GaleHarnessCodingCLI

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

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.

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

Execute work efficiently while maintaining quality and finishing features

Refresh stale or drifting learnings and pattern docs in docs/solutions/ by reviewing, updating, consolidating, replacing, or deleting them against the current codebase. Use after refactors, migrations, dependency upgrades, or when a retrieved learning feels outdated or wrong. Also use when reviewing docs/solutions/ for accuracy, when a recently solved problem contradicts an existing learning, when pattern docs no longer reflect current code, or when multiple docs seem to cover the same topic and might benefit from consolidation.

Document a recently solved problem to compound your team's knowledge or update CONCEPTS.md, the project's shared domain vocabulary.

Start the dev server, open the feature in a browser, and iterate on improvements together. Manual invocation only — type /gh:polish to run it.

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

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.

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.

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 `gh:work` or `gh:review` offers a worktree option.

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.

GitNexus code intelligence skill for analyzing repos. Run gitnexus analyze, query, cypher, context, and impact commands against indexed repositories. Auto-detects and installs gitnexus@1.6.3 if missing.

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/.

Simplify and refine recently changed code for clarity, reuse, quality, and efficiency while preserving behavior.

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 gh:ideate, gh:brainstorm, or gh:plan need upstream grounding and no strategy doc exists yet.

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.

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.

Diagnose and configure compound-engineering environment. Checks CLI dependencies, plugin version, and repo-local config. Offers guided installation for missing tools. Use when troubleshooting missing tools, verifying setup, or before onboarding.

Check if the GaleHarnessCLI plugin is up to date and recommend the update command if not. Use when the user says "update gale harness", "check gale harness version", "gh update", "is gale harness up to date", "update gh plugin", or reports issues that might stem from a stale GaleHarnessCLI plugin version. This skill only works in Claude Code — it relies on the plugin harness cache layout.

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.

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.

生产级长期记忆系统 v5.0，支持 L2→L1/L0 自动分层与智能摘要提取

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.

Capture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.

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.

Run browser tests on pages affected by current PR or branch

Full autonomous engineering workflow

Create, share, view, comment on, edit, and run human-in-the-loop review loops over markdown documents via Proof, the collaborative markdown editor at proofeditor.ai ("Proof editor"). Use when the user wants to render or view a local markdown file in Proof, share markdown to get a URL, iterate collaboratively on a Proof doc, comment on or suggest edits in Proof, HITL a spec/plan/draft for human review, sync a Proof doc back to local, or work from a proofeditor.ai URL. Trigger on phrases like "view this in proof", "share to proof", "iterate with proof", or "HITL this doc", and on gh-brainstorm / gh-ideate / gh-plan handoffs for human review. Also match clear requests for a rendered/shared markdown review surface even if the user does not name Proof. Do not trigger on "proof" meaning evidence, math/logic proof, burden of proof, proof-of-concept, or bare "proofread this" requests where inline text review is expected.

Debug and fix iOS Swift/ObjC bugs with Morph-X blueprint, transform, audit, and memory fingerprinting to reduce template-code repetition risk.

Execute iOS Swift/ObjC work with Morph-X blueprint, transform, audit, and memory fingerprinting to reduce template-code repetition risk.

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, 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.

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.

Search Slack for interpreted organizational context -- decisions, constraints, and discussion arcs that shape the current task. Produces a research digest with cross-cutting analysis and research-value assessment, not raw message lists. Use when searching Slack for context during planning, brainstorming, or any task where organizational knowledge matters. Trigger phrases: 'search slack for', 'what did we discuss about', 'slack context for', 'organizational context about', 'what does the team think about', 'any slack discussions on'. Differs from slack:find-discussions which returns individual message results without synthesis.

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.

Report a bug in the compound-engineering plugin

Build and test iOS apps on simulator using XcodeBuildMCP. Use after making iOS code changes, before creating a PR, or when verifying app behavior and checking for crashes on simulator.

Sample skill

Sync GaleHarnessCLI skills with latest changes from the reference upstream repo. Use when you need to pull upstream updates, review what changed, apply gh: renames, and re-inject HKTMemory patches. Triggers: 'sync upstream', 'update skills', 'pull latest changes', 'upstream diff'.