hac-init

Plugin hac-init from marketplace pytholic-skills in pytholic/claude-skills. Commands read from the repo's manifest — 14 days ago.

Skills (18)

• codebase-research

  Navigates and maps a codebase to answer where-and-how-organized questions, with ranked, annotated answers instead of raw search output. Use when the user asks where logic lives, where a symbol is defined or used, what imports or depends on a module, whether something is still used, which files handl

• explain-code

  Explains how and why code works, with an analogy, a diagram, and a walkthrough matched to the scope of the question. Use when the user asks "how does this work?", "what does this do?", "explain this code", or "walk me through this". For where something lives in a codebase, use codebase-research inst

• goal-workflow

  Implements a spec fully, checks each requirement off against the implementation, and ends with a requirement-by-requirement report. Use when the user runs /goal-workflow, asks to "implement the spec" or "verify against the spec", or wants to go from a requirement list to a verified implementation in

• guided-implementation

  Guide the user through writing code themselves, one piece at a time, instead of implementing it for them. Use when the user wants to build something with the agent as a mentor rather than an author. Trigger phrases include: "guide me", "walk me through building this", "don't write it for me", "teach

• hac-init

  Bootstrap the .hac/ (Human-Agent Context) directory in any project. Use when the user says "set up hac", "add .hac", "set up working memory", "initialize hac", or when beginning multi-session work on a project that lacks a .hac/ directory. Language-agnostic — works for Python, TypeScript, Go, Rust,

• help

  Use when the user asks "what can I ask you to do?", "what skills do you have?", "show me a usage guide", or types /help. Presents a user-facing cheat sheet of all personal skills grouped by category.

• interview-me

  Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invo

• notion-cli

  Works with Notion pages and databases through the `ntn` CLI or the Notion MCP, picking the cheaper tool for each job. Use for any Notion task — reading, creating, editing, appending to, or trashing a page, querying or adding database rows, or uploading an image to a page.

• planning-and-task-decomposition

  Turn clear requirements into an ordered, verifiable implementation plan. Use when a spec or well-understood goal needs decomposition before coding — when the task feels too large to start, the order of work isn't obvious, or scope must be communicated. Trigger phrases include: "plan this", "break th

• playwright-cli

  Automate browser interactions, test web pages and work with Playwright tests.

• pr-description

  Generates a minimal, clear PR description from the current branch's diff and the repo's PR template. Use at the end of any task when the user wants to open a PR or needs a PR description written.

• python-code-review

  Reviews Python changes for correctness, security, simplicity, and my coding conventions, and gives a verdict. Use when the user asks for a review of a diff, branch, PR, or files, including quick or casual asks ("quick review", "check this over", "does this look OK"), or as the review step of an impl

• python-dev

  Planning-first Python development — understand, design, implement, check — with Python 3.13+, ruff, pyright, pytest, and pyproject.toml. Use when implementing a Python feature or module, refactoring, or making a Python design or architecture decision. For setting up a new project, use python-project

• python-project-scaffold

  Scaffolds a new Python project with production-ready tooling and structure. Use when the user asks for a new project, to set up or initialize a Python project, to create a repo, a project template, or boilerplate setup. Generates pyproject.toml, Makefile, pre-commit config, ruff/pyright config, test

• systematic-debugging

  Language-agnostic, four-phase debugging method that finds the root cause before any fix. Use when investigating a bug, a failing test, unexpected behavior, or a runtime or logic error — for example when the user says "debug", "fix this bug", "why is this failing", "not working", or shares a stack tr

• task-handover

  Writes a single uncommitted .claude/HANDOVER.md so the next agent or engineer can resume with no prior context. Use when the user asks to "wrap up", "hand off", "create a summary for the next agent", or "continue in a new chat", or when a long multi-subtask session with real progress is close to its

• task-scope-and-spec

  Scope a loose engineering task into a tight, testable spec list. Use when the user gives background for a piece of work and wants the requirements narrowed down before implementation. Trigger phrases include: "scope this", "what are the specs", "what's involved", "what would it take", "what's left f

• write-tests

  Writes focused pytest tests for critical paths, edge cases, and error handling, without redundant tests. Use when the user asks for tests, including brief asks like "write tests", "add tests for this", or "write important tests", or as the test step of an implement-test-review request.