3 of 9 projects need attention
9 active projects: 6 on track, 2 at risk, 1 off track. Billing v2 moved to off track this week, and Mobile onboarding has had no update in 12 days.
Every Friday afternoon: each active Linear project's latest update and health, on track, at risk or off track, and the projects that went quiet.
Reads
You get
The card on the right is a sample. Yours shows your own numbers and updates in place every run.
What lands on your board
9 active projects: 6 on track, 2 at risk, 1 off track. Billing v2 moved to off track this week, and Mobile onboarding has had no update in 12 days.
Linear project updates are good at the project level and hard to read across twenty projects. Founders and heads of product end up clicking through each one on Friday to find the two that slipped.
The agent reads every active project's latest update and health, compares it with last Friday, and posts one digest: counts by health, the projects that moved to at risk or off track, and the ones whose last update is more than a week old. Each project gets one line in plain words, with a link back.
Query projects(first: 50) with name url health healthUpdatedAt targetDate progress lead { name } status { name type } lastUpdate { body health createdAt user { name } }, and keep the projects whose status.type is started.
A project went quiet when lastUpdate is missing or its createdAt is more than 7 days old. Also flag projects whose targetDate has passed while progress is below 1.
Compare health (onTrack, atRisk, offTrack) with the values saved last Friday in a JSON file, and list every project that changed, worst first.
Summarize each update body in one line of at most 120 characters, keeping dates and blockers. Group by health, put changed and quiet projects at the top, and link each project's url.
With BRIEFKIN_TOKEN set, the agent sends the result as one card that updates in place every run. Without it, you get the report in the chat.
Pick your agent, where the data comes from and how to schedule it; the commands below follow.
One command. It puts the SKILL.md in ~/.claude/skills and in ~/.agents/skills, which Codex, Cursor, Gemini CLI, Copilot CLI and OpenCode read too.
shellcurl -fsSL https://briefkin.dev/skills/linear-project-updates-digest/install | shAsk Claude Code:
promptRun the linear-project-updates-digest skillOr paste the prompt instead of installing:
promptUsing the Linear GraphQL API (or the Linear MCP server), list the projects whose status type is started, with health, lead, target date, progress and the last project update (body, health, date, author). Count them by health, flag projects with no update in the last 7 days or with a target date already passed, and tell me which ones changed health since last week if you know. Summarize each update in one line. End with the one project I should raise first.Fridays at 15:00, from cron on any machine where Claude Code is signed in:
crontab0 15 * * 5 claude -p "Run the linear-project-updates-digest skill"Add it with crontab -e. A laptop asleep at that time runs it when it wakes if you use launchd or Task Scheduler instead; GitHub Actions works for the API route.
Connect Briefkin once with curl -fsSL https://briefkin.dev/install | sh and every run lands on your board as a report card. How setup works
SKILL.md---
name: linear-project-updates-digest
description: "Every Friday afternoon: each active Linear project's latest update and health, on track, at risk or off track, and the projects that went quiet. Use when the user asks for this, or when it runs on a schedule."
---
# Linear project updates digest
Every Friday afternoon: each active Linear project's latest update and health, on track, at risk or off track, and the projects that went quiet.
Linear project updates are good at the project level and hard to read across twenty projects. Founders and heads of product end up clicking through each one on Friday to find the two that slipped.
The agent reads every active project's latest update and health, compares it with last Friday, and posts one digest: counts by health, the projects that moved to at risk or off track, and the ones whose last update is more than a week old. Each project gets one line in plain words, with a link back.
## Two ways to get the data
Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used.
## Route A: API or MCP server
### What you need
- Access to the teams' projects in Linear, through the Linear MCP server or connector, or a read-only key in `LINEAR_API_KEY`.
- Which teams to cover, if not all of them.
If something is missing, say what and stop; do not invent numbers.
### Steps
1. **Read the active projects** (Linear): Query `projects(first: 50)` with `name url health healthUpdatedAt targetDate progress lead { name } status { name type } lastUpdate { body health createdAt user { name } }`, and keep the projects whose `status.type` is `started`.
2. **Check freshness**: A project went quiet when `lastUpdate` is missing or its `createdAt` is more than 7 days old. Also flag projects whose `targetDate` has passed while `progress` is below 1.
3. **Find health changes**: Compare `health` (`onTrack`, `atRisk`, `offTrack`) with the values saved last Friday in a JSON file, and list every project that changed, worst first.
4. **Write the digest**: Summarize each update `body` in one line of at most 120 characters, keeping dates and blockers. Group by health, put changed and quiet projects at the top, and link each project's `url`.
## Route B: the browser
### What you need
- Signed in to Linear as a member of the workspace who can see the projects; guests only see the projects shared with them.
If something is missing, say what and stop; do not invent numbers.
### Steps
Start at https://linear.app. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears.
1. **Open the projects view**: Open `https://linear.app`, which lands in your workspace, and click **Projects** in the sidebar, then **All projects**. Add the filter **Status** is **In Progress** so only started projects remain.
2. **Show health and the latest update**: Use **Display** to group by **Health** and to show the **Lead**, **Target date**, **Progress** and **Last updated** columns. Note the counts of On track, At risk and Off track.
