Use Perplexity to find web sources, get cited research summaries, explore complex decisions, or investigate a topic in depth. Separate modes support quick questions, ranked search results, combined answers, and comprehensive research.
Turn feature requests and conversation context into an implementation plan and handoff document. Review existing code, clarify complex requirements, and organize concrete tasks, affected files, verification steps, assumptions, and risks for review before implementation.
Turn mathematical claims into Lean4 proofs, checked by a theorem prover. A five-phase workflow researches existing results, designs the proof, tests candidate lemmas, implements it, and reports remaining proof gaps and any custom axioms.
Check code quality with qlty CLI, a command-line tool for multiple languages. Review changed or selected files, automatically fix supported issues, format code, and measure complexity and duplication to identify areas that need attention.
Search previous work records to recover useful decisions, successful approaches, and failed attempts. Find context in handoffs, plans, and build or test histories, then use those findings when tackling similar tasks or recurring errors.
Search stored learnings from past sessions by meaning or keywords. Retrieve relevant entries in full, along with their type, confidence, and session context, to revisit earlier findings about development patterns, installation, or errors.
Prepare software releases through security checks, end-to-end tests that cover the full system, and final review. After approval, coordinate version updates, a changelog, and release notes, with blocking issues stopping the workflow.
Investigate an unfamiliar codebase and create a handoff document covering its structure, technologies, implementation patterns, and contribution rules. Findings include source file references, issue and pull request templates, testing requirements, and practical points to check before contributing.
Investigate how an existing codebase works and document its components, connections, and file references. Combine current code findings with historical notes to produce a research document grounded in specific paths and line numbers.
Connect five MCP tools, agent-accessible external capabilities, into a development workflow spanning documentation search, code search, quality checks, and Git status. Learn how to share results between steps and continue when individual tools are unavailable or fail.
Set up Python agents using Agentica SDK with a local proxy that forwards requests to Claude CLI. Follow startup steps, configure connection endpoints, check service health, and troubleshoot connection failures or missing tool access.
Set up Agentica patterns that coordinate multiple AI agents. Choose different perspectives for research, a coordinator with specialists for implementation, repeated generation and critique for refinement, or a panel of agents for majority-based validation.
Coordinate background agents using system progress reminders while continuing other work. Read their output files after completion signals, avoiding repeated status checks and full transcripts that consume tokens and crowd the main conversation.
Review Claude Code sessions using Braintrust traces, records of agent activity. Summarize tool, agent, and skill usage, inspect repeated actions, replay sessions, and track token consumption to understand failures and recurring work patterns.
Look up Claude Code commands and options for interactive work or automation. Covers non-interactive execution, session management, output formats, tool permissions, and agent definitions, with command examples for scripts and CI/CD workflows.
Review session changes, group related files into focused Git commits, and draft messages explaining their purpose. Presents the plan for approval before committing, omits Claude attribution, and records development reasoning through a project script.
Use this skill for end-to-end testing of a persistence pipeline, the sequence of steps that saves data. The supplied material states this purpose but provides only placeholder instructions, without concrete checks.
Review saved session learnings to find recurring successes, failures, and decisions. Consolidates similar patterns, proposes reusable skills, rules, event-triggered actions, or agent updates, and creates approved changes with references to the source sessions.
Create a concise YAML handoff, a structured text document, for another agent or session. Capture completed work, decisions, blockers, file references, verification commands, and next steps so work can resume with the key context available.
Diagnose Claude Code hooks, scripts triggered by events, when they fail to run or produce unexpected results. Follow checks for logs, registration, files, manual execution, hidden errors, and rebuilt TypeScript bundles to narrow down the cause.
Create pull request descriptions using a repository’s template, drawing on code changes, commit history, and verification results. Save the description locally and update it on GitHub, with incomplete checks clearly identified for reviewers.
Turn a rough app or automation idea into a detailed specification through guided interviews and research. Clarify user journeys, data, security, operations, and competing priorities, then document requirements and acceptance criteria for implementation.
Diagnose unexpected Python package installation behavior by checking the interpreter uv actually uses, the pinned Python version, installed packages, and imports. Includes a recovery pattern for dependencies that require a newer Python version.
Explores an existing codebase at quick, deep, or architecture-focused levels. Summarizes structure, function calls, and dependencies, then produces documentation or a handoff for implementation without changing the code.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)