Claude Skills by KalastajaM

Expert guide for setting up and improving a Claude or ChatGPT personal assistant — covering CLAUDE.md, skills, memory, scheduled tasks, token efficiency, self-improving tasks, MCP servers, git integration, dev workflow, personal data projects, and LLM wikis. Use this skill whenever a user wants to: set up Claude, ChatGPT, or Codex as an assistant, write or improve project instructions, create or refine a skill, set up memory or profiles, build or optimize a scheduled task, connect Claude to p...

Analyze and optimize an assistant task or project to make it run faster, use fewer tokens, reduce unnecessary steps, and improve overall structure. Use this skill whenever the user shares an assistant task or project and asks to optimize, improve, speed up, refactor, or reduce model usage. Also trigger when the user says things like "make this more efficient", "this task is slow", "can we trim this down", "review my task setup", or pastes an assistant task/project definition and asks for feed...

Route delegated work to the right model tier and effort level. Use this skill whenever the session is about to spawn subagents, split a task into parallel or independent parts, choose a model or effort for a subtask, workflow stage, or scheduled task, or when the user says things like "dispatch", "route this", "orchestrate", "fan out", "run in parallel", "which model should this use", or asks for a multi-step task that contains bulk, mechanical, or independent parts — including sweeps, audits...

Full-lifecycle git and GitHub management for the user's repositories — it diagnoses the repo's real state, then commits, branches, syncs, merges, and cleans up itself where it can, and hands over exact validated copy-paste commands where the session can't act (credentials, network, or environment limits). Use this skill whenever the user mentions git, GitHub, commit, push, pull, branch, merge, PR, squash, rebase, tag, release, .gitignore, or repository — AND for vague phrasings that imply ver...

Company policy guardrail, applying three enforcement tiers: hard block (T1), required check (T2), soft guidance (T3). Use this skill when the Policy Registry in §1 has been filled in for this organisation AND the request touches one of the policies listed there — typically drafting external or internal communications, handling classified data, choosing a tool or vendor, forwarding or summarising organisational content, or recommending an approach with security implications. Where it applies, ...

Run a structured review that produces a judgment the assistant reached on its own, rather than a reflection of the view the user already holds. Use whenever the user wants something reviewed, critiqued, checked, sanity-checked, or second-opinioned — a document, a plan, a decision, a prompt, a piece of code — and especially when they say they have already formed a view, have doubts, or want to know whether they are being agreed with. Trigger on phrases like "review this", "give me a second opi...

Run a phased security audit of Claude or OpenAI configuration and a target project. Use when the user asks to: review security, audit Claude Code setup, check for exposed credentials, set up security hooks, harden their Claude environment, scan a project for secrets, or anything like "check if my setup is secure", "audit my Claude config", "set up security hooks", "scan for credentials". Accepts an optional project path argument (e.g. `/security-review /path/to/project`) to scope project-leve...

Use this skill whenever the user wants to create a reusable template from an existing Claude artifact or setup — including chat system prompts, Assistant tasks, Assistant projects, or skills. Trigger when the user says things like "turn this into a template", "create a template I can share", "make this reusable", "export this as a template", "I want to share this setup with someone", or "create a template for [task/project/skill/chat]". Also trigger when a conversation contains a full Assista...

> **Portable task** — copy this file to any project's `tasks/` directory and run: > `Assistant, run tasks/audit-skill.md` > **Source guides:** `03_SKILLS.md`, `02_PROMPTING_BASICS.md`

> **Portable task** — copy this file to any project's `tasks/` directory and run: > `Assistant, run tasks/setup-skill.md` > **Source guide:** `03_SKILLS.md`