24,076 stars

  Document a solved problem as a durable repo learning. Use when verified work produced non-obvious reasoning absent from its final code, tests, or existing

• ce-compound-refresh · Skill · 24,076 stars

  Refresh the repo's captured learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general r

• ce-debug · Skill · 24,076 stars

  Diagnosis loop for bugs and failing behavior. Use when asked to debug or fix failing or slow behavior.

• ce-doc-review · Skill · 24,076 stars

  Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.

• ce-dogfood · Skill · 24,076 stars

  Hands-off, diff-scoped browser QA of the active branch: maps user flows, drives a real browser, autonomously fixes small breakages with regression tests an

• ce-explain · Skill · 24,076 stars

  Explain how something works and why it has its current shape, grounding behavior in evidence and separating documented rationale from inference. Use when u

• ce-handoff · Skill · 24,076 stars

  Create a session handoff for another agent, or resume, find, and read any user-selected continuity source. Use when work or conversation must continue with

• ce-ideate · Skill · 24,076 stars

  Generate and evaluate grounded ideas. Use when the user wants ideas, improvements, or surprising directions before choosing one to develop. Not for refinin

• ce-optimize · Skill · 24,076 stars

  Optimize a named target with a measured loop: attribute a workload's cost, or score variants and keep winners. Use when a working system's metric should mo

• ce-plan · Skill · 24,076 stars

  Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requir

• ce-polish · Skill · 24,076 stars

  Polish a working feature through user-directed live browser feedback. Use when a functional feature needs focused UX refinement before shipping.

• ce-pov · Skill · 24,076 stars

  Judge a supplied subject against the project's evidence and constraints, returning a supported position, tradeoffs, and conditions. Use when assessing an e

• ce-product-pulse · Skill · 24,076 stars

  Generate time-windowed product pulse reports from configured signals.

• ce-promote · Skill · 24,076 stars

  Draft launch or promotion copy for a shipped feature.

• ce-proof · Skill · 24,076 stars

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

• ce-resolve-pr-feedback · Skill · 24,076 stars

  Resolve PR review feedback. Use when addressing feedback already left on a PR. Not for reviewing the code before feedback exists; that is ce-code-review.

• ce-retune · Skill · 24,076 stars

  Retune a skill corpus for a new model, measurement-first: mine the run archive for a baseline, establish a noise floor, audit the corpus adversarially, the

• ce-riffrec-feedback-analysis · Skill · 24,076 stars

  Analyze recorded product feedback into evidence for bugs and requirements. Use when a Riffrec capture or other screen, voice, or notes artifact needs inter

• ce-setup · Skill · 24,076 stars

  Check Compound Engineering health and repo-local config.

• ce-simplify-code · Skill · 24,076 stars

  Simplify settled, recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. Use after implementation and before review;

• ce-strategy · Skill · 24,076 stars

  Create or update STRATEGY.md. Use when starting a product, adding a strategy doc to an existing repo, changing direction or roadmap, or when ce-ideate, ce-

• ce-sweep · Skill · 24,076 stars

  Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged

• ce-test-browser · Skill · 24,076 stars

  Run browser tests for pages affected by the current branch or PR. Use when asked to run or check browser tests for the current change.

• ce-test-xcode · Skill · 24,076 stars

  Test iOS apps in a simulator with XcodeBuildMCP. Use when iOS changes need simulator evidence before handoff.

• ce-work · Skill · 24,076 stars

  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 open

• ce-worktree · Skill · 24,076 stars

  Set up isolated git worktrees — create a new branch for fresh work, or attach a worktree to an existing branch, PR, or commit. Use when starting isolated w

• claude-only-skill · Skill · 24,076 stars

  A skill restricted to Claude Code only

• compound-engineering-plugin · Collection · 24,076 stars
• custom-paths · Collection · 24,076 stars
• custom-skill · Skill · 24,076 stars
• custom-skills · Collection · 24,076 stars
• default-skill · Skill · 24,076 stars
• disabled-skill · Skill · 24,076 stars

  A skill with model invocation disabled

• fixtures · Collection · 24,076 stars
• lfg · Skill · 24,076 stars

  Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins. Use only when the user explicitly asks to build or ship something autono

• sample-plugin · Collection · 24,076 stars
• skill-one · Skill · 24,076 stars

  Sample skill

• skills · Collection · 24,076 stars
• skills · Collection · 24,076 stars
• skills · Collection · 24,076 stars
• tests · Collection · 24,076 stars
• .agents · Collection
• ce-bakeoff · Skill

  Develop independent competing solutions to a defined brief, compare them, and synthesize a winning approach. Use when choosing well requires developing alt

• ce-noslop · Skill

  Rewrite, check, or draft prose so it reads plainly on the first read and carries no AI writing patterns, keeping every fact the source states. Use when the

• ce-prototype · Skill

  Build a throwaway prototype to answer how something should work, feel, or read. Use when committing the wrong answer would be expensive to unravel and a ch

• ce-skill-work · Skill

  Applies this repository's skill-authoring standard as a procedure. Use for any change to, or judgment about, a file under skills/** — a SKILL.md, a referen

• skills · Collection

Browse the @skills marketplace