All Skills

SpecKit Safe Update

You are a senior software engineer helping a peer work through a problem, feature implementation, or bug investigation. Your role is to understand the

You are an expert software engineer with 15+ years of experience in large-scale collaborative projects. You have a keen eye for design patterns, code

You are a software development agent focused on creating simple, beautiful software through thoughtful specification. Your philosophy: the best code i

Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Backend API design, database architecture, microservices patterns, and test-driven development. Use for designing APIs, database schemas, or backend system architecture.

Automate QA regression testing with reusable test skills. Create login flows, dashboard checks, user creation, and other common test scenarios that run consistently.

Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

Create, update, and manage Jira issues from natural language. Use when the user wants to log bugs, create tickets, update issue status, or manage their Jira backlog.

Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.

Turn Notion specs into implementation plans, tasks, and progress tracking; use when implementing PRDs/feature specs and creating Notion plans + tasks from them.

Modern Python development with Python 3.12+, Django, FastAPI, async patterns, and production best practices. Use for Python projects, APIs, data processing, or automation scripts.

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful `whyHere` notes, and create a starter pack once the first pass is solid.

Generalist

Implement features from spec documents (context/doc required)

Use when an idea needs disciplined exploration before building: generate options, test whether it is worth building, map adjacent solutions, challenge assumptions, narrow scope, or choose Build RFC / Prototype / Narrow / Park — even if nobody said brainstorm. Already decided to implement a specific plan → skip.

Use this skill when the user asks to find, evaluate, preview, install, rate, review, score, improve, refactor, or synthesize Agent Skills (the `SKILL.md` folder format) across GitHub, local skill folders, and skill marketplaces. Covers searching for a skill for a task, deep-diving a candidate, installing one or more skills into one or more agents at user or project scope, rating or reviewing an existing SKILL.md, refactoring a skill, or creating a new local skill from researched patterns. Do NOT activate for general package search (npm, cargo), general (non-skill) web search, or code research not involving SKILL.md files.

Use this skill whenever you call the octocode MCP tools directly to research code — local (localSearchCode, localGetFileContent, localViewStructure, localFindFiles, lspGetSemantics, localBinaryInspect) or GitHub (npmSearch, ghSearchRepos, ghViewRepoStructure, ghSearchCode, ghGetFileContent, ghHistoryResearch, ghCloneRepo). It is the operating guide for picking the right tool, chaining find → map → read → prove, minifying reads, paginating losslessly, and reading the evidence/hints signals. Triggers on "how does X work", "where is Y defined", "who calls Z", "trace this flow", "find usages", "read this file efficiently", "research this repo/package". For multi-step research over the HTTP server, use octocode-research instead.

Use when designing, reviewing, or implementing agentic flows, multi-agent orchestration, LLM caching, memory/state passing, schema contracts, tool routing, Google ADK agents, LangChain/LangGraph agents, or reusable agent workflows. Produces a flexible flow design with Zod contracts, cache/memory policy, framework mapping, gates, and verification steps.

This skill should be used when the user asks to "generate documentation", "document this project", "create docs", "write documentation", "update documentation", "document all APIs", "generate onboarding docs", "create developer docs", or needs comprehensive codebase documentation. Orchestrates parallel AI agents to analyze code and produce documentation files.

Use when the user asks to "find X in codebase", "where is Y defined?", "explore this dir", "list files in src/", "trace definitions", "find usages" — local-only. Local codebase exploration via Octocode Local + LSP. No GitHub; for external repos use octocode-research.