Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
Use when the user asks to run or prepare the Almanac clean-slate workflow, uninstall all local codealmanac/Almanac CLI artifacts, or reset a machine to first-time Almanac install state.
Use when a user asks for a major architecture/refactor audit, codebase smell investigation, boundary critique, feature simplification review, vibe-coded or AI-generated code cleanup assessment, hand-rolled library review, or no-code report on how a codebase should be reshaped.
Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity. Use for evidence-backed deletion or consolidation of dead code, duplicate state, redundant APIs or layers, ownerless abstractions, obsolete compatibility or design records, and over-engineering in any…
Use when you need to find related files, understand code dependencies, or analyze impact scope. Triggers when the user asks about: "Which files use this function/class?" "What files will be affected if I change this?" "Find code related to X" "What does this file depend on?" "Where is this symbol defined/referenced?"…
Build a trustworthy first ontology from an empty or near-empty ontology-atlas vault using only Atlas MCP evidence. Use when the user asks to analyze a codebase, bootstrap/fill its ontology, extract product meaning from a repository, or when a requested ontology task finds only starter nodes. Separate observed…
Measure whether Atlas actually works on a repository nobody here knows, by building a vault with a real MCP agent and then handing that vault — without the source — to a second agent who must answer questions from it alone. Use when changing the construction rules, the MCP read/write contract, the bootstrap skill, or…
Pre-launch codebase audit skill. Use this whenever someone is about to ship, deploy, launch, push to main/prod, or merge a release - even without "goshipit" explicitly. Trigger on: "is my app ready?", "can I deploy now?", "pre-deploy check", "review before launch", "is this production-ready?", "check my codebase"…
Help developers using coding agents retain solution knowledge by quizzing them on the current codebase one question at a time, grading each response against the implementation, and explaining incorrect answers. Use when a user asks "Do I know this codebase?", "quiz me on this codebase", "grill me", wants to verify or…
Turn a codebase or GitHub repo into a hand-drawn "小黑 (Xiaohei)" illustrated explainer — a bilingual (中文/English) image+text slide deck saved as one HTML file. Use when the user wants to explain, decode, visualize, walk through, or 拆解 / 图解 how a repository or codebase works using illustrations; mentions Xiaohei Code…
Analyze any abandoned, legacy, or inherited codebase and produce a Revival Document — a health report, revival plan, and contribution guide in one. Trigger when someone says "analyze this repo," "I inherited this codebase," "is this worth reviving," "help me understand what I've got here," "I found an abandoned repo,"…
Drop into any repo and generate a structured architecture overview. Maps the codebase, identifies entry points, frameworks, and dependencies — then produces a "start here" guide for new contributors.
Use semantic code search before reading files. Find relevant chunks by intent (e.g. "where is auth handled?") via the semhood MCP server, then read only what's needed.
Use semantic code search before reading files. Find relevant chunks by intent (e.g. "where is auth handled?") via the semhood MCP server, then read only what's needed.
Build deep architectural understanding of a codebase by excavating its git history, GitHub issues/PRs/discussions, and any available documentation. Produces a chapter-based narrative of how the system evolved, reviewed interactively with the user through challenge-and-response Q&A. Use when onboarding onto a codebase…
Provides token-efficient analysis of dependency libraries. Gathers all necessary information about given libraries. Improves development efficiency. Must be used before the actual development process.
Analyze a GitHub repository URL and produce a source-backed, time-boxed reading route through its critical execution path. Use for unfamiliar repository walkthroughs, rapid codebase onboarding, or tracing how a feature works from a GitHub repository, directory, or file link.