phatblat

Claude Code workflow tips from Boris Cherny (creator of Claude Code) and the Claude Code team. Use when: setting up Claude Code, optimizing workflows, running parallel sessions, configuring CLAUDE.md, using skills/commands, subagents, hooks, MCP integrations, or learning best practices. Covers: git worktrees, plan mode, verification, permissions, Slack MCP, BigQuery, prompting tips, plugins, custom agents, sandboxing, keybindings, status lines, output styles, customization, /simplify for code quality, /batch for parallel code migrations, /loop for scheduled tasks, code review agents, /btw for mid-task questions, /effort max reasoning, remote control sessions, voice mode, setup scripts, session naming, /color, PostCompact hook, auto mode, /schedule cloud jobs, iMessage plugin, auto-memory, and auto-dream, mobile app, session teleporting, Cowork Dispatch, Chrome extension, Desktop app, /branch forking, --bare SDK startup, --add-dir multi-repo, --agent custom agents, /voice input.

The English summary is being prepared. Showing the original description.

Turn an idea into a Conventional Docs Decision, then a Plan: classify the request, explore options and risks through dialogue, then commit a numbered Decision that review, prototypes, and acceptance move through. Use PROACTIVELY before any creative work — new features, new subsystems, interface or dependency changes, or any open-ended design question ("what are the options", "how should I approach", "should I use X or Y", "help me decide", "write a decision", "ADR").

The English summary is being prepared. Showing the original description.

Use when implementation is complete and you need to decide how to integrate the work — presents structured options for merge, PR, keep, or discard

The English summary is being prepared. Showing the original description.

Investigate and fix failing CI. Takes a PR reference, one or more CI run/job URLs, or freeform text describing where the failures are, then enumerates failing workflows/jobs/steps, determines the root cause (often one shared cause behind several red checks), proposes a fix plan, applies code changes, commits, pushes, watches the new runs, and repeats until checks pass. Use when the user says "fix CI", "CI is red", "checks are failing", "the build is broken on my PR", "fix the failing jobs", or pastes a failing CI run URL. Do NOT use for authoring new workflows, or for read-only diagnosis with no fix intent — use gha-log-reader for that.

The English summary is being prepared. Showing the original description.

Apple's native `container` CLI for running Linux containers as lightweight per-container VMs on macOS 26 Apple Silicon. Load when creating, configuring, managing, backing up, sharing, or deleting containers, images, volumes, or networks with `container`; when `container` or `container system start` fails; or when choosing between `container` and Docker/Podman/Colima on a Mac.

The English summary is being prepared. Showing the original description.

Search the web and open-source code for library usage, API syntax, and documentation via Exa. Use this whenever verifying an API signature, looking up how a library is used, checking a config file format, or resolving an error from a third-party dependency -- including when you think you already know the answer, since library APIs drift. Also use for questions documentation cannot answer: release timing, breaking changes, "is X still maintained", licensing, security advisories, and ecosystem comparisons.

The English summary is being prepared. Showing the original description.

Use when you have a written implementation plan to execute in a separate session with review checkpoints

The English summary is being prepared. Showing the original description.

Retrieve current documentation, API references, and code examples for any library, framework, SDK, CLI tool, or cloud service — including well-known ones like React, Next.js, Prisma, Django, or Spring Boot. Use for API syntax, configuration options, version migrations, setup instructions, and library-specific debugging, even when you already think you know the answer: training data on API details and signatures is frequently outdated. Prefer this over web search for library documentation.

The English summary is being prepared. Showing the original description.

Check GitHub Actions CI status for PRs and branches. Use when the user asks "did CI pass", "check status", "what failed", "are checks green", "PR checks", "CI status", "workflow status", "re-run jobs", or wants a quick summary of GitHub Actions runs for a PR or the current branch.

The English summary is being prepared. Showing the original description.

