alchemiststudiosDOTai

Run or continue a differential debugging session between two implementations, traces, captures, or outputs. Record artifact identity, exact commands, first mismatch progression, findings, validation, and next probe in a durable session log.

Execute implementation plans from .artifacts/plan/. Focus on EXECUTING ONLY - no planning, no fixes outside plan scope. Uses gated checks, atomic commits, and maintains a single execution log in .artifacts/execute/. Use when the user says "execute this plan" or provides a plan path.

Map a repository's mechanical harness layers: canonical check command, local and CI gates, architecture boundaries, structural rules, behavioral verification, docs ratchets, evidence workflows, and operator-facing surfaces. Use when you need to understand how a repo keeps change safe.

Generate execution-ready implementation plans from research docs - planning ONLY, no fixing or verifying. North Star is whether a JR developer can execute the plan with zero additional context.

Perform quality assurance on code changes after the research-phase -> plan-phase -> execute-phase workflow. STRICTLY QA only—no coding, no fixes, no source-code changes. Focus on changed areas only, emphasizing control/data flow correctness.

This skill should be used when mapping or researching a codebase to understand its structure, patterns, and architecture. Use when the user asks to "map the codebase", "research how X works", "find all Y patterns", or needs to understand code organization. Produces factual structural maps in .artifacts/research/—no suggestions, no recommendations, just what exists. Uses ast-grep for structural pattern matching.

This skill should be used when creating, refreshing, or validating a repository `AGENTS.md` so it stays concise, current, and grounded in repository evidence. Use when `AGENTS.md` is missing or stale, after refactors or tooling changes, when new docs become the system of record, or when adding lightweight drift checks.

Set up ast-grep for a codebase with common TypeScript rules for detecting anti-patterns, enforcing best practices, and preventing bugs. Creates sgconfig.yml, rule files, and rule tests. Use when adding structural linting, banning legacy patterns, or implementing ratchet gates.

This skill should be used when mapping or researching a codebase to understand its structure, patterns, and architecture. Use when the user asks to "map the codebase", "research how X works", "find all Y patterns", or needs to understand code organization. Produces factual structural maps in memory-bank/research/—no suggestions, no recommendations, just what exists. Uses ast-grep for structural pattern matching.

Run or continue a differential debugging session between two implementations, traces, captures, or outputs. Record artifact identity, exact commands, first mismatch progression, findings, validation, and next probe in a durable session log.

Map a repository's mechanical harness layers: canonical check command, local and CI gates, architecture boundaries, structural rules, behavioral verification, docs ratchets, evidence workflows, and operator-facing surfaces. Use when you need to understand how a repo keeps change safe.

Generate execution-ready implementation plans from research docs - planning ONLY, no fixing or verifying. North Star is whether a JR developer can execute the plan with zero additional context.

Execute implementation plans from memory-bank/plan/. Focus on EXECUTING ONLY - no planning, no fixes outside plan scope. Uses gated checks, atomic commits, and maintains a single execution log in memory-bank/execute/. Use when the user says "execute this plan" or provides a plan path.

Perform quality assurance on code changes after the implementation-planner -> plan-executor workflow. STRICTLY QA only—no coding, no fixes, no source-code changes. Focus on changed areas only, emphasizing control/data flow correctness.

This skill should be used when working in the salary-man-setup repository to inspect, run, debug, or extend the Ubuntu bootstrap flow. Use it when another agent needs to drive setup.sh or the numbered install scripts, test the bootstrap on a local or remote machine, work through tmux, or update the managed shell/git/bootstrap configuration while preserving the repo's secret-handling guardrails.

Map a repository's mechanical harness layers: canonical check command, local and CI gates, architecture boundaries, structural rules, behavioral verification, docs ratchets, evidence workflows, and operator-facing surfaces. Use when you need to understand how a repo keeps change safe.

Browser automation for AI agents (Linux/macOS/Windows). Use when the user needs to interact with websites, navigate pages, fill forms, click buttons, take screenshots, extract data, test web apps, or automate browser tasks. Triggers include "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data", "test this web app", "login to a site", or any task requiring programmatic web interaction.

Generate execution-ready implementation plans (PLUS per-task ticket files) from research docs — planning ONLY, no fixing or verifying. North Star is whether a JR developer can execute the work with zero additional context.

Enforce repository Markdown docs with required YAML frontmatter and ontology_relations, and set up a pre-push hook that blocks pushes when any .md file except AGENTS.md is missing required frontmatter keys.

Stage all local changes, generate a commit message with branch context, diff stats, and a truncated inline diff versus origin/<branch>, then commit and push with automatic rebase-and-retry when remote is ahead.

This skill should be used when mapping or researching a codebase to understand its structure, patterns, and architecture. Use when the user asks to "map the codebase", "research how X works", "find all Y patterns", or needs to understand code organization. Produces factual structural maps—no suggestions, no recommendations, just what exists. Uses ast-grep for structural pattern matching.

Execute implementation plans from memory-bank/plan/. STRICTLY execution only—NO research, NO planning, NO deviation from plan without confirmation. Trust that planning-from-research has already prepared the work. Output is working code with execution logs.

Generate execution-ready implementation plans from research documents. STRICTLY planning only—NO execution, NO coding. Validate research completeness first; if vague, resolve via subagents or user confirmation. Output is a standalone plan that a junior developer can execute without additional documentation.

Perform quality assurance on code changes after research-plan-execute workflow. STRICTLY read-only analysis—NO coding, NO fixing, NO execution. Focuses on changed areas only, emphasizing control/data flow correctness.

Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.

This skill should be used when releasing tunacode-cli to PyPI. It keeps the existing local release checks, then hands the actual PyPI upload to a GitHub Actions workflow that uses the repository's PYPI_API_TOKEN secret.

This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work. Claude Code drives Gemini like an intern - issuing tasks, reviewing output, requesting fixes - but never writes code itself. Use when user says "manage gemini", "architect mode", "drive gemini", or wants to delegate all implementation to Gemini.

This skill should be used when the user wants Claude Code to act purely as a manager/architect while Gemini CLI does all the coding work. Claude Code drives Gemini like an intern - issuing tasks, reviewing output, requesting fixes - but never writes code itself. Use when user says "manage gemini", "architect mode", "drive gemini", or wants to delegate all implementation to Gemini.

Generate .coderabbit.yaml configurations tailored to your project by analyzing PR history, commit patterns, and existing code standards. Use when the user asks to "create coderabbit config", "set up coderabbit", "generate code review rules", or needs automated PR review configuration based on their project's specific patterns and tooling.

This skill should be used when CodeRabbit code review feedback needs to be processed and fixed systematically. Use after running `coderabbit --plain` to automatically save feedback, analyze issues using MCP tools, and implement minimal code fixes with proper planning.

Rust CLI for provider-agnostic web search using Brave Search or Exa APIs