opencode-setup

Document a recently solved problem to compound your team's knowledge. Use when a bug is fixed or a problem is solved, especially after phrases like 'that worked', 'it's fixed', 'working now', or 'problem solved'. Also invoke manually with /ce-compound to capture any resolved issue.

Simplify and refine recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. Use when simplifying code, reducing complexity, cleaning up after implementation, or when the user says 'simplify this', 'clean up this code', or 'reduce complexity'.

Run browser tests on pages affected by current PR or branch. Use when running browser tests, testing pages affected by a PR, or when the user says 'test this in the browser', 'run browser tests', or 'check this page'.

Execute work efficiently while maintaining quality and finishing features. Use when implementing plans, shipping features, or executing work defined in a plan doc. Invoke when the user says 'do the work', 'implement this', 'execute the plan', or when ce-brainstorm or ce-plan hand off to execution.

Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.

Run comprehensive agent-native architecture review with scored principles

Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build. Also use when a user describes a vague or ambitious feature request, asks 'what should we build', 'help me think through X', presents a problem with multiple valid solutions, or seems unsure about scope or direction — even if they don't explicitly ask to brainstorm.

Clean up local branches whose remote tracking branch is gone. Use when the user says "clean up branches", "delete gone branches", "prune local branches", "clean gone", or wants to remove stale local branches that no longer exist on the remote. Also handles removing associated worktrees for branches that have them.

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.

Commit, push, and open a PR with an adaptive, value-first description. Use when the user says "commit and PR", "push and open a PR", "ship this", "create a PR", "open a pull request", "commit push PR", or wants to go from working changes to an open pull request in one step. Also use when the user says "update the PR description", "refresh the PR description", "freshen the PR", "rewrite the PR body", "write a PR description", "draft a PR description", or "describe this PR" — the skill will produce a description without committing or pushing if that is all the user wants. Produces PR descriptions that scale in depth with the complexity of the change, avoiding cookie-cutter templates.

Create a git commit with a clear, value-communicating message. Use when the user says "commit", "commit this", "save my changes", "create a commit", or wants to commit staged or unstaged work. Produces well-structured commit messages that follow repo conventions when they exist, and defaults to conventional commit format otherwise.

Refresh stale learning docs and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, replacing, or deleting the drifted ones. Trigger this skill when the user asks to refresh, audit, sweep, clean up, or consolidate stale docs in docs/solutions/ (phrases like "refresh my learnings", "audit docs/solutions/", "clean up stale learnings", "consolidate overlapping docs", "compound refresh", "/ce-compound-refresh"), or when ce-compound has just captured a new learning and flagged a specific older doc in docs/solutions/ as now inaccurate or superseded — invoke with the narrow scope hint ce-compound provides. Also trigger when the user points at a specific learning or pattern doc under docs/solutions/ and calls it stale, outdated, overlapping, or drifted. Do not trigger for general refactor, migration, debugging, or code-review work unless the user has explicitly directed attention to docs/solutions/ itself.

Systematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.

This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creating models, controllers, or any Ruby file. Triggers on Ruby/Rails code generation, refactoring requests, code review, or when the user mentions DHH, 37signals, Basecamp, HEY, or Campfire style. Embodies REST purity, fat models, thin controllers, Current attributes, Hotwire patterns, and the "clarity over cleverness" philosophy.

Review requirements or plan documents using parallel persona agents that surface role-specific issues. Use when a requirements document or plan document exists and the user wants to improve it.

Build web interfaces with genuine design quality, not AI slop. Use for any frontend work - landing pages, web apps, dashboards, admin panels, components, interactive experiences. Activates for both greenfield builds and modifications to existing applications. Detects existing design systems and respects them. Covers composition, typography, color, motion, and copy. Verifies results via screenshots before declaring done.

Generate and critically evaluate grounded ideas about a topic. Use when asking what to improve, requesting idea generation, exploring surprising directions, or wanting the AI to proactively suggest strong options before brainstorming one in depth. Triggers on phrases like 'what should I improve', 'give me ideas', 'ideate on X', 'surprise me', 'what would you change', or any request for AI-generated suggestions rather than refining the user's own idea.

Run metric-driven iterative optimization loops. Define a measurable goal, build measurement scaffolding, then run parallel experiments that try many approaches, measure each against hard gates and/or LLM-as-judge quality scores, keep improvements, and converge toward the best solution. Use when optimizing clustering quality, search relevance, build performance, prompt quality, or any measurable outcome that benefits from systematic experimentation. Inspired by Karpathy's autoresearch, generalized for multi-file code changes and non-ML domains.

Create structured plans for any multi-step task -- software features, research workflows, events, study plans, or any goal that benefits from structured breakdown. Also deepen existing plans with interactive review of sub-agent findings. Use for plan creation when the user says 'plan this', 'create a plan', 'write a tech plan', 'plan the implementation', 'how should we build', 'what's the approach for', 'break this down', 'plan a trip', 'create a study plan', or when a brainstorm/requirements document is ready for planning. Use for plan deepening when the user says 'deepen the plan', 'deepen my plan', 'deepening pass', or uses 'deepen' in reference to a plan. For exploratory or ambiguous requests where the user is unsure what to do, prefer ce-brainstorm first.

[BETA] Start the dev server, open the feature in a browser, and iterate on improvements together.

Generate a time-windowed pulse report on what users experienced and how the product performed - usage, quality, errors, signals worth investigating. Use when the user says 'run a pulse', 'show me the pulse', 'how are we doing', 'weekly recap', 'launch-day check', or passes a time window like '24h' or '7d'. Configures via .compound-engineering/config.local.yaml and saves reports to docs/pulse-reports/.

Resolve PR review feedback by evaluating validity and fixing issues in parallel. Use when addressing PR review comments, resolving review threads, or fixing code review feedback.

Discover session files for a repo across Claude Code, Codex, and Cursor, and extract session metadata (timestamps, branch, cwd, size, platform). Invoked by session-research agents — not intended for direct user queries.

Search and ask questions about your coding agent session history. Use when asking what you worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior sessions, previous attempts, or past investigations — even without saying 'sessions' explicitly.

Create or maintain STRATEGY.md - the product's target problem, approach, users, key metrics, and tracks of work. Use when starting a new product, updating direction, or when prompts like 'write our strategy', 'update the roadmap', 'what are we working on', or 'set up the strategy doc' come up. Also triggers when ce-ideate, ce-brainstorm, or ce-plan need upstream grounding and no strategy doc exists yet.

[BETA] Execute work with external delegate support. Same as ce-work but includes experimental Codex delegation mode for token-conserving code implementation.

Create an isolated git worktree for parallel feature work or PR review. Use when starting work that should not disturb the current checkout, or when `ce-work` or `ce-code-review` offers a worktree option.

Full autonomous engineering workflow