agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/sprint-plan/SKILL.md

sprint-plan

Skill0 starsChanged 4 months agoMITView on GitHub

Use when planning a new sprint, reviewing sprint progress, or when the designer says 'plan the next sprint', 'what should we work on next', or 'sprint status'. Creates or updates sprint plans in production/sprints/. ShiningPlague-adopted: full implementation with modes (new/status/update), capacity check (40h/sprint solo dev), producer PR-SPRINT gate, sprint-status.yaml integration.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use balance-check, playtest-report and 3 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.
  • CoralGameSkill

    balance-check

    Analyzes game balance data files, formulas, and configuration to identify outliers, broken progressions, degenerate strategies, and economy imbalances. Use after modifying any balance-related data or design.

    Also in 5 projects that use this

  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 4 projects that use this

  • +3 more from CoralGame

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 34 edited versions we read keep these.

  • 4

    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. Very specific:

    new: Create a new sprint plan.

    line 32
  2. Very specific:

    update: Update existing sprint with new status, create production/sprint-status.yaml.

    line 34
  3. Distinctive:

    Workflow note: if the project uses the specs/plans workflow rather than epics/stories, sprint plans can reference either.

    line 50
  4. Distinctive:

    If UNREALISTIC: descope — remove lowest-priority items until producer approves.

    line 115
  5. Distinctive:

    Read the latest sprint file.

    line 121
  6. Distinctive:

    Update task statuses in the sprint file.

    line 136

“Common” is measured: kept by at least 6 in 10 of the 34 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 Plan — Sprint Creation and Tracking

🌱 ShiningPlague-adopted. Originally Donchitos (barebones stub); battle-tested on a shipped Godot project. Upstream was a pointer-only file; this version is the full implementation — sprint creation, status report, update mode, producer gate, capacity check.

Creates new sprint plans from the story/spec backlog, tracks progress, and manages sprint lifecycle. Dispatches producer agent for feasibility review.

If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.

Modes

new: Create a new sprint plan. status: Quick 30-line snapshot of current sprint progress. update: Update existing sprint with new status, create production/sprint-status.yaml. No argument: detect current sprint state and offer appropriate action.


Phase 1: Assess Current State

Read silently:

  1. production/stage.txt — project phase
  2. Glob production/sprints/sprint-*.md — existing sprint plans
  3. data/_schemas/system_registry.json → next_session_priorities — designer's priorities
  4. data/_schemas/dev_diary.json → latest entry → next — immediate next actions
  5. Glob production/epics/**/*.md — stories (if epic/story workflow adopted)
  6. Glob docs/specs/*.md — active specs (specs/plans workflow)
  7. Glob docs/plans/*.md — active plans

Workflow note: if the project uses the specs/plans workflow rather than epics/stories, sprint plans can reference either. When the epic/story workflow is adopted, this skill reads from both.


Phase 2: Create Sprint Plan (mode: new)

2a. Gather Candidate Work

From sources above, build a candidate list:

  • Stories with Status: Ready (from production/epics/)
  • Active specs not yet implemented (from docs/specs/)
  • next_session_priorities from registry
  • Bugs from production/qa/bugs/ (if any)

2b. Prioritize

Order by:

  1. Blocking dependencies (must-do-first)
  2. Designer priority (next_session_priorities[0] is highest)
  3. MVP vs Alpha vs Full Vision
  4. Estimated effort (smallest first for momentum)

2c. Capacity Check

Solo dev capacity per sprint (1-2 weeks):

  • ~40 hours of Claude-assisted work
  • ~8-12 implementable items (depending on complexity)
  • Reserve 20% for bugs and polish

2d. Draft Sprint Plan

# Sprint [N] — [Theme/Focus]

> **Start**: [date]
> **End**: [target date]
> **Goal**: [one sentence — what can we demo at the end?]

## Stories / Tasks

| # | Task | Source | Estimate | Status |
|---|------|--------|----------|--------|
| 1 | [task name] | [spec/story/priority ref] | [S/M/L] | Not Started |
| 2 | ... | | | |

## Sprint Risks
- [risk 1]
- [risk 2]

## Definition of Done
- All tasks complete or explicitly deferred with reason
- Consistency check passes
- Designer smoke test passes

Write to production/sprints/sprint-[N].md.


Phase 3: Producer Review (if review-mode = full)

Spawn producer via Agent with gate PR-SPRINT from .claude/docs/director-gates.md:

  • Pass: proposed story list, capacity, milestone constraints
  • Verdict: REALISTIC / CONCERNS / UNREALISTIC

If UNREALISTIC: descope — remove lowest-priority items until producer approves.


Phase 4: Sprint Status (mode: status)

Read the latest sprint file. Count tasks by status. Report:

Sprint [N] — [Theme]
Progress: [X]/[Y] tasks complete
- [completed task names]
- [in-progress task names]
- [blocked tasks + reason]
Days remaining: [N]

Phase 5: Sprint Update (mode: update)

Update task statuses in the sprint file. If all tasks complete, close the sprint:

  1. Mark sprint as Complete in the sprint file
  2. Create/update production/sprint-status.yaml
  3. Propose: "Sprint [N] complete. Run /retrospective or plan next sprint with /sprint-plan new?"

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.