
contacts
Add, enrich, and manage contacts in Joel's Vault. Fire the Inngest enrichment pipeline for full multi-source dossiers, or create quick contacts manually. Use when: 'add a contact', 'enrich this person', 'who is X', 'VIP contact', 'update contact', or any task involving the Vault/Contacts directory.
- Installs
- 3.3K
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/joelhooks/joelclaw --skill contacts- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads contacts automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Contacts
Manage contacts in ~/Vault/Contacts/. Each contact is a markdown file with YAML frontmatter.
Contact File Location
~/Vault/Contacts/<Name>.md
Index file: ~/Vault/Contacts/index.md — wikilink list of all contacts.
Frontmatter Schema
---
name: Full Name
aliases: [nickname, handle]
role: Current Role / Title
organizations: [Org1, Org2]
vip: true # or false
slack_user_id: U0XXXXXXX
slack_dm_channel: D0XXXXXXX # null if unknown
website: https://example.com
github: username
twitter: handle
email: user@example.com
tags: [vip, instructor, creator, family, employee]
---
Sections
# Name
## Contact Channels
- Slack, email, social handles, website
## Projects
- Active projects, courses, collaborations
## Key Context
- Relationship notes, working style, history
## Recent Activity
- YYYY-MM-DD | channel | summary
See ~/Vault/Contacts/Matt Pocock.md for a fully enriched example.
Adding a Contact
Option 1: Fire the Enrichment Pipeline (preferred)
Send an Inngest event. The contact-enrich function fans out across Slack, Roam, web/GitHub, Granola, Brain-backed recall, and other indexed sources, synthesizes with LLM, and writes the Vault file.
# Via curl (CLI has OTEL import bug under Bun v1.3.9)
curl -s -X POST "http://localhost:8288/e/$INNGEST_EVENT_KEY" \
-H "Content-Type: application/json" \
-d '[{
"name": "contact/enrich.requested",
"data": {
"name": "Person Name",
"depth": "full",
"hints": {
"slack_user_id": "U0XXXXXXX",
"github": "username",
"twitter": "handle",
"email": "user@example.com",
"website": "https://example.com"
}
},
"ts": EPOCH_MS
}]'
Depth modes:
full(~60s, ~$0.05): All 7 sources + LLM synthesis. Use for new contacts or periodic refresh.quick(~10s, ~$0.01): Slack + memory only. Good for real-time VIP detection.
Hints are optional but help: Any known identifiers (Slack ID, GitHub, email, Twitter, website) seed the search and improve results.
Option 2: Quick Manual Create
For simple contacts where enrichment is overkill:
---
name: Person Name
aliases: []
role: Role
organizations: [Org]
vip: false
slack_user_id: null
website: null
github: null
twitter: null
email: null
tags: [tag1]
---
# Person Name
## Contact Channels
- ...
## Key Context
- ...
Write to ~/Vault/Contacts/Person Name.md and add [[Person Name]] to index.md.
Updating Contacts
Re-run enrichment with the existing vault path:
{
"name": "contact/enrich.requested",
"data": {
"name": "Person Name",
"vault_path": "Contacts/Person Name.md",
"depth": "full"
}
}
The synthesizer merges new data with existing content — it won't discard existing facts unless contradicted.
VIP Contacts (ADR-0151)
Mark vip: true in frontmatter. VIPs get deep enrichment + ongoing monitoring.
Deep Enrichment Playbook (one-time)
Every VIP gets the full treatment. This is what we did for Kent C. Dodds (Feb 26, 2026):
| Step | Source | What to Capture |
|---|---|---|
| 1. Web presence | Web search {name} + {org} | Bio, role, location, personal details |
| 2. Podcast/interviews | Web search {name} podcast interview | Appearance list, own podcasts, audiences |
| 3. Joel collaborations | Their website, appearances pages | Joint podcasts, co-organized events, shared projects |
| 4. Career timeline | Defuddle 2-3 key interview transcripts | Origin story, career arc, key decisions, values |
| 5. GitHub profile | GitHub API or web | Repos, followers, orgs, contribution patterns |
| 6. X/Twitter profile | X API v2 (use x-api skill) | Bio, followers, recent tweets, engagement |
| 7. Key relationships | Cross-reference transcripts + contacts | Who they work with, who they mention, who we know in common |
| 8. Content catalog | Website crawl (defuddle) | Courses, blog posts, open source projects |
| 9. Audience reach | Podcast counts, social followers | Conference circuit, community presence |
Index to Typesense after enrichment:
- Batch-import appearances/content to
discoveriescollection (NDJSON,action=upsert) - Tag all docs with person's name slug (e.g.
