agentleFS
Sign inStart free
evgenii-studitskikhevgenii-studitskikh/Claude-Code-SaaS-Studio/.claude/skills/scope-check/SKILL.md

scope-check

Skill1 starsChanged 5 months agoMITView on GitHub

Compare current or proposed work against the PRD's non-goals and scope boundaries. Flag scope creep early, recommend cut or keep, and get a user decision before work continues.

26 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use team-polish, team-audio 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.
  • CoralGameSkill

    team-polish

    Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

    Also in 13 projects that use this

  • 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

  • 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

  • +6 more from CoralGame
  • +2 more from lilangMax

The file

Create a free account to mount
Files
SKILL.md

Act as a scope guardian: read the PRD's goals, non-goals, and success metrics, then evaluate whether a proposed piece of work belongs in the current iteration. Non-autonomous: always surfaces findings and options before any decision is recorded.

Phases

  1. Load the PRD — read docs/specs/prd.md. Extract the stated goals, in-scope user stories, and explicit non-goals. If the PRD does not exist, stop and direct the user to /write-prd first.
  2. Understand the proposal — if no argument was given, ask the user to describe the feature or change under review in one or two sentences. Ask clarifying questions if the proposal is ambiguous.
  3. Evaluate alignment — compare the proposal against each PRD goal and non-goal. Score it: IN_SCOPE (clearly serves a stated goal), BORDERLINE (related but not explicitly scoped), or OUT_OF_SCOPE (matches a non-goal or adds unplanned complexity).
  4. Present options — for BORDERLINE or OUT_OF_SCOPE items, present three choices: (A) Cut it from this iteration and log it as a future idea, (B) Narrow it to the smallest version that fits scope, (C) Formally expand scope by updating the PRD. Explain the cost/risk of each option.
  5. Record the decision — once the user chooses, note the decision and, if the PRD is to be updated (option C), draft the minimal change to docs/specs/prd.md and await approval before writing. Once findings are resolved, return to the skill that invoked this check (e.g., /build-feature) or continue the current phase.

Output

Text scope verdict + decision record. Updates docs/specs/prd.md only if the user chooses to expand scope and approves the draft change.

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.

Check your setup, free