claude-code-toolkit

Reviews code changes before merging, through a correctness/security lens and an SRE operational-risk lens. Use when reviewing PRs, checking staged changes, reviewing diffs, code review, merge readiness check, assessing deploy or rollback risk, or validating changes before commit/push.

Dispatches a task to a Claude Fable 5 subagent with a prompt written the way Fable 5 wants to be prompted, and holds a back-and-forth with it across turns. Use when the user says /ask-fable, ask fable, fable, fable 5, send this to fable, hand this off to fable, get a Fable second opinion, or when a task sits at the top of the difficulty range: multi-hour or multi-day implementations, deep debugging, whole-repo review or bug hunts, dense technical screenshots, or ambiguous multithreaded requests where first-shot correctness matters.

Drafts a copy-pasteable prompt for Claude Fable 5 without dispatching anything. Use when the user says /prompt-fable, write me a fable prompt, draft a prompt for fable, help me prompt fable 5, or wants to hand a prompt to Fable somewhere else (the web app, another session, a colleague). For actually running the task, use the ask-fable skill instead.

User-invoked codebase recon via an ant-colony pattern. The moderator carves a large or unfamiliar codebase into disjoint territories, fans out cheap Haiku scout subagents that explore in parallel and dump full findings to /tmp scratchpads (returning only terse pointers), then one Sonnet verifier cross-checks every claim against the repo before reporting. Use to map an unfamiliar codebase or locate where something lives without bloating the main context.

User-invoked breadth check — convenes 3 specialist subagent personas to pressure-test a plan/decision/diff from angles you might have missed, surfacing framed positions + a dissent log. Intended to run AFTER the user has already reasoned through the problem, as a final "did we miss anything" sweep.

Serialize the current brainstorm/design discussion into a structured implementation spec and delegate the build to the cheaper "executor" subagent (Sonnet). Use when the user says to dispatch, delegate, hand off, or offload implementation to the executor after designing an approach together.

Renders conversation content (brainstorms, design discussions, walls of text) as a single self-contained, visually-structured HTML page that is easy to grasp at a glance. Use when the user says "visualize this", "make this visual", "turn this into a page", "make a visual explainer", "render as HTML", "this is a wall of text", "hard to read", "make a visual summary", or wants a friendlier visual representation of a technical discussion, architecture, concept explainer, or set of decisions/tradeoffs.

Runs web searches and page fetches inside an isolated Docker container instead of on the host, so browsing untrusted pages can't touch your machine and every query/URL is logged. Use when the user wants to search the web, research a topic online, fetch or read web pages, or asks for sandboxed, isolated, or contained web access. Requires a one-time build; reuses your existing host Claude login (mounted read-only). The container runs the official Claude Code CLI headless on Sonnet.

Conducts realistic mock interviews with detailed feedback and scoring. Use for interview prep, behavioral questions, technical interviews, STAR practice, system design interviews, or interview coaching.

Generates multiple choice quiz questions based on current conversation context. Use when testing understanding, reviewing what was discussed, or wanting a knowledge check on the session.

Reviews Claude Code sessions and proposes workflow improvements. Use when: (1) /workflow-review command, (2) "review my workflow", "how can I improve", (3) after long sessions when nudged, (4) start of session with pending review. Analyzes tool usage patterns, CLAUDE.md configuration, and compares against CC best practices. Proposes: CLAUDE.md updates, new skills, underused CC features. Saves session summaries to .claude/workflow-reviews/ for cross-session continuity.

Creates impressive LaTeX Beamer presentations with modern design. Generates .tex files with theme selection, font pairing, TikZ diagrams, overlays, and best practices. Use for LaTeX slides, Beamer presentations, scaffolding decks, slide design advice, or TikZ diagram generation.

Guides strong, effective unit test generation using proven testing techniques. Use when writing unit tests, reviewing test quality, improving existing tests, generating test cases, checking test coverage strength, or when tests exist but may be weak. Triggers on: unit test, test quality, test coverage, write tests, improve tests, review tests, test strength, mutation testing, boundary testing.

Creates new Claude Code skills with proper structure and best practices. Use when user wants to create a skill, update an existing skill, add a new command, scaffold a workflow, define skill hooks, or asks "how do I make a skill".

Manages tasks using the ctask CLI wrapper over a local SQLite database. Use when tracking work items, creating tasks, managing dependencies, adding comments, labeling, or reviewing task status. Triggers on task tracking, ticket management, work planning, backlog management.

Plans and executes git commits with optional TICKET_ID prefix. Analyzes staged changes, proposes optimal commit structure (single or multiple), generates descriptive messages with technical context, and executes after user approval. Use when committing code changes, creating atomic commits, or splitting large changesets.