agentleFS
cenconq25cenconq25/claude-code-app-studio/.claude/skills/sprint-status/SKILL.md

sprint-status

Skill40 starsChanged 7 months agoMITView on GitHub

Fast sprint status check — reads the active sprint plan, scans story files for status, and produces a concise progress snapshot with burndown read and emerging risks. Use any time during a sprint for situational awareness.

11 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. 1 is common, 9 are distinctive, and 2 are very specific to this project.

  • 1

    Common

    Most of the 11 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before standup, to prep

    line 21
  2. Distinctive:

    After a story moves status, to confirm the snapshot updates

    line 22
  3. Very specific:

    All story files in production/epics/*/story-*.md

    line 29
  4. Distinctive:

    If none exist, stop:

    line 44
  5. Very specific:

    If multiple have Status: Active, surface the conflict and ask which to report on.

    line 47
  6. Common:

    Start and end dates

    line 55
  7. Distinctive:

    If implied finish ≤ days remaining → On track

    line 89
  8. Distinctive:

    If implied finish ≤ days remaining × 1.2 → Tight

    line 90
  9. Distinctive:

    If implied finish > days remaining × 1.2 → At risk

    line 91
  10. Distinctive:

    If multiple stories Blocked → Blocked-heavy (mention even if other numbers look OK)

    line 92
  11. Distinctive:

    Keep the output to roughly 25-40 lines.

    line 143
  12. Distinctive:

    If the plan's backlog table differs from the live story Status (e.g., plan says Ready but story says Complete), surface it:

    line 149

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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

Sprint Status

A fast read of the in-flight sprint. Where things stand, what is at risk, what blocks. Read-only. Should complete in seconds.


Purpose / When to Run

Run when:

  • The user asks "how is the sprint going" / "sprint status" / "where are we"
  • Mid-sprint check-in
  • Before standup, to prep
  • After a story moves status, to confirm the snapshot updates

Distinct from /scope-check (which evaluates scope creep) and /milestone-review (broader scope).

Inputs

  • The active sprint plan at production/sprints/
  • All story files in production/epics/*/story-*.md
  • production/session-state/active.md (optional)

Outputs

  • Printed snapshot. No file writes.

Phase 1: Find the Active Sprint

Glob production/sprints/*.md sorted by filename (sprint-001, sprint-002, ...). The active sprint is:

  • The one with Status: Active in its header
  • Else the most recently dated one

If none exist, stop:

"No sprint plan found. Run /sprint-plan new to create one."

If multiple have Status: Active, surface the conflict and ask which to report on.


Phase 2: Read Sprint Plan

Extract:

  • Sprint number and slug
  • Start and end dates
  • Goal
  • Backlog table with stories and statuses (the plan's view)
  • Capacity
  • Risks

Phase 3: Refresh from Story Files

The sprint plan's backlog table may be stale if engineers moved story Status without touching the plan. Re-read each story listed in the backlog:

  • Current Status (Ready / In Progress / Blocked / Complete)
  • Whether it's been touched recently (file mtime)
  • Whether it has a ## Implementation Notes or ## Mid-Story Update block (signals work in flight)

Build a fresh status tally:

  • Total
  • Complete
  • In Progress
  • Blocked
  • Ready (not yet started)

Phase 4: Burndown Read

Compute:

  • Days elapsed in sprint
  • Days remaining
  • Stories complete vs. total
  • Implied velocity: complete / days elapsed
  • Implied finish: total / velocity (in days)

Compare implied finish to days remaining:

  • If implied finish ≤ days remaining → On track
  • If implied finish ≤ days remaining × 1.2 → Tight
  • If implied finish > days remaining × 1.2 → At risk
  • If multiple stories Blocked → Blocked-heavy (mention even if other numbers look OK)

Phase 5: Detect Risks

Scan for:

  • Stories In Progress for >2 days (file mtime suggests stall)
  • Stories Blocked — list the blockers
  • Stories whose governing ADR is Proposed (story should be Blocked but isn't yet)
  • Stories whose Manifest Version is older than the current control-manifest version
  • Sprint goal at risk: any story in the critical path Blocked or stalled

Phase 6: Output

# Sprint <NNN>: <slug>

**Goal**: <goal>
**Status**: <On track / Tight / At risk / Blocked-heavy>
**Day**: <N> of <M> (<X> remaining)

## Progress
- Complete: <N> / <total> (<%>)
- In progress: <N>
- Blocked: <N>
- Not yet started: <N>

## Burndown
- Velocity so far: <N> stories / <X> days = <Y>/day
- Implied finish: <date>, vs. sprint end <date>

## Stories in motion
- [In Progress] story-NNN: <title> — engineer <name or unassigned>, last touched <date>
- [In Progress] story-NNN: <title> — STALLED (last touched <N> days ago)

## Blockers
- story-NNN: <title> — Blocked because <reason>. Action: <suggested fix>
- ...

## Risks emerging
- <list — stalled stories, manifest drift, scope creep signals>

## Recommended next actions
- For users picking up work: start with story-NNN (highest leverage)
- For PMs: <if at risk, suggest /scope-check; if blocked-heavy, schedule a blocker-clearance>
- For leads: <if any Manifest version drift, suggest re-running /create-control-manifest>

Keep the output to roughly 25-40 lines. This skill should be skimmable.


Phase 7: Compare to Plan

If the plan's backlog table differs from the live story Status (e.g., plan says Ready but story says Complete), surface it:

"Note: sprint plan's backlog table is stale — <X> stories have advanced beyond what the plan shows. Run /sprint-plan update to refresh."


Quality Gates

  • Output completes in seconds — no specialist spawns, no deep reads beyond story headers
  • Status verdict matches the data (no "On track" when 5 of 8 are Blocked)
  • Read-only

Examples

/sprint-status

  • Sprint 003, day 6 of 10
  • 4 Complete, 2 In Progress, 1 Blocked, 1 Ready
  • Velocity: 0.67/day → implied finish: 4 more days → on track
  • Blocker: story-005 (biometric) — ADR Proposed, action: advance ADR-0007
  • Recommended: pick up story-007 next (foundation for two downstream)

/sprint-status mid-sprint with stall

  • Sprint 002, day 7 of 10
  • 2 Complete, 4 In Progress (3 stalled >2 days), 0 Blocked
  • Status: At risk — implied finish 6 more days vs. 3 remaining
  • Recommended: immediate sprint review or scope reduction; run /scope-check

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.