Diagnoses failing GitHub Actions runs by reading logs, identifying the root cause, and suggesting fixes. Use this skill whenever a user shares a GHA run URL, pastes runner log output, mentions a failing workflow, asks why a CI job is broken, or says anything like "my GHA is failing", "workflow failed", "can you check my run", or "CI is broken". Also trigger when raw log text is detected in the conversation that appears to come from a GitHub Actions runner. Do NOT use for general GHA workflow authoring questions, YAML formatting help, or passing runs with no failure context.

The English summary is being prepared. Showing the original description.

Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.

The English summary is being prepared. Showing the original description.

A relentless interview to sharpen a plan or design.

The English summary is being prepared. Showing the original description.

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

The English summary is being prepared. Showing the original description.

Create and commit a durable handoff document that gives a fresh agent the context and prompt to continue the current planning or implementation work. Use only when explicitly invoked as `$handoff` or when the user explicitly requests a handoff.

The English summary is being prepared. Showing the original description.

Research one agent harness's release (docs, source, runtime) and fill its capability cells in scripts/harness_capabilities.py with cited evidence. Use after a harness version bump, when just harness-probe reports re-research, or when capability cells read unknown.

The English summary is being prepared. Showing the original description.

Drive QA of a SwiftUI app on a real iPhone over USB - screenshot, read the accessibility tree, inspect @Observable state, tap, swipe, and type through an HTTP bridge embedded in the app under test. Use when asked to test an iOS app on a physical device, find bugs on the device, or expose a connected iPhone to a remote agent over Tailscale. Requires the ios-agent-qa runtime; not for simulator or XCTest work.

The English summary is being prepared. Showing the original description.

Answer questions about the Paseo product and app, including setup, configuration, connectivity, providers, workspaces, updates, logs, and troubleshooting. Use when a user inside Paseo asks how Paseo works, how to configure it, or why something is broken; use the paseo skill instead to operate agents and workspaces through MCP or the CLI.

The English summary is being prepared. Showing the original description.

Review a written plan or design doc through a designer's lens before implementation - seven passes over information architecture, interaction states, emotional arc, AI-slop risk, design-system alignment, responsive and accessibility coverage, and unresolved decisions. Each dimension is rated 0-10 with an explicit statement of what would make it a 10, then the plan is edited to get there. Use when a plan has a UI surface and you want the design gaps closed before code is written. Not for auditing a live site.

The English summary is being prepared. Showing the original description.

Run an infrastructure-first security audit of a repository - secrets archaeology, dependency supply chain, CI/CD pipeline, LLM/AI attack surface, agent skill supply chain, OWASP Top 10, STRIDE threat model, and data classification - with a confidence gate and a pre-emit verification gate that suppress speculative findings. Use when asked for a security audit, threat model, pentest-style review, OWASP pass, or a pre-release security check. Not for reviewing a single diff - use requesting-code-review for that.

The English summary is being prepared. Showing the original description.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when brainstorming what AI could make possible in an app, or when an LLM prompt-and-parse step could become a structured decision. Applications include routing, ranking, extraction, verification, and interactive experiences; these are starting points, not the limits. Read live docs and cookbooks to find useful patterns and discover new combinations.

The English summary is being prepared. Showing the original description.

Use when you have a spec or requirements for a multi-step task, before touching code

The English summary is being prepared. Showing the original description.

Codex workflow tips from Boris Cherny and the Codex team. Use when setting up Codex or optimizing workflows: parallel sessions, worktrees, plan mode, AGENTS.md, skills, subagents, hooks, MCP, permissions, and sandboxing.

The English summary is being prepared. Showing the original description.

No-op workflow for when the user says they duplicated the chat/session into another tab. Use when invoked as `$dupe` or when the user says this tab was duplicated and no action is needed.

The English summary is being prepared. Showing the original description.

Hand off the current task to another agent with full context. Use when the user says "handoff", "hand off", "hand this to", or wants to pass work to another agent.

The English summary is being prepared. Showing the original description.