Standard

Documentation Index

Fetch the complete documentation index at: https://docs.xysq.ai/llms.txt

Use this file to discover all available pages before exploring further.

Skills are system instruction files that tell your AI agent exactly how to work with xysq. Install a skill once and your agent knows how to authenticate, what to capture, when to recall, and how to use tags — without you explaining it every session.

​

Why skills matter

Modern coding agents (Claude Code, Cursor, Codex, Windsurf, Copilot CLI, Gemini CLI) all load instruction files at session start. Anthropic formalised this pattern as Agent Skills — portable, model-readable instruction packs that an agent loads on demand to acquire a specific capability. Without a skill, you re-explain context every session: who you are, what you’re working on, which tools you prefer. With a skill, the agent starts informed and stops asking. Less re-explanation → fewer tokens → faster, sharper output. xysq ships two tiers of skill so you get this benefit on day one and again over time as the agent learns who you are. Further reading from Anthropic:

• Introducing Agent Skills — the engineering rationale
• Skills overview — the official spec
• Equipping agents for the real world with Agent Skills — design principles

​

How it works

Skills come in two tiers: Baseline skill — available immediately, no memories required. A hand-crafted set of instructions covering the core protocol: session start, aggressive capture, surgical recall, knowledge handling, and consent rules. Works from the moment you install it. Personalised skill — unlocked once you have more than 5 memories. xysq reflects on your memory bank and injects a personalised section into the skill. Your agent starts each session already knowing your working style, active projects, tool preferences, and agent behaviour notes. For the full mechanics — what gets injected, when it regenerates, how directives feed it — see Personalised skills.

​

Installing your skill

​

Step 1 — Download from the dashboard

Go to app.xysq.ai and open the Dashboard. The Get Started panel has a Download Skill button. Click it — a dialog opens with download options for every supported platform.

​

Step 2 — Choose your platform

The Install guides page covers every supported agent: Claude Code, Claude Desktop, Claude.ai (web), Cursor, Windsurf, Codex CLI, Gemini CLI, Antigravity, and GitHub Copilot CLI. Jump to your agent from the page’s right-side nav. Only Claude products consume Anthropic’s Agent Skills format natively. For other agents, xysq emits the same content in the rules-file or system-prompt format that tool expects — the instructions are identical, only the wrapper differs.

​

Step 2b — Attaching the skill in Claude (web / desktop)

The video below shows how to paste your skill into Project Instructions in Claude.ai — the same steps apply to Claude Desktop.

​

Step 3 — Verify it’s active

On your first substantive message in a new session, the agent should call memory_recall(query=<your message>, budget="low") to pull relevant context before answering. That’s the skill working. authenticate() runs lazily — only on the first write (memory_retain, memory_delete, knowledge_add) — not at session start. memory_reflect is reserved for synthesis questions (“what do I prefer about X”, “summarise my stance on Y”), not warmup.

​

Getting a personalised skill

Once you have more than 5 memories stored, the Get Started panel will prompt you to generate a personalised skill. Click Download personalised skill — xysq compiles a personalised section from your memory’s structured signals (identity, communication style, preferences, current context, plus any directives you’ve set) and injects it into the skill file. For the full breakdown of what gets injected, when it regenerates, and how directives feed it, see Personalised skills. Download the updated file and replace your existing skill installation.

​

Keeping your skill current

Your skill evolves as your memory bank grows. xysq checks whether your memories have changed meaningfully since the last generation — if they have, a new version is written. Client-side daily refresh — the dashboard silently checks whether your personalised skill is more than 24 hours old each time you open it. If it is, it regenerates in the background and updates the version number. You’ll see the new version available to re-download.

​

The north star

Every skill is written around a single principle: less tokens = same or better output. Agents that use xysq effectively don’t need you to re-explain your context at the start of every session. They don’t ask what project you’re working on. They don’t forget your preferences. They start informed. The skill teaches your agent to capture aggressively — every decision, correction, preference, and fact — so that future sessions cost fewer tokens to reach the same quality of output. The memory you build today is tokens saved tomorrow.

​

What the skill instructs

Session start protocol (MCP platforms — Claude Code, Claude Desktop, Cursor, Windsurf, generic) On your first substantive message (not greetings):

1. Call memory_recall(query=<your message shaped as a lookup>, budget="low") — pulls relevant memories and wiki entries in parallel. The results become task-specific context before the agent answers.
2. Call authenticate() lazily, on the first write (memory_retain, memory_delete, knowledge_add) — not at session start.
3. Call memory_tags() just before the first memory_retain.

Capture rules Recall vs reflect — pick one, never both for the same question.

• memory_recall(query, budget="low") — default. Targeted lookup of facts and recent memories. Used on every substantive turn.
• memory_recall(query, budget="mid"/"high") — broader pulls, used sparingly.
• memory_reflect(query) — synthesis only. Reserved for questions that require reasoning across memory: “what do I prefer about X”, “summarise my stance on Y”, “compare my past decisions on Z”. Not for warmup.

​

Skill versions

Every time a new personalised skill is generated, the version number increments. All versions are stored — nothing is deleted. You can see the current version and when it was last generated from the Dashboard.