3. **Find the quiet projects**: Add a second filter, **Date**, on the latest project update, older than 7 days; Linear also marks these with the dashed "Update missing" icon. Note projects whose target date has passed while progress is below 100%.
4. **Read each update**: Open each project and its **Updates** tab, read the newest update and its author and date, and write one line of at most 120 characters that keeps dates and blockers.
5. **Compare with last Friday**: Check each health against the digest from last week (keep the previous list in a note) and put the projects that moved, worst first, at the top, with their project links.
Note: The Projects view already shows health, so the browser route works well for up to a few dozen projects. Linear loads update bodies only when you open a project, so twenty projects means twenty page loads.
## The report
- **Counts by health**: on track, at risk, off track, and no update this week.
- **Changed this week**: projects whose health moved, with the reason from their update.
- **Every active project**: health, lead, target date and the latest update in one line.
- One line on the project to raise first.
## Post it to Briefkin
When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on.
```bash
[ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env
curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \
-H "authorization: Bearer $BRIEFKIN_TOKEN" \
-H "content-type: application/json" \
-d @- <<'JSON'
{
"v": 1,
"event_id": "linear-project-updates-digest/<date of this run, e.g. 2026-10-16>",
"item_key": "linear-project-updates-digest",
"project": "Acme",
"source": "Linear project updates digest skill",
"kind": "update",
"title": "3 of 9 projects need attention",
"summary": "9 active projects: **6 on track**, **2 at risk**, **1 off track**. Billing v2 moved to off track this week, and Mobile onboarding has had no update in 12 days.",
"widget": [
{
"type": "Badges",
"props": {
"items": [
{
"label": "On track 6",
"tone": "ok"
},
{
"label": "At risk 2",
"tone": "warn"
},
{
"label": "Off track 1",
"tone": "bad"
},
{
"label": "No update 1"
}
]
}
},
{
"type": "Table",
"props": {
"columns": [
"Project",
"Health",
"Lead",
"Target",
"Latest update"
],
"align": [
"left",
"left",
"left",
"left",
"left"
],
"rows": [
[
"Billing v2",
"Off track",
"Dana",
"Nov 14",
"Provider review moved to Nov 3; launch likely slips two weeks."
],
[
"Search relevance",
"At risk",
"Priya",
"Oct 31",
"Ranking model ready; the evaluation set still misses 40% of queries."
],
[
"SSO for teams",
"At risk",
"Theo",
"Nov 7",
"SAML flow done; second identity provider blocked on a test tenant."
],
[
"Mobile onboarding",
"On track",
"Lena",
"Dec 5",
"No update in 12 days."
],
[
"Usage dashboard",
"On track",
"Sam",
"Oct 24",
"Charts shipped behind a flag; rollout to 10% on Monday."
],
[
"API rate limits",
"On track",
"Marco",
"Nov 21",
"Limits enforced in staging; docs in review."
]
]
}
},
{
"type": "Callout",
"props": {
"text": "Billing v2 went from at risk to off track this week. Raise it first in Monday's review.",
"tone": "bad"
}
}
]
}
JSON
```
Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report.
## Run it on a schedule
Suggested: Fridays at 15:00 (`0 15 * * 5`). From cron, with the agent signed in on that machine:
```bash
0 15 * * 5 claude -p "Run the linear-project-updates-digest skill"
# Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run
```
Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/linear-project-updates-digest#schedule
Source: https://briefkin.dev/skills/linear-project-updates-digest
Access to the teams' projects in Linear, through the Linear MCP server or connector, or a read-only key in LINEAR_API_KEY.
Which teams to cover, if not all of them.
https://mcp.linear.app/mcp. Add Linear from Claude's connector directory, or run claude mcp add --transport http linear https://mcp.linear.app/mcp in Claude Code, and sign in with OAuth.LINEAR_API_KEY, and send it as the Authorization header with no Bearer prefix. For a workspace bot, an OAuth app with the read scope does the same job.When you create the key, give it Read access and only the teams in the report; it then can't create or edit issues.
It still appears with its last update and that update's age, under "No update". Its health stays whatever the last update said, which is why the digest calls out quiet projects instead of trusting an old "on track".
Yes. Name the teams in the prompt and the skill keeps projects whose teams include one of them. Use a separate item_key per team if several leads each want their own card.
No. The skill runs with your own agent and gives you the report in the chat. With a Briefkin token set, each run also posts it to your board as a report card, so you can glance at it instead of asking again.
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot CLI, OpenCode, Windsurf and Amp all read SKILL.md files. The install command puts it in ~/.claude/skills and ~/.agents/skills, where they look. ChatGPT, the Claude app and Grok take the prompt instead. Pick your agent under "Install and run it" and the commands change to match.
Yes. Switch the data source to "Your browser" and the steps change to the Linear pages themselves: the agent opens linear.app in a browser you are signed in to and reads the numbers off the page. Claude Code, Codex, Cursor, Claude app and ChatGPT can drive a browser out of the box; Gemini CLI, Copilot CLI and OpenCode need a Playwright or Chrome DevTools MCP server first. It is slower than the API and needs you signed in, so it suits a report you run by hand or from a scheduler on your own computer.
Skills are free to use with any agent. Briefkin is where their results land: one board for every report, number and question your agents send, with a ping when something needs you.
Free during the open beta. No card.