sprint
Skill0 starsChanged 25 days agoMITView on GitHub
Plan your sprint and your day. "/sprint" pulls the tickets assigned to you in the current (or next) sprint, and distributes them across business days so everything finishes before the sprint ends. "/sprint today" reads that plan and says what to tackle today and where each ticket really stands (not started, branch, PR open, changes requested, approved, merged). Once a plan exists, re-runs follow it, check briefly for changes and re-plan from today when behind or the sprint changed (no approval needed, unattended runs included). Use on "plan my sprint", "plan the next sprint", "what should I work on today", "plan my day", "/sprint", "/sprint today".
27 other projects use a version of this.
Adopted by
Most recently taken up by
- varelaia/claude-skills-publictheir own version, first seen Nov 8, 2026
- naman10parikh/pennytheir own version, first seen Nov 8, 2026
- naman10parikh/wikimemtheir own version, first seen Nov 8, 2026
- dagonet/claude-code-toolkittheir own version, first seen Nov 1, 2026
- atelier-fashion/adlc-toolkittheir own version, first seen Oct 31, 2026
- naman10parikh/turbotheir own version, first seen Oct 25, 2026
Used with
Projects with it also use ecosystem-reference, fractal-delegation and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
naman10parikhSkillecosystem-reference
Quick-access directory of Claude Code ecosystem repos, skills, plugins, MCPs, and patterns. Use when improving the harness.
Also in 5 projects that use this
naman10parikhSkillfractal-delegation
Also in 5 projects that use this
KirchliveSkillskill-routing
Decides which of the installed skills a task needs and loads them before the work starts. This skill should be used at the beginning of any multi-step task — build, fix, refactor, migrate, review, plan, release, research, write, design, video — and again at every phase change, after context compaction, and when work moves into a different part of the codebase. Use it for requests like "let's build X", "fix this bug", "refactor Y", "plan the migration", "review this", and also when the user asks which skill applies, why a skill did not fire, or asks to check what is available.
Also in 5 projects that use this
sublimotionSkillagent-runtime
Launch and manage detached agent runs on EKS via the agent-runner CLI. Use when the user says "launch an agent run", "agent runtime", "agent-runner", "run this spec on the cluster", "check run status", "agent run logs", or "stop a run". Do NOT use for writing the agent-runner code itself (edit the sibling ../agent-runner repo), Terraform of the foundation (use terraform-automation), or GPU serving deployments (use infra-deployer).
Also in 5 projects that use this
GoZippySkillrepo-scout
Also in 5 projects that use this
BenjaminGSkillharness-review
Turn one PR's review comments into harness fixes — classify each cause by the most solid place it can live (codebase, lint, rules, skill), then draft the fixes in a separate PR.
Also in 5 projects that use this
- +6 more from naman10parikh
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- meta-pytorch/OpenEnv★ 2.8ksame name
- huggingface/OpenEnv★ 2.8ksame name
- popup-studio-ai/bkit-claude-code★ 605same name
- ww-w-ai/bkit-claude-code★ 605same name
- atelier-fashion/adlc-toolkit★ 173same name
- naman10parikh/agentgrid★ 9same name
- sunitghub/canon-skills★ 9same name
- naman10parikh/wikimem★ 8same name
- dagonet/claude-code-toolkit★ 4same name
- SaketMunda/claude-org-template★ 3same name
17 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- address-commentsSkill
- demoSkill
- deploySkill
- documentSkill
- gather-contextSkill
- implementSkill
- investigateSkill
- observeSkill
- pr-follow-upSkill
- project-profileSkill
- pr-reviewSkill
- qa-planSkill
- qaSkill
- resolve-conflictsSkill
- specSkill
- standupSkill
- todoSkill
- triageSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 24 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 17
Follow ../../shared/policy.md.
- Distinctive: line 20
Never changes the tracker.
- Distinctive: line 28
Everything assigned fits: Never report that the sprint doesn't fit, never suggest cutting or moving tickets, and don't use the tickets' …
- Distinctive: line 33
Follow the saved plan. Don't re-read ticket descriptions or weigh tickets unless re-planning.
“Common” is measured: kept by at least 6 in 10 of the 24 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.
Files
Sprint
Follow ../../shared/policy.md. Run dev-skills:project-profile for the current repo to find the
tracker and board. Tracker queries: ../../shared/references/trackers.md.
The plan belongs to the board, not a repo: ~/.dev-skills/plans/<board-slug>/<sprint-slug>.md.
Never changes the tracker; ticket updates the user wants go on the confirmation list.
Config from ### sprint (profile ## Mine, then defaults.md): days_off (dates), holidays
(dates), workdays (default Mon-Fri).
