nicograef/handbook

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Plans, researches, structures, writes, and reviews an explanatory audiobook about a codebase or a topic, then renders it as an ElevenReader-ready EPUB. Confirms scope, focus, and prior knowledge once, then runs to completion. Use when the user wants to build deeper understanding of a system or a subject by listening…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Prevents the agent from making assumptions by forcing structured clarifying questions before acting. Use when the user wants thorough spec-gathering, disambiguation, or wants the agent to ask before assuming. Applies to any task type.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Reviews code changes for clean code principles, design patterns, and anti-patterns. Use on recent changes (staged, unstaged, last commit) or a specific area (module, route, component, page). Reports findings with concrete suggestions, applies fixes after confirmation. Integrates AI slop detection, architecture…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Creates an implementation plan from a PRD or a task description. Researches codebase context, clarifies ambiguities, and outputs a phased plan with vertical slices and acceptance criteria. Use when the user wants to plan a feature, break down a PRD, create an implementation plan, or mentions "tracer bullets".

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Dispatches multiple subagents in parallel for 2+ confirmed-independent, each-substantial failures or investigation targets that share no state or sequential dependency. Use when the work splits cleanly and each part is big enough to justify a separate agent.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Radically minimizes and restructures the prose of a whole repository — Markdown, docs, READMEs, code and config comments. Re-derives the docs from a blank slate instead of editing them: deletes what is historic, derivable, generic, aspirational, or duplicated, then splits surviving monoliths into small deduplicated…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Decides how to integrate a finished branch — merge, pull request, keep, or discard — once tests pass. Use when implementation work on a branch is complete and you need to decide what happens to it next.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Guides a developer step-by-step through implementing a user story or plan phase — without writing any code. The agent acts as navigator: it explores the codebase, breaks work into small vertical steps, explains what to do and why, and waits for the developer to implement each step. Use when the user wants coaching…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Executes an entire implementation plan end to end — phase by phase in dedicated git worktrees, committing and ticking each acceptance criterion as it is verified, then rebasing and merging its branches back onto the base branch. Use when the user wants a whole plan implemented autonomously, or wants to pick a plan run…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Coordinates concurrent Claude Code sessions working in one repository. Discovers live peer sessions and their worktrees, publishes what this session claims, predicts merge conflicts and resource collisions, and exchanges messages with peers directly instead of through the user. Use when another session or worktree is…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Cleans accumulated agent state in two layers: an ungated mechanical sweep that deletes session state older than a threshold (transcripts, session caches, scratchpads) via a bundled allowlist-only script, and a gated semantic review that proposes stale memories, outdated rules, and repo leftovers for deletion or update…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Acts on code-review feedback (from a human, a PR comment, or an AI reviewer) by verifying each item against the codebase before implementing, and asking when items are unclear. Use when receiving code review comments, PR feedback, or suggestions from another reviewer — before implementing any of them.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Runs a structured retrospective over a work session: reports problems, solutions, insights, and friction; derives an improvement plan categorized as memory, rule, skill, documentation, or tooling/process; retires the artifacts those items supersede; and applies only the items the user picks. Use as a deliberate…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Researches companies, jobs, or tools from live sources and records structured findings, with strict verification. Delegates to the web-researcher agent.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Investigates a bug, test failure, or unexpected behavior root-cause-first before proposing a fix. Use when a test fails, an error shows up in logs or CI, or something behaves unexpectedly and the next step would otherwise be guessing at a patch.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Drives development with a red-green-refactor loop, one test at a time. Use when the user wants to build a feature or fix a bug using TDD, mentions "red-green-refactor", or asks for test-first development.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Reviews and refactors an existing test suite. Use when the user wants to reduce test count, remove implementation-detail tests, improve test readability, or clean up a test suite that has grown noisy or brittle.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Trains the user on any subject — a general topic, an external tool or spec, or the current codebase — through interactive quiz sessions: single-choice, multiple-select, and free-text questions with scaffolded hints instead of handed-over answers, plus per-topic progress that persists across sessions. Use when the user…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Explores a codebase deeply to build a human's mental model. Use when the user wants to understand a specific part of the codebase holistically — database schema, API, function, domain model, business logic, frontend component, architecture, or any other concept. Invoke with one or more references to the code in…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Creates or reuses an isolated git worktree for feature work, a risky refactor, or unattended agent runs. Use when starting work that shouldn't touch the current checkout, before executing a multi-step plan, or when running an agent unattended and it needs its own branch and directory.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Reviews a frontend for mobile UX, UI consistency, workflow friction, and terminology drift. Use when the user wants a UX audit of a mobile-first web app or needs to find usability problems on small screens.

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Fact-checks a repository's committed documentation against ground truth — the code, config, and scripts it describes, read-only command output, and official upstream sources — and against itself for contradictions, drifted duplicates, and dead references. Runs as an independent session over an already-committed…

nicograef/handbook

Skill Claude CodeCodex

Part of handbook

Creates a PRD through structured clarification, codebase exploration, and module design, then saves it as a local Markdown file. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.