Update to Unabyss

{
  "description": "Load who the user is, what they're working on, and what matters to them right now — so every subsequent skill or task has full context without asking. Use this skill at the start of any session where personal or company context would improve the output. Also trigger when the user says tell me what you know about me, what's my context, load my profile, who am I, or before running any skill that needs to know the user's role, company, or current priorities.",
  "included_files": [],
  "name": "personal-context",
  "skill_md_contents": "---\nname: personal-context\ndescription: \"Load who the user is, what they're working on, and what matters to them right now — so every subsequent skill or task has full context without asking. Use this skill at the start of any session where personal or company context would improve the output. Also trigger when the user says tell me what you know about me, what's my context, load my profile, who am I, or before running any skill that needs to know the user's role, company, or current priorities.\"\n---\n\n# Personal Context\n\nLoad a rich, complete picture of the user from Unabyss — identity, company, current work, priorities, relationships, and context that would otherwise need to be re-explained every session.\n\n## Required Integrations\n\nThis skill uses **Unabyss MCP** — `whoami` for identity, `query` for current context, `agentic_query` for deeper synthesis when needed.\n\n> If Unabyss is not connected, tell the user: \"This skill requires Unabyss MCP. You can connect it from the Tools menu.\"\n\n---\n\n## How to Run\n\n### Step 1 — Call `whoami`\n\nCall `whoami` first. Returns name, role, and key stored facts. Fast — always start here.\n\n### Step 2 — Enrich with `query`\n\nFollow up with a broader `query` to fill out the picture:\n\n```\nTell me everything relevant about this user — their company, what they're building, current stage, team, key priorities, active projects, recent decisions, open challenges, and anything important happening right now.\n```\n\n### Step 3 — Escalate to `agentic_query` if context is thin\n\nIf the above returns limited information, run `agentic_query`:\n\n```\nSynthesize a full profile of this user from everything available across all connected sources — professional background, what they're working on, their company's stage and traction, active challenges, important relationships, communication patterns, and any goals or priorities they've mentioned.\n```\n\n### Step 4 — Present the context\n\nSurface everything loaded in a structured, readable format:\n\n---\n\n**Personal Context — [Name]**\n\n**Who you are**\nName, role, company. Background if relevant — what brought them here, what they've built before.\n\n**What you're building**\nThe product or company: what it does, who it's for, what problem it solves. Current stage.\n\n**Traction & stage**\nKey metrics, funding, customer count — whatever signals where the company stands right now.\n\n**Team**\nKey people, size, structure. Anyone important to know about.\n\n**Current focus**\nWhat they're actively working on right now — the live priorities, not the long-term vision.\n\n**Active challenges**\nWhat's hard, what's unresolved, what they're figuring out. Open questions.\n\n**Recent decisions**\nSignificant things decided recently that provide context for current work.\n\n**Key relationships**\nImportant customers, investors, partners, or collaborators that show up in their context.\n\n**Communication style**\nHow they work and communicate — useful for tailoring subsequent output.\n\n**What to keep in mind**\nAnything else Unabyss surfaces that's relevant to working with this person effectively.\n\n---\n\nThen confirm: \"Context loaded. What would you like to work on?\"\n\n---\n\n## Output Rules\n\n- Call `whoami` → `query` → `agentic_query` in sequence, escalating only if the previous step is thin\n- Surface everything available — this is a rich load, not a brief summary\n- If a section has no signal, omit it rather than leaving it blank\n- If Unabyss returns very little overall, tell the user their profile may be sparse and suggest connecting more sources\n- Never ask the user to fill gaps — load what exists\n"
}