Business days = workdays minus holidays and days_off. Work is only ever placed on business
days; weekends and days off never get rows. Dates use the user's local timezone.
Everything assigned fits. Never report that the sprint doesn't fit, never suggest cutting or moving tickets, and don't use the tickets' estimates or story points. The job is to distribute all remaining tickets across the remaining business days.
Existing plan (/sprint when a plan file for that sprint exists)
Follow the saved plan. Don't re-read ticket descriptions or weigh tickets unless re-planning.
- Show the plan's rows from today on, in the output format below.
- Brief change check, one tracker query for your tickets in that sprint (key, summary, status),
compared with the plan file:
- tickets added to or removed from the sprint;
- tickets that became done;
- status moves that change the order (To Do → In Progress).
- Nothing changed: say
No changes since <Updated date>.and stop. - Something changed: list each change on one line, then re-plan from today with the Plan steps
below, without asking (in
guided, show the new plan and wait for approval).
Plan (/sprint with no plan file yet, /sprint next, or re-plan approved)
- Tickets: yours in the current sprint (or the next one with
next), with summary, status, priority, board rank, links (blocks/is blocked by), and the sprint's start and end dates. - What's left (matters mid-sprint): get each ticket's real status (see Today, step 4).
- Done (tracker done/closed, or PR merged with nothing left): not planned again; listed under
Already done. - Partly done (PR open, in review, in QA): left out of the plan; the open PRs need no row.
- Past days are never re-planned. If a plan file for this sprint exists, keep its earlier rows as history and replace only the rows from today on.
- Done (tracker done/closed, or PR merged with nothing left): not planned again; listed under
- Relative weight: small / normal / big, judged from the description and a quick look at the code it touches (not from estimates). Used only to balance days.
- Days: remaining business days, from the first one (today if it is one, else the next; or the
sprint start for
next) to the sprint end. - Order: In Progress tickets first, then To Do tickets in the board's rank order. A recurring
ticket (on-call, support) goes on an
Every dayline instead of a row. - Distribute in that order so each day gets a similar share:
- Tickets ≈ days: one ticket per day.
- More tickets than days: some days take two or more; group small ones together, and keep a big one alone on its day.
- Fewer tickets than days: a big ticket may span two days; leave the last day(s) for review follow-ups and QA.
- Save the plan; in
guided, show it and wait for approval before saving.
Output format (chat and plan file)
One row per ticket, KEY: summary with the tracker's summary verbatim. A ticket sharing a day gets
its own row with the same day. A ticket spanning days gets one row with a day range.
# <board> — <sprint> (<start> → <end>)
| Day | Ticket |
|---|---|
| Mon 10/12 | PROJ-118: <summary> |
| Tue 10/13 | PROJ-120: <summary> |
| Tue 10/13 | PROJ-125: <summary> |
| Wed 10/14 – Thu 10/15 | PROJ-121: <summary> |
| Fri 10/16 | Review follow-ups and merges |
| Every day | PROJ-130: <summary> |
Risks: <one line, only if any>
Updated: <timestamp> (<reason>)In chat, skip the # heading and Updated line and add nothing else besides Risks.
Today (/sprint today)
- Load the current sprint's plan. None: offer
/sprintand stop. Withoutrefresh, if<sprint-slug>.today.mdnext to the plan was made today, show it, add/sprint today refresh to re-check, and stop. The day plan is built once a day; live PR and message status isdev-skills:todo's job. - Not a business day (weekend, holiday, day off): say
Nothing planned today (<weekday>)., then show the next business day's rows as a preview with their real status (step 4). Don't re-plan. - Business day: today's rows plus anything planned earlier that is not done.
- Real status per ticket: tracker status + branch exists (all repos in
related_reposand the current one) + PR state (open, changes requested, approved, merged) + CI state. Batch it: one tracker query for all the tickets, onegit branch -aand one PR list per repo (e.g.gh pr list --author @me --state all --json headRefName,state,reviewDecision,statusCheckRollup), then match by ticket key. Never one call per ticket. - Changes: tickets added to or removed from the sprint since planning.
- Behind? Compare done vs planned to date. If behind or the sprint changed, say so and re-plan
from today with the Plan steps, without asking (in
guided, show it and wait for approval); then build today's report from the new plan.
Save the report to <sprint-slug>.today.md, with a last line Made: <YYYY-MM-DD HH:MM>.
Today (Tue 10/13) — on track | behind by <n> ticket(s) | ahead
- PROJ-120: <summary> — changes requested → address comments (dev-skills:address-comments)
- PROJ-121: <summary> — not started → implement
Carried over: <ticket — why>
Sprint changes: <added/removed>Non-business day:
Nothing planned today (Sunday).
Next: Mon 10/12
- PROJ-120: <summary> — not started → implementDoes 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
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.

