pi-agent-toolkit

Route delegated work through the current host's supported sub-agent mechanism. In Pi, use the installed pi-subagents package. Use whenever the user asks for a subagent, Pi agent, Claude or Codex agent, or independent multi-agent work.

Launch both thermo-nuclear review subagents in parallel. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

Run the CodeRabbit CLI for AI-powered review. Use only when the user explicitly asks for CodeRabbit or invokes coderabbit-review. Never trigger for a generic code review, PR review, quality check, security audit, or autonomously.

Use when reviewing implementation plans, migration plans, refactoring proposals, feature plans, generated implementation trackers, or committable phase plans before execution; especially when asked whether a plan is ready, concrete enough, testable, safe, or dependency-aware.

Use when creating, refining, or reviewing implementation plans, migration plans, refactoring proposals, feature plans, implementation trackers, or committable phase plans; especially when turning a rough plan into executable phases or checking whether a plan is concrete, testable, safe, dependency-aware, and suitable for parallel work.

Use this skill whenever the user gives a YouTube URL and asks to summarize, digest, analyze, extract transcript/context, decide whether a video is worth watching, or understand what a video is about. Prefer the summarize CLI for YouTube/video context instead of web search. Use Codex as the default summarize backend when possible, and use the local Whisper large-v3 model for transcription fallback. Do not use this for ordinary web pages; the user prefers Exa for webpage research.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.

Comprehensive security and correctness audit of a branch's changes. Use for thermo nuclear, thermonuclear, or deep review requests, or branch/PR diff audits focused on bugs, breaking changes, security issues, devex regressions, and feature-gate leaks.

Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before closing the ticket. Trigger on /post-mortem, when the user says "write the post-mortem / postmortem / RCA / root cause analysis", "document this fix", "write up the root cause", "close out this bug with a writeup", or hands you a fixed-and-validated bug and asks for the writeup.

Expert SQL assistance for query writing, query review, optimization, schema analysis, execution-plan interpretation, DDL review, ERD analysis, and database design across PostgreSQL, MySQL, Redshift, SQL Server, and Oracle. Use when the user asks for SQL help, performance tuning, schema modeling, or safe database query guidance.

Validate API integration code against API contracts and schemas. Use when implementing, refactoring, reviewing, or debugging code that calls REST, GraphQL, gRPC, SDK, or webhook APIs, especially when OpenAPI specs, GraphQL schemas, protobufs, SDK types, TypeScript interfaces, Pydantic models, or documented request/response contracts are available.

Create or update targeted tests for changed behavior. Use when adding features, fixing bugs, refactoring code, or finding missing coverage, especially when existing tests need to be extended to cover new behavior, edge cases, or regressions.

Scan a repository to discover all external SaaS tools and services it integrates with, then determine whether each has an official CLI. Use this skill whenever the user asks to find CLIs for their project, audit third-party service integrations, discover what external services a codebase depends on, check for official CLI tools, or wants to know "what services does this repo use." Also trigger when the user asks about automating service management, scripting deployments, or wants to interact with their project's services from the terminal.

Use when creating GitHub issues via the `gh` CLI. Covers body structure, issue type classification (bug, feature, task), label selection, and consistent formatting. Triggers on requests to file, create, open, or submit a GitHub issue.

Analyze git changes between branches and generate a changelog entry. Use when catching up on repo changes, after merges, or when asking "what's new in the codebase?"

Implement Google Chat Cards v2 format for rich alert notifications. This skill should be used when migrating from plain text messages to Cards v2 format, adding visual alerts to Google Chat webhooks, or building card-based notification systems.

Standards and best practices for creating technical documentation. Use when the user requests documentation updates or asks to create README files, API docs, user guides, or docstrings.

Use when a working feature has duplicated mechanics, repeated API calls, inconsistent parsing or validation, messy helpers, or structure that will make review or future agent work harder.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "brainstorm".

Work with 1Password developer features including SSH key management, the SSH agent, 1Password Environments for secrets injection, and the op CLI. Use this skill whenever the user mentions 1Password, op CLI, 1Password SSH agent, 1Password Environments, secret references, op run, op inject, or wants to manage SSH keys through 1Password, secure .env files with 1Password, or inject secrets at runtime. Also trigger when the user wants to stop storing plaintext secrets on disk or asks about securing developer credentials.

Semantic web search and structured research using Exa. Use when you need web search, semantic search, similar-page discovery, content extraction from search results, direct answers with sources, or structured research over web sources. Triggers: exa, web search, semantic search, find similar, research, docs lookup, github search.