kent-c-dodds) for filtering - Fields:
id,title,url,summary,tags[],timestamp - Write a
Vault/Resources/{name}-media-appearances.mdreference doc linking back to contact
Output sections in the vault note:
- Background & Story (origin, career timeline)
- Teaching/Work Philosophy (or equivalent for non-educators)
- Key Relationships (cross-linked
[[wikilinks]]to other contacts) - Audience & Reach
- Content/Products
- Podcast/Collaboration History with Joel
- Recent Activity (timestamped)
Ongoing Monitoring (Phase 2-4 of ADR-0151)
| Channel | Tool | Signal |
|---|---|---|
| Google Alerts | joelclawbot Google account | Name mentions in news, blogs, press |
| X/Twitter list | joelclaw X account | Tweets, engagement |
| GitHub activity | GitHub API (polling) | New repos, releases |
| Podcast RSS | Feed monitoring | New episodes |
| Website changes | Periodic defuddle + diff | Blog posts, launches, bio changes |
High-signal (immediate): course launches, role changes, mentions of Joel/egghead/Skill, fundraising. Low-signal (daily/weekly digest): regular tweets, blog posts, OSS activity.
Current VIPs
- Get notified to Joel via gateway after enrichment
- Are refreshed weekly via scheduled cron
- Have priority in channel intelligence pipeline (ADR-0131, ADR-0132)
- Get ongoing monitoring when ADR-0151 Phase 2+ is implemented
Roam Research Enrichment
Joel's Roam archive (~/Code/joelhooks/egghead-roam-research/) contains the full egghead-era graph (2019-2024). Many contacts have extensive history there.
Quick Search (Python regex)
cd ~/Code/joelhooks/egghead-roam-research
python3 -c "
import re
with open('egghead-2026-01-19-13-09-38.edn', 'r') as f:
content = f.read()
pattern = r':block/string\s+\"([^\"]*?)\"'
matches = []
for m in re.findall(pattern, content):
if '[[SEARCH_TAG]]' in m.lower():
matches.append(m)
print(f'Found {len(matches)} blocks')
for m in matches[:30]:
print(f' - {m[:200]}')
"
People Taxonomy
People are tagged with relationship prefixes in Roam:
[[collaborator/Name]]— Strategic partners (Ian Jones, Alex Hillman)[[client/Name]]— egghead instructors (Matt Pocock, Jacob Paris)[[staff/Name]]— egghead team (Will Johnson, Daniel Miller, Maggie Appleton)[[name]](no prefix) — Informal references (Zac is[[zac]])
Page Title Search
python3 -c "
import re
with open('egghead-2026-01-19-13-09-38.edn', 'r') as f:
content = f.read()
pattern = r':node/title\s+\"([^\"]*?SEARCH_TERM[^\"]*?)\"'
for m in re.findall(pattern, content):
print(f' page: {m}')
"
Adding to Contacts
When extracting person data from Roam, add roam_tag to frontmatter:
roam_tag: "[[collaborator/Ian Jones]]"
This enables future re-queries and cross-referencing.
Datalog Queries (advanced)
The EDN file is Datomic-style. Clojure scripts exist at scripts/ for structured analysis. See the roam-research skill for full Datalog patterns.
Resolving Unknown People
When you encounter a Slack user ID (<@U0XXXXXXX>):
# Lease token and look up profile
SLACK_USER=$(secrets lease slack_user_token --ttl 5m)
curl -s "https://slack.com/api/users.info?user=U0XXXXXXX" \
-H "Authorization: Bearer $SLACK_USER" | jq '.user.real_name, .user.profile.email'
# Revoke only the exact lease ids acquired by this task; never all sessions’ leases.
Then fire enrichment with the resolved name and hints.
Inngest Function
- Function:
contact-enrich(packages/system-bus/src/inngest/functions/contact-enrich.ts) - Event:
contact/enrich.requested - ADR:
~/Vault/docs/decisions/0133-contact-enrichment-pipeline.md - Concurrency: 3 max
- Sources: Slack, Slack Connect, Roam archive, GitHub/web, Granola meetings, Brain-backed recall, and other indexed sources
Privacy
- Contact files are in Vault (private, not in public repos)
- Slack data stays private — never surface in public content
- Email/phone are stored for Joel's reference only
FAQ
What does the contacts skill do?
Add, enrich, and manage contacts in Joel's Vault. Fire the Inngest enrichment pipeline for full multi-source dossiers, or create quick contacts manually. Use when: 'add a contact', 'enrich this person', 'who is X', 'VIP contact', 'update contact', or any task involving the Vault/Contacts directory.
How do I install contacts?
Run npx skills add https://github.com/joelhooks/joelclaw --skill contacts in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/contacts/ (personal) or .claude/skills/contacts/ (project).
Which AI agents can use contacts?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is contacts safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains contacts?
It is published by joelhooks in joelhooks/joelclaw. It has 3,283 recorded installs.
More from joelhooks/joelclaw
docker-sandbox
joelhooks/joelclaw
Open the skill to read its SKILL.md instructions.
joel-writing-style
joelhooks/joelclaw
Open the skill to read its SKILL.md instructions.
task-management
joelhooks/joelclaw
Open the skill to read its SKILL.md instructions.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。