isanthoshgandhi

Full project context setup and session management skill. Use this when starting a new project, onboarding onto an existing codebase, resuming work after a session gap, ending a session and wanting to save progress, or when context is running low mid-session. Sets up a docs/context/ system that any AI tool can read (Claude, Codex, Cursor, Windsurf). Three modes: SETUP (first time), RESUME (session

Personal Claude Code skills by Santhosh Gandhi — context-manager and frugal-token-usage

Generates a human-readable architecture document for any codebase. Use when onboarding contributors, presenting to stakeholders, explaining how a system works to non-technical collaborators, or after a major architectural change. Outputs docs/ARCHITECTURE.md with a Mermaid system diagram, plain English narrative, data flow walkthrough, and tech stack rationale. Trigger on: "map the architecture",

Activate when the user wants to reduce token usage, manage context efficiently, or says "be frugal", "save tokens", "token usage", "frugal mode", "reduce context", "don't waste tokens", "context limit", or "token efficient". Reviews current behaviour and enforces minimal-token rules for the rest of the session. Always active via CLAUDE.md — this skill is a mid-session audit and reminder.

Post AI Thinking — unbiased solution space explorer. Strips inherited human heuristics, enumerates ALL possible approaches, then lets the user choose. No paradigm gets priority. Auto-calibrates depth: simple problems get a quick scan (3 paradigms), architectural decisions get the full space (7 paradigms, all phases). Existing solutions are fully included — if they fit best, use them. Invoke as: /p

Product pressure test before you build. Two modes: Startup (6 YC-style forcing questions that expose demand reality, status quo, target user, narrowest wedge, observation, and future-fit) and Builder (generative brainstorming for side projects, hackathons, and open source). Produces a design doc. Invoke when the user describes a new idea, asks whether something is worth building, or wants to press

Scan the current codebase or a specified file/diff for production bugs, logic errors, and risky code before it ships. Use when the user says "review", "check my code", "is this safe to ship", or "any bugs in this?". Produces a prioritised bug list with exact file:line references and optional auto-fixes.

Audit code for security vulnerabilities. Use when the user says "security-audit", "security check", "is this secure", "audit for vulnerabilities", or before any public deployment. Covers OWASP Top 10 and common API/backend attack surfaces.

Audit any system for human usability against Nielsen's 10 heuristics. Deterministic checklist — same 10 heuristics, same severity scale, same report structure every run. Works on UI screens, CLI flows, API response patterns, user journeys, component code, or any described interface. Invoke when user says "usability audit", "UX review", "heuristic evaluation", "audit for usability", "check this for

Trace the root cause of a bug or unexpected behaviour. Use when the user says "why is this broken", "why does this fail", "whybroken", "something's wrong with X", or pastes an error. Never patches symptoms — always finds the cause first.