agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/scope-check/SKILL.md

scope-check

Skill9 starsChanged 7 months agoMITView on GitHub

Evaluate current scope vs. resources. Identify cut candidates and perform risk assessment. Use when feeling overwhelmed or running late on milestones.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use team-audio, playtest-report and 6 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

    team-audio

    Orchestrate audio team: audio-director + sound-designer + technical-artist + gameplay-programmer for full audio pipeline from direction to implementation.

    Also in 11 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 10 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 8 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 8 projects that use this

  • +2 more from CoralGame
  • +2 more from lilangMax

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 21 edited versions we read keep these.

  • 2

    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
  1. Distinctive:

    Option C: No cuts → ship late by N days

    line 52
  2. Very specific:

    Update design/gdd/systems-index.md with new priority

    line 78
  3. Distinctive:

    Update risk register if cuts introduce new risks

    line 79

“Common” is measured: kept by at least 6 in 10 of the 21 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

/scope-check — Scope vs. Resources Analysis

Delegate to: producer

When to Use

  • Milestone at risk of slipping
  • Feature list seems too long for the available time
  • Team/solo dev feeling overwhelmed
  • Regular sprint planning activity (midway check-in)

Steps

1. Inventory Current Scope

List all planned work:

  • From production/sprints/current-sprint-plan.md
  • From design/gdd/systems-index.md (planned but not started)
  • From production/bugs/index.md (known issues)

2. Assess Capacity

  • Remaining sprint time
  • Actual velocity (what's been shipped so far)
  • Known blockers or distractions
  • Dependencies on external work (assets, approvals)

3. Categorize Everything as MoSCoW

  • Must Have: Non-negotiable; milestone fails without this
  • Should Have: Important but skippable in a crunch
  • Could Have: Nice to have; add if time permits
  • Won't Have (this time): Explicitly defer

4. Identify Cut Candidates

Scoring each feature on:

  • Impact: How much does this improve the player experience? (1-5)
  • Cost: How much work remains? (hours)
  • Risk: How uncertain is the estimate? (Low/Med/High)
  • Dependencies: Does cutting this free up other work?

High cost + low impact = cut first Low cost + high impact = keep Low cost + low impact = easy wins, defer unless trivial High cost + high impact = must deliver but watch carefully

5. Propose Cuts

Present 2-3 options:

  • Option A: Cut X, Y → ships on time with 85% of vision
  • Option B: Cut Y, Z → ships on time with 75% of vision but easier to test
  • Option C: No cuts → ship late by N days

6. Document the Decision

Write to production/decision-log.md:

## YYYY-MM-DD — Scope Cut for [Sprint/Milestone]

**Context**: [why scope was reviewed]

**Options Presented**:
1. [Option A]
2. [Option B]
3. [Option C]

**Decision**: [What was chosen]

**Cut Features**:
- [Feature] — deferred to [future sprint / post-launch / killed]

**Reasoning**: [1-3 sentences on why this was the right call]

**Rollback Plan**: [How to bring cut features back if needed]

7. Update Plans

  • Mark cut features in sprint plan as "deferred"
  • Update design/gdd/systems-index.md with new priority
  • Update risk register if cuts introduce new risks

Output

# Scope Check: [Sprint/Milestone]

## Current Status
- Committed work: X items
- Estimated remaining: Y hours
- Available capacity: Z hours
- **Over by**: (Y - Z) hours — NN% over budget

## Recommendation
**Cut**: [list of features]
**Keep**: [list of features]
**Reasoning**: [why this cut set]

## Risks Introduced
- [Risk 1 from cutting X]
- [Risk 2 from cutting Y]

## Next Steps
1. Confirm cuts with user
2. Update sprint plan
3. Communicate to any affected stakeholders

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.