agentleFS
Sign inStart free
ShiningPlagueShiningPlague/shiningplague-studio/skills/bug-report/SKILL.md

bug-report

Skill0 starsChanged 4 months agoMITView on GitHub

Use when filing a bug found mid-session ('file a bug', 'log this bug', 'that's broken — track it'), when a routine finding needs manual promotion, or when verifying/closing an existing BUG-NNN after a fix ('/bug-report verify BUG-003', '/bug-report close BUG-003'). Not for triage/prioritisation — that's /bug-triage.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use playtest-report, soak-test and 1 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

    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 12 projects that use this

  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 9 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 9 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 0

    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:

    After a fix lands. Per verification-before-completion: run the actual repro / relevant headless check, cite output in the bug file under a …

    line 60
  2. Very specific:

    Only after a passing verify.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 31 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

🌱 ShiningPlague-authored. Replaces the original Donchitos pointer stub — this is the real implementation.

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.

Overview

Files, verifies, and closes formal bugs at production/qa/bugs/BUG-NNN-<slug>.md. One file per bug. The file format below is the contract: keep it identical whether a bug is filed by hand through this skill or emitted by a project-side auto-promotion script, so /bug-triage and /sprint-plan never have to care which path created it.

Mode 1 — File (default)

  1. Next ID: ls production/qa/bugs/BUG-*.md → max NNN + 1, zero-padded to 3.
  2. Severity (impact, not urgency): S1 crash/data-loss/blocks-all-testing · S2 feature broken, no workaround · S3 feature impaired, workaround exists · S4 cosmetic/polish.
  3. Write the file — production/qa/bugs/BUG-NNN-<kebab-slug>.md:
---
id: BUG-NNN
status: TRIAGE-PENDING
severity: S1|S2|S3|S4
priority: TRIAGE-PENDING
source: <designer-report | assistant-observed | skill/routine name>
flagged: YYYY-MM-DD
flagged_at: YYYY-MM-DD HH:MM
auto_promoted: false
---

# BUG-NNN — <One-line title>

## Finding

What is broken, where observed (scene/system/file), repro steps if known,
expected vs actual. Cite evidence (console output, screenshot path, registry
live_test_notes entry) — no evidence, say so explicitly.

## Report

Pointer to fuller context (spec, review doc, devlog date) or "inline — no separate report".

## Triage notes

_Empty — pending /bug-triage run._
  1. Close the loop: mention the new BUG-NNN in the session's devlog/dev_diary entry at /update time. If S1/S2, ALSO surface it to the designer immediately — don't let it sit silent until triage.

Mode 2 — Verify (/bug-report verify BUG-NNN)

After a fix lands. Per verification-before-completion: run the actual repro / relevant headless check, cite output in the bug file under a new ## Verification YYYY-MM-DD section. Evidence before assertions. If verification fails, say so in the file and leave status untouched.

Mode 3 — Close (/bug-report close BUG-NNN)

Only after a passing verify. Set status: CLOSED, add closed: YYYY-MM-DD to frontmatter, one-line resolution under ## Resolution. Never close without a Verification section — that's the failure mode this mode exists to block.

Common mistakes

  • Filing bugs in next_session_priorities or chat context instead of a BUG file — they evaporate. If it's a real defect, it gets a file.
  • Setting priority at filing time — priority is /bug-triage's job (severity is yours).
  • Closing on "should be fixed now" — verify mode first, always.

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