agentleFS
CodePhobiiaCodePhobiia/claude-roblox-game-studio/.claude/skills/bug-report/SKILL.md

bug-report

Skill9 starsChanged 7 months agoMITView on GitHub

Structured bug report creation with repro steps, expected/actual behavior, and severity classification.

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-audio and 9 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

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    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 13 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 10 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 10 projects that use this

  • +3 more from CoralGame
  • +4 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 3

    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. Distinctive:

    Ask the user for:

    line 13
  2. Distinctive:

    Frequency: Always / sometimes / once?

    line 20
  3. Distinctive:

    Start from a known state (e.g., fresh login)

    line 25
  4. Very specific:

    Use .claude/docs/templates/bug-report-template.md as the base.

    line 37
  5. Very specific:

    Add to production/bugs/index.md if that exists

    line 83

“Common” is measured: kept by at least 6 in 10 of the 32 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

/bug-report — Bug Report Creation

Delegate to: qa-tester (with qa-lead for triage)

Steps

1. Gather Information

Ask the user for:

  • Short description: One sentence summary
  • What happened: What did you observe?
  • What should have happened: Expected behavior
  • When: Did this just start or has it been happening?
  • Where: Which system/feature is affected?
  • Device: Platform (mobile/PC/console), screen size, network
  • Frequency: Always / sometimes / once?
  • Impact: How many players affected? Data loss risk?

2. Reproduce (if possible)

Work with the user to find reliable repro steps:

  1. Start from a known state (e.g., fresh login)
  2. List each action taken
  3. Note the exact point where behavior diverges from expected

3. Classify Severity

  • S0 — Critical: Data loss, crashes, security exploits, can't play
  • S1 — Major: Feature broken for many users, major visual/UX issues
  • S2 — Normal: Feature works but with noticeable problems
  • S3 — Minor: Small glitches, edge cases, polish items
  • S4 — Cosmetic: Typos, minor style issues

4. Generate Bug Report

Use .claude/docs/templates/bug-report-template.md as the base.

# BUG: [Short descriptive title]

**ID**: BUG-YYYY-MM-DD-NNN
**Severity**: [S0-S4]
**Device**: [Platform, resolution, network]
**Build**: [Version or git commit]
**Reported**: YYYY-MM-DD
**Status**: Open

## Steps to Reproduce
1. [Step 1]
2. [Step 2]
3. [Step 3]

## Expected Behavior
[What should happen]

## Actual Behavior
[What actually happens]

## Evidence
- Screenshots: [paths or links]
- Video: [link if available]
- Console output: [paste relevant errors]
- Stack trace: [paste if available]

## Affected Systems
- [System 1]
- [System 2]

## Suspected Root Cause
[Any theories about where the bug lives]

## Workaround (if known)
[Anything the user can do to avoid it]

## Notes
[Anything else relevant]

5. Save and Triage

Present the report to the user. On approval:

  • Save to production/bugs/BUG-<date>-<NNN>.md
  • Add to production/bugs/index.md if that exists
  • For S0/S1: Immediately escalate to qa-lead + producer
  • Delegate investigation to the appropriate specialist based on affected system

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.