agentleFS
pawellachpawellach/pm-ai-prompts/skills/linear-sprint-dashboard/SKILL.md

linear-sprint-dashboard

Skill0 starsChanged 2 months agoMITView on GitHub

Pull current sprint state from Linear and produce a status dashboard with health indicators and blockers

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the current cycle (sprint) from Linear and produce a structured status dashboard suitable for a standup, sprint review, or async Slack …

    line 8
  2. Distinctive:

    Use this skill when the user says:

    line 12
  3. Distinctive:

    If multiple active cycles exist, ask the user which one to report on.

    line 31
  4. Distinctive:

    If no active cycle: check for the most recently completed cycle and note that the sprint has ended.

    line 33
  5. Distinctive:

    Ask the user which format they want, or default to the full dashboard if not specified.

    line 154
  6. Distinctive:

    No cycle configured: If the team does not use cycles, offer to generate a dashboard based on label + status filter instead (e.g., "show all …

    line 158
  7. Distinctive:

    Multiple teams: Run the dashboard for each team separately and produce a roll-up summary at the top.

    line 162

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Linear Sprint Dashboard

Read the current cycle (sprint) from Linear and produce a structured status dashboard suitable for a standup, sprint review, or async Slack update.

When to use this skill

Use this skill when the user says:

  • "Give me the sprint status"
  • "What's the current cycle looking like?"
  • "Prepare the standup dashboard"
  • "What's blocked / what's at risk in Linear?"
  • "Sprint health check"

Prerequisites

  • Linear MCP connected (mcp__linear__* tools available)
  • Team ID or team name known (ask if not)

Step 1 — Find the active cycle

Use: mcp__linear__list_cycles
Parameters: { teamId: "<team_id>", filter: { isActive: true } }

If multiple active cycles exist, ask the user which one to report on.

If no active cycle: check for the most recently completed cycle and note that the sprint has ended.

Step 2 — Pull all issues in the cycle

Use: mcp__linear__list_issues
Parameters: { 
  filter: { 
    cycle: { id: { eq: "<cycle_id>" } }
  },
  includeArchived: false
}

For each issue, capture:

  • ID, title, status, assignee, priority, labels
  • Whether it has any blockers (blocked_by relations)
  • Estimate (story points or time)
  • Updated date (to detect stale issues)

Step 3 — Compute cycle health metrics

Calculate:

MetricFormula
Completion rateDone issues / Total issues × 100%
In-progressCount of issues in "In Progress" / "In Review"
Not startedCount of issues in "Todo" / "Backlog"
BlockedCount of issues with blockers or "Blocked" status
StaleIssues not updated in >3 working days
UnassignedIssues with no assignee
OverdueIssues past their due date (if due dates set)

Health score:

  • 🟢 Green: Completion rate on track for cycle end (>= expected % complete given days elapsed)
  • 🟡 Yellow: 10-20pp behind expected pace, or 1+ blocked issues
  • 🔴 Red: >20pp behind, or 2+ blocked issues, or unresolved blockers with no owner

Step 4 — Identify risks and highlights

Blockers: List all blocked issues with:

  • Issue ID and title
  • Who is blocked (assignee)
  • What is blocking them (if captured in Linear)
  • Days blocked

At-risk items: Issues that are In Progress but have not been updated in >2 working days.

Completed highlights: List up to 5 recently completed issues (most impactful first, based on priority label or estimate).

Step 5 — Generate dashboard output

Produce a structured report in this format:


Sprint Dashboard — [Team Name] — [Cycle Name]

Date: [Today] | Cycle end: [End date] | Days remaining: [N]

Health: 🟢 / 🟡 / 🔴 [status]

MetricValue
Total issuesN
✅ DoneN (XX%)
🔄 In ProgressN
📋 Todo / Not startedN
🚫 BlockedN
⚠️ Stale (>3 days)N
👤 UnassignedN

Expected completion at this point in cycle: XX% | Actual: XX%


🚫 Blockers

IssueTitleAssigneeBlocked SinceBlocker
[ID][Title][Name][N days][Description or "Unknown"]

No blockers if none.


⚠️ At Risk

IssueTitleAssigneeLast Updated

No at-risk items if none.


✅ Recently Completed (last 3 days)

  • [ID] [Title] — [Assignee]

📋 Not Started (by priority)

List unstarted issues grouped by priority: Urgent → High → Medium → Low.


Recommendation

[1-3 sentences: what does the team need to focus on for the rest of the cycle? Any escalations needed?]


Formatting variants

Standup format (shorter): Skip the full "Not Started" list. Focus on Blockers + At Risk + Completed Yesterday.

Async Slack format: Produce a text-only version without markdown tables — use emoji + bullet points instead.

Weekly executive summary: Drop issue-level detail. Show only health status, completion %, blocker count, and recommendation.

Ask the user which format they want, or default to the full dashboard if not specified.

Common issues

No cycle configured: If the team does not use cycles, offer to generate a dashboard based on label + status filter instead (e.g., "show all In Progress issues in project X").

Large cycle (50+ issues): Summarize by assignee or label group — do not list all 50 issues.

Multiple teams: Run the dashboard for each team separately and produce a roll-up summary at the top.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.