Skip to content
Agentmart
Submit a tool

scrum-next

Scrum board next-work triage.

Skill by lucavb

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying scrum-next?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/lucavb-scrum-next

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Scrum board next-work triage. Use when asked what to work on next, what is next on the board, or to choose an actionable Jira task, updates on the user's open PRs, or a PR review.

Use cases: productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/scrum-next

What's inside

Skill name
scrum-next
Description
Scrum board next-work triage. Use when asked what to work on next, what is next on the board, or to choose an actionable Jira task, updates on the user's open PRs, or a PR review.
License
MIT
Instructions
37 lines in SKILL.md · view on GitHub

Files (2)

  • README.md
  • SKILL.md

SKILL.md (first lines)

# Scrum next-work triage

Recommend work the user can start now. Treat the board as a queue, not as proof that an item is actionable.

## Triage

1. Identify the current user and active sprint.
2. Record any work the user says is already running elsewhere as **occupied**. Keep it out of recommendations until the user says it is free.
3. Build candidates in this order:
   1. assigned implementation or refinement work that is ready to start;
   2. the user's own open PRs that need a response (new review feedback, requested changes, failing checks, merge conflicts, or unresolved review threads awaiting the author);
   3. unassigned, ready implementation or refinement work in the active sprint;
   4. open PRs authored by someone else that still need the user's review.
4. Exclude QA work, tickets in QA review, tickets the user implemented, reviews the user has already approved on the current head, and work already in progress elsewhere. Do not exclude the user's own PRs when they need author action.

## Evidence

For every candidate, verify the evidence before recommending it:

- **Jira:** active-sprint membership, status, assignee, rank, dependencies, and ticket readiness.
- **GitHub (review):** PR exists and is open; author is not the user; user has not approved the current head; checks, mergeability, and unresolved review threads are known.
- **GitHub (own PR):** PR is open and authored by the user; there is new activity since the user's last response (review comments, review decisions, check runs, or mergeability) that requires author action.
- **Scope:** the work is implementation, refinement, or code review—not QA.

Use narrow queries first. Fetch full ticket or PR details only for the leading candidates.

## Choice

Recommend one item, with its link and the immediate first action. State why it is actionable using the evidence above.

If no active-sprint item qualifies, say so plainly. Offer the highest-ranked unassigned backlog candidate only after marking it as outside the active sprint, or ask whether the user wants to pull backlog work.

## Completion

Finish only when the recommendation is actionable for this user now, or when the absence of such work is explicit.

From lucavb/skills, MIT.

More from lucavb/skills

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Oct 13, 2026 (19 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from lucavb

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get scrum-next running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying scrum-next?

CallGet help
Cite this page

scrum-next skill. Agent Mart. https://agentmart.dev/skills/lucavb-scrum-next (last updated 2026-10-24)