dotfiles

Full Caido SDK integration for Claude Code. Search HTTP history, replay/edit requests, manage scopes/filters/environments, create findings, export curl commands, and control intercept - all via the official @caido/sdk-client. PAT auth recommended.

Use when user asks for terse output, fewer tokens, compact replies, caveman style, /caveman, /commit, /review, /compress, /caveman-help, or brief technical responses.

Use when the user wants an Obsidian-style vault, linked project documentation, developer docs, architecture notes, codebase knowledge base, repo map, or small connected Markdown notes that explain how a project works.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when reviewing, validating, scoring, or improving authorized bug bounty vulnerability reports, especially when the user wants to verify reproducibility, impact, severity, evidence quality, attack-chain logic, or whether a report is ready to submit.

Use when the user wants bug bounty research ideas, authorized hacking/testing hypotheses, vulnerability hunting inspiration, or online writeup synthesis from a README or public bug bounty reports.

Use when building, reviewing, refactoring, or optimizing Kotlin/JVM applications where throughput, latency, allocation rate, memory use, GC pressure, startup cost, or concurrency efficiency matters. Trigger on requests about hot paths, benchmarks, coroutines, sequences, collections, memory leaks, reducing overhead, or making Kotlin code faster.

Use this skill when designing an indoor navigation system that needs graph construction, A* pathfinding, door-aware transitions, wall avoidance, clearance control, and multi-floor routing. Trigger it when the user wants a navigation architecture or algorithm design, or asks for A* in buildings, rooms, corridors, doors, or floor transitions. Default output is JavaScript-style pseudocode and a clear step-by-step plan.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.