{"$schema":"https://schemas.agentskills.io/discovery/0.2.0/schema.json","skills":[{"name":"add-person","type":"skill-md","description":"Add or update someone in noticed without creating duplicates. Use when the user asks to add, save, remember, or update a person, or shares a profile with relationship context. A clear request is permission to make reversible relationship writes. Ask only when identity or essential context is unclear.","url":"/.well-known/agent-skills/add-person/SKILL.md","digest":"sha256:c99db46682f14e55dcc357279bbf36c3c2d7c5037223317ac26dbb74fcba7ec9"},{"name":"event-debrief","type":"skill-md","description":"Process a meeting or event dump into structured pieces in noticed: people, meeting notes, follow-ups, ideas, references. Use whenever the user pastes a debrief from any meeting (1:1 call, walk, dinner, group event). Trigger on \"debrief\", \"process this voice note\", \"here are my notes from [event]\", \"I just had a [meeting / walk / dinner] with [person]\", or any post-meeting dump. Parses the dump, resolves each person against the user's network, builds a unified preview, and writes everything in one fan-out on the user's go-ahead.","url":"/.well-known/agent-skills/event-debrief/SKILL.md","digest":"sha256:eb6f434ac48916afd01d1165f3c603957a81e513e88856ba13755e0a2f4eb29f"},{"name":"research-person","type":"skill-md","description":"Prepare the user for a meeting or conversation with one person by combining their existing relationship history in noticed with current public context. Use for requests such as \"research X\", \"prep me for X\", \"what do we know about X\", or \"tell me about X\". Research is read-only until the user asks to save it.","url":"/.well-known/agent-skills/research-person/SKILL.md","digest":"sha256:6cd3723c8e59ed127bc2daa7f4ea6138f78c4c92cbab3cb47ce7e9744ef696d9"},{"name":"follow-up","type":"skill-md","description":"Draft a follow-up message to someone the user recently met IRL. Figures out new vs existing in their network, picks the right channel (email, linkedin, whatsapp, telegram, sms), suggests an angle from context, drafts in the user's voice with something actionable in it. Returns the text to copy/paste (subject too, for email) plus a link to open the chat. Logs the touchpoint only after the user confirms it went out. Use whenever the user says \"follow up with X\", \"draft a message to X\", \"thank X for the meeting\", \"send X our deck\", or similar.","url":"/.well-known/agent-skills/follow-up/SKILL.md","digest":"sha256:e68f122dd7911d63e99f80900fd3bd1d8ba2a894da1674d67cf361171b6fb87f"},{"name":"intro","type":"skill-md","description":"Help the user with introductions across fundraising, sales, hiring, investing, partnerships, and networking. Four jobs: find the best warm path to a target person, draft an intro email between two people, write an ask to a connector requesting an intro to a target (with a forwardable blurb), or write a backchannel note asking a mutual to reinforce the user's credibility after a meeting. Pulls paths and relationship strength from the noticed network, enriches the target from the web, and returns copy/paste drafts. Use whenever the user says \"who can intro me to X?\", \"find a path to X\", \"draft an intro between A and B\", \"ask X to connect me with Y\", \"write an intro request\", or \"can someone vouch for me with X?\".","url":"/.well-known/agent-skills/intro/SKILL.md","digest":"sha256:29fb400d43b818ad4d3f9ed42697ec0ab25eab1f1241d97feb3840ee9f7ae718"},{"name":"search-network","type":"skill-md","description":"Find people in the user's noticed network through a direct natural-language lookup. Use for questions such as \"who do I know at X?\", \"find designers in Berlin\", \"any investors in my network?\", or \"how many founders do I know?\". This is a focused, read-only lookup. Use a broader goal workflow when the person wants help deciding who could advance a business goal.","url":"/.well-known/agent-skills/search-network/SKILL.md","digest":"sha256:f3c2755ccf89b911a8b1d2d059d800658f1d16e80f23dc39493d62906bb705cf"},{"name":"match-identities","type":"skill-md","description":"Review proposed identity matches in noticed, merge records that are clearly the same person, mark clear false positives as different people, and ask the user about genuinely ambiguous pairs. Also attach verified LinkedIn or GitHub profiles to contacts that are missing one.","url":"/.well-known/agent-skills/match-identities/SKILL.md","digest":"sha256:3232cc434ffbc40051789eaea59e607eed6f031d8d788a53398b83feed5b8391"}]}