# Naren's Claude Toolkit

> Original Claude Code skills, mods and MCP servers by Naren. Install plugins through the plugin marketplace `NarenDawar/narens-claude-toolkit`.

## Skills

- [comprehension-check](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/comprehension-check/README.md): Use when the user asks to be quizzed on, or to check their understanding of, code Claude wrote this session (for example 'quiz me on that' or 'do I actually understand this change?').
- [decision-journal](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/decision-journal/README.md): Use when the user wants to log a prediction or estimate about a dev or project decision, grade past predictions, or see how calibrated they are (for example 'log a prediction', 'grade my predictions', 'how calibrated am I?').
- [human-writing](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/human-writing/README.md): Use when the user wants words written or rewritten in a human, personal voice, including short casual messages: a Slack note, newsletter intro, cover letter, email, post, bio, speech or story, with or without a pasted voice sample. Also use when a draft sounds fake, robotic, generic, corporate or "ChatGPT-ish", even if they wrote it with an AI, and as a final pass on anything Claude drafted that the user will send or publish as themselves. Skip code, data, translation, proofreading-only requests, legal text, and anything whose exact wording must stay unchanged.
- [model-bakeoff](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/model-bakeoff/README.md): Use when the user wants to pick the cheapest model that still works for a custom subagent, asks whether Haiku or Sonnet would do, or wants to re-check an agent's model after new models ship (for example 'which model should this agent use?', 'could this run on Haiku?', 'bake-off my reviewer agent').
- [pdf-table-fixer](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/pdf-table-fixer/README.md): Use when the user has a tagged PDF whose tables fail accessibility checks or read badly in a screen reader (for example 'fix the table headers in this PDF', 'my PDF tables fail PDF/UA', 'repair the table tags').
- [podcast-clip-scout](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/podcast-clip-scout/README.md): Use when the user has a timestamped podcast or video transcript and wants the best short clips picked from it (for example 'find the best clips in this episode', 'which moments would work as shorts', 'pick reel candidates from this transcript').
- [rule-promoter](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/rule-promoter/README.md): Use when the user wants rules in CLAUDE.md enforced with hooks, says Claude keeps ignoring a CLAUDE.md rule, or asks to turn CLAUDE.md rules into hooks (for example 'promote my CLAUDE.md rules to hooks' or 'make Claude stop editing migrations').
- [schedule-doctor](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/schedule-doctor/README.md): Use when the user is about to schedule a Claude task, or asks why a scheduled task, /loop, cron job or routine did not run, ran late, or stopped partway (for example 'will this scheduled task actually run?', 'why didn't my 7am task fire?', 'check this before I schedule it').
- [subagent-tax-auditor](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/subagent-tax-auditor/README.md): Use when the user asks why their Claude Code quota or usage limit runs out so fast, which subagents cost the most, or wants their subagents made cheaper (for example 'audit my subagents', 'which agent is eating my quota', 'make my agents cheaper').

## Mods

- [clocks-band](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/clocks-band/README.md): A band above the prompt showing every Bash command, MCP call and subagent that has run for a while, with elapsed time against its limit.
- [local-answer-router](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/local-answer-router/README.md): Answers trivial questions (what branch, what changed, did the last test pass) from git and the last test run on your machine, with no model tokens.
- [subagent-meter](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/plugins/subagent-meter/README.md): A live status line showing how much of your session's tokens go to subagents, and which agent type uses the most.

## MCP servers

- [mcp-fixer](https://github.com/NarenDawar/narens-claude-toolkit/blob/main/servers/mcp-fixer/README.md): Scores an MCP server's tool definitions with deterministic lint rules, so you can see what makes agents pick the wrong tool or waste tokens.