KiMiGuel
- 8 skills
- 0 followers
- 6 hours ago last updated
- ▌ Caveman · kimiguelUse when the user invokes /caveman or requests caveman, compact, ultra-compact, terse, brief, or minimal-token communication mode.
- ▌ Wordsmith · kimiguel bundleSmart wordlist generator and cleaner. Use when the user asks to create, build, expand, or clean a wordlist / password dictionary / .txt list of words — from a natural-language description, a seed .txt file, or SecLists files — with control over output size. Also for merging/deduping/cleaning existing lists before use with hashcat, aircrack, crunch-style workflows, or any tool that consumes wordlists. Trigger phrases: "make me a wordlist", "generate a dictionary", "expand these words", "clean this list", "dedupe this txt", "wordlist for hashcat/aircrack", "top N passwords".
- ▌
- ▌ Token Hobo · kimiguel bundlePrompt optimization for reducing token consumption in AI coding agents. Use when writing, reviewing, or refactoring prompts for Kimi Code, Codex, or Claude Code to cut token cost — e.g. "optimize this prompt", "make this prompt cheaper", "reduce token usage", "tighten this system prompt". Applies three rule sets — Structural Optimization (system roles, stop sequences), Output Control (character limits, no preamble, few-shot efficiency), and Input Management (trim history, semantic compression) — and outputs platform-formatted prompts.
- ▌ Cdb Companion · kimiguelCompresses content before saving to the Claude-Desktop-Bridge vault (save_note/update_note) so notes cost fewer tokens to write and to recall later. Use whenever calling Claude-Desktop-Bridge's save_note or update_note tools, or when asked to make CDB notes more token-friendly.
- ▌ Local File Assistant · kimiguelLocal file and folder management assistant for Kimi Code running on the user's machine (macOS / Kali Linux). Use when the user asks for help with moving, copying, renaming, or organizing files and folders, cleaning up directories, finding files, or general local housekeeping — NOT for coding, writing code, or editing source files. Can also run local CLI tools and scripts that do NOT require sudo (e.g. mergecap, editcap, hcxpcapngtool, cap2hccapx, hashcat file prep, archive extraction, ffmpeg conversions) when they serve a file-management or file-processing goal. Enforces strict approval gates — every sudo command requires explicit user approval first, and any deletion (file, folder, rm, rmdir, trash) always requires explicit approval before execution. Trigger on requests like "move these files", "organize this folder", "clean up my directory", "find file X", "sort my downloads", "merge these caps", "convert this pcap", or any local filesystem/file-processing operation without code changes.
- ▌ Claude Desktop Bridge · kimiguelSave, search, and recall notes in the shared Claude-Desktop-Bridge knowledge vault (MCP tools save_note, get_notes, search_notes, update_note, delete_note) that both the Chat tab and Code tab read from. Use whenever the user asks to remember/save something for later, recall past research or decisions, or wants continuity across chat and code sessions. Also handles /claude-desktop-bridge as a quick "what's in the vault" command.
- ▌ Report Accuracy Auditor · kimiguelFact-check and accuracy-audit a long AI-generated research, legal, tax, or compliance report against primary sources, then (on request) produce a cleaned-up corrected version and a personal action-item/deadline extraction. Use when the user uploads or points at a deep-research deliverable (often a long .md from a research agent or swarm) and asks to "analyze the report", "do an accuracy check", "fact-check this", "verify the claims", "break it down", "find errors", "is this right", or asks for a cleaned-up/corrected report after a review. Covers claim extraction, batched source verification, confirmed/error/unverifiable classification, citation-machinery checks, and the user's standing presentation preference: neutral tone, issues first, good points LAST.