block

Regenerate code after generator input, implementation, configuration, or tool-version changes.

Determine whether an existing migration can change and implement corrective migrations safely.

Run the repository generation pipeline and report source and generated changes.

Verify a branch, resolve in-scope failures, and prepare its PR description; publish only when requested.

Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

Write or update a PR description that lets reviewers judge the architecture and technical decisions without reading low-level code — high-level mechanism, mermaid diagrams, and a code-area map.

Rebuild ASIC-rs after changes to plugin/asicrs, sdk/rust, or server/sdk/v1/pb inputs.

Edit the development Compose stack or diagnose just dev startup and networking failures.

Help with Berd the desktop app: how-to, troubleshooting, settings, agents, skills, automations, projects, sessions, providers, connections, feedback, or berdctl. Use for app questions, not harness-specific behavior.

Use when adding, reviewing, configuring, graduating, or removing Berd experiments.

Run a long-lived command outside the current Berd turn and wake the owning session with actionable stdout. Use for builds, tests, reviews, deployments, polling, watchers, and other external waits.

Coordinate work across Berd sessions while keeping one conversation available to the user. Use for a long-lived orchestration session.

Read and hand off Buzz channels or threads in a private agent conversation using the installed Buzz CLI. Use when a user shares a buzz://message URL or Buzz channel UUID, asks to continue Buzz work privately, or explicitly approves a reply back to Buzz.

Create, edit, or inspect Berd agents/personas stored as Agent Markdown files with YAML frontmatter under ~/.agents/agents. Use when user needs to manage Berd agents or personas.

Use when adding, reviewing, designing, testing, or managing Assistive UX moments in Berd, including discover, suggest, and autoApply guidance, adaptive settings, behavior signals, retirement rules, or changes under src/shared/assistive-ux.

Use when adding, extending, modifying, or removing berdctl commands, verbs, nouns, schemas, help text, or any of the berdctl surface.

Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to…

Write and publish blog posts for the block/goose open source project

Use beads (bd) for persistent task tracking in coding projects. A git-backed issue tracker designed for AI agents with dependency graphs, hierarchical tasks, and multi-agent coordination.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Set up API integration with configuration and helper scripts

Comprehensive code review checklist for pull requests

Guidelines for writing effective tests in this project

Use Trailblaze or its CLI to author, debug, run, or test `.trail.yaml` trails, trailmaps, waypoints, and typed scripted tools; or drive iOS, Android, or web apps in natural language.

Turn Trailblaze App demo bundles (`demo.yaml`, `actions.ndjson`, screenshots, hierarchies) into runnable trails or add another platform's recording to an existing trail; verify by running.

Use when checking Trailblaze's out-of-box (OOB) experience against installed CLI behavior: validate the `trailblaze` skill, CLI UX, new-user friction, or a framework regression.

Write or update a devlog entry in the devlog directory. Use when the user asks to write a devlog, record a decision, document what happened, or says "write up what we did".

Analyzes branch changes to find edge cases, error states, and untested user flow paths in UI code. Use when the user says "find edge cases", "what am I missing", "edge cases", "test my flows", "what could go wrong", or wants to harden a feature before…

Create app e2e tests for the Goose desktop app using the Tauri app test driver. Use when the user wants to generate, write, or verify UI tests that run against the live app.

Senior engineer code review focused on catching issues before they become PR comments. Reviews only changed lines, categorizes issues by priority, and fixes them one by one. Use when the user says "code review", "review my code", "review this branch", or…

Create a GitHub PR from the current branch: handle uncommitted changes, generate a summary, and submit via gh CLI. Use when the user says "create PR", "open PR", "submit PR", "push PR", or wants to create a pull request.

Manage the SPECTRE comparison scripts, schema declarations, and descriptors for a service. Use when adding a route or dependency, or when a comparison fails on a difference that does not matter.

Migrate the next module of a service from the reference to the candidate. Use when asked to continue or advance the SPECTRE migration.

Write or update a `spectre/state.toml` file for a SPECTRE enabled migration of a service.

Enable, configure, and write tsk Go linters. Use when the user asks to enforce a convention or architectural constraint, to fix a kind of issue across the codebase, or to change .tsk/config.toml or a .tsk/*.ts linter.

Requirements-driven development framework. Use when setting up product/engineering requirements documents, checking traceability between requirements and code, verifying document consistency, or working on code in a repo that contains ANCHORS.md files (load…

Open markdown documents in Penpal for collaborative review. Use when you want a human to review a document, plan, or research artifact.

Monitor and respond to penpal document review comments on markdown files in thoughts/ directories.

Our preferred stars for celestial navigation and astronomical reference

Debugging guidelines and best practices

Invoke whenever writing, changing, reviewing, or sweeping tests in buzz-app. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand.

Build lightweight Buzz UI mockups and click-through prototypes using real components and fake data. Use for exploring layouts and user flows, not validating backend behavior.

Author, validate, consume, and review against a repo-local package of brand guidance. Use when the user wants to set up a .ghost package, write or update guidance nodes, gather brand context before generation, or assemble a review packet from ghost checks.

Create a GitHub pull request for the ghost repo from the current branch: inspect branch changes, handle scoped commits, verify release and ghost review requirements, push safely, and open a draft PR. Use when the user says "create PR", "open PR", "submit PR",…

Prepare and trigger QRGo releases. Use when the user asks to release QRGo, bump the app version, create a patch/minor/major release, trigger release CI, or publish the formula/cask.

Perform an QRGo self review or audit of current changes. Use when the user asks for a self review, audit, review of uncommitted changes, or a final quality pass before commit/PR in the QRGo repo.

Requirements-driven development framework. Use when setting up product/engineering requirements documents, checking traceability between requirements and code, verifying document consistency, or working on code in a repo that contains ANCHORS.md files (load…

Requirements-driven development framework. Use when setting up product/engineering requirements documents, checking traceability between requirements and code, verifying document consistency, or working on code in a repo that contains ANCHORS.md files (load…