bug-report
Skill0 starsChanged 17 days agoMITView on GitHub
Turn a rough description of a problem, error log, or screenshot into a professional, validated bug report ready to paste into Jira/Azure DevOps. Use when the user found a bug, wants to report a defect, or needs help writing a bug ticket.
35 other projects use a version of this.
Adopted by
Most recently taken up by
- Sn4kyGit/qa-agent-blueprinttheir own version, first seen Nov 16, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Nov 9, 2026
- alexpalexpinne/qa-toolkittheir own version, first seen Nov 8, 2026
- craigcossairt/trellistheir own version, first seen Nov 6, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
Used with
Projects with it also use team-level, setup-engine 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.
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 13 projects that use this
CoralGameSkillsetup-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 14 projects that use this
lilangMaxSkillasset-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 11 projects that use this
lilangMaxSkillcreate-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 11 projects that use this
- +4 more from CoralGame
- +4 more from lilangMax
Other versions35 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 35
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- pipecat-ai/gradient-bang★ 420same name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- oasm-platform/open-asm★ 277same name
- striderZA/OpenCodeGameStudios★ 124same name
- tranhieutt/software_development_department★ 71same name
- cenconq25/claude-code-app-studio★ 40same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- composio-community/support-skills★ 18same name
- dawn840705/codex-code-studios★ 17same name
25 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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- api-testSkill
- automateSkill
- exploratorySkill
- mobile-testSkill
- test-casesSkill
- test-dataSkill
- test-planSkill
- test-reportSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 33 edited versions we read keep these.
0
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 13
If reproduction steps or environment are missing, ask ONE short question covering all gaps.
“Common” is measured: kept by at least 6 in 10 of the 33 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
Bug Report Writer
The user is a tester who found a bug. They may describe it roughly, in broken English, or just paste an error/screenshot. Produce a complete, professional bug report. Follow this workflow EXACTLY.
Workflow (mandatory)
- Extract facts from what the user gave (steps, environment, exact error text, screenshots — Read any image they attached).
- If reproduction steps or environment are missing, ask ONE short question covering all gaps. If the user seems in a hurry, use placeholders like
<build version>and mark them clearly. - Write the report to a file
bug-reports/<short-slug>.mdusing EXACTLY this template (keep every**Section:**header — the validator checks them):
**Title:** [Component] What fails + under which condition
**Environment:** OS / browser or device / app version / build / environment (QA, staging...)
**Severity:** Blocker | Critical | Major | Minor | Trivial
**Priority:** P1 | P2 | P3
**Preconditions:** state needed before the steps
**Steps to Reproduce:**
1. ...
2. ...
**Actual Result:** what actually happens — include the EXACT error text
**Expected Result:** what should happen, with requirement reference if known
**Reproducibility:** Always / Intermittent (x out of y tries)
**Attachments/Evidence:** screenshots, logs, video to attach
**Notes / Possible cause:** optional observationsSeverity guide: Blocker = testing/usage cannot continue; Critical = major function broken, no workaround; Major = major function broken but workaround exists; Minor = small function/UI defect; Trivial = cosmetic.
- Validate your report (MANDATORY):
python .claude/skills/bug-report/scripts/validate_bug_report.py bug-reports/<short-slug>.mdFix every ERROR and re-run until it prints OK. Try to fix WARN lines too. Never show the user an unvalidated report.
- Show the user the final report plus one line justifying the Severity/Priority you chose.
Rules: title must be specific and searchable ("Login button does nothing after session timeout on Chrome 126" — never "Login broken"). Facts only, no blame, no guesses stated as fact.
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
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.

