bug-report
Write a clear, reproducible bug report that gets fixed fast
Install / Use
npx skills add mohitagw15856/pm-claude-skills --skill bug-reportInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of bug-report
bug-report scores 75/100 on our quality scale, 3172nd of 4,355 Development & Engineering skills we index.
Its SKILL.md is 3.4 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.
With 1,396 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 7 days ago, so bug-report is actively maintained.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands.
Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
bug-report compared with similar skills
All 4 of these similar skills score higher than bug-report; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| bug-report (this skill)by mohitagw15856 | 75 | 1.4k | 7d ago | SKILL.md |
| ai-job-searchby MadsLorentzen | 100 | 44.7k | 1d ago | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 41.7k | 1d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 8d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 8d ago | SKILL.md |
Frequently asked questions
- How do I install bug-report?
- Run
npx skills add mohitagw15856/pm-claude-skills --skill bug-report. The install tabs above show the steps for each supported agent. - Which AI agents does bug-report work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is bug-report safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is bug-report still maintained?
- The repository was last updated 7 days ago, so bug-report is actively maintained.
Skill content
View source on GitHubname: bug-report description: "Write a clear, reproducible bug report that gets fixed fast. Use when asked to write a bug report, file a defect, report an issue, or turn 'it's broken' into an actionable ticket. Produces a structured report — a precise title, steps to reproduce, expected vs. actual, environment, severity/priority, and evidence — so a developer can reproduce and fix it without a back-and-forth."
Bug Report Skill
A bug report is only useful if someone else can reproduce it. The best ones are precise: an exact title, numbered steps, what you expected vs. what happened, and the environment it happened in. This skill turns a vague "it's broken" into a ticket a developer can act on immediately — no clarifying round-trips.
Working from a brief
Given "the export button doesn't work", write the full report anyway — infer the likely repro steps, expected behaviour, and environment, marking inferences (confirm). Keep facts (what was observed) separate from guesses (likely cause). Never invent logs/errors; flag them to attach.
Required Inputs
Ask for these only if they aren't already provided (else infer and label):
- What's wrong — what you did, what happened, and what you expected instead.
- Steps to reproduce — the exact sequence (and whether it's consistent or intermittent).
- Environment — device, OS, browser/app version, account/role, and any relevant data state.
- Evidence — screenshots, a screen recording, console/network errors, logs, request IDs.
Output Format
Bug Report
- Title — a precise one-liner: what's broken + where + the key condition ("Export to CSV fails for >1,000 rows on Safari").
- Severity / Priority — impact (blocker/critical/major/minor) and how widespread, kept distinct from urgency.
- Environment — device/OS/browser+version, app/build version, account/role, region/data as relevant.
- Steps to reproduce — numbered, exact, starting from a known state; note frequency (always / ~X% / once).
- Expected result — what should happen.
- Actual result — what actually happens (the observable failure — error text, wrong value, crash).
- Evidence — screenshots/recording, console & network errors, logs, request/correlation IDs (listed/attached).
- Notes (optional) — a workaround, when it started/regressed, and any suspected cause clearly marked as a hypothesis, not fact.
Quality Checks
- [ ] The title is specific enough to identify the bug at a glance
- [ ] Steps reproduce from a known starting state and note frequency (consistent vs. intermittent)
- [ ] Expected vs. actual are both explicit and the actual is the observable failure
- [ ] Environment (versions, role, data) is captured — the usual reason a bug "can't be reproduced"
- [ ] Severity (impact) is separated from priority (urgency)
- [ ] Observed facts are kept separate from suspected cause; evidence is referenced
Anti-Patterns
- [ ] Do not write "doesn't work" — state the exact action, expectation, and observed failure
- [ ] Do not omit environment/version — it's the top reason bugs aren't reproducible
- [ ] Do not merge expected and actual into one sentence — keep them distinct
- [ ] Do not present a guessed cause as fact — label hypotheses
- [ ] Do not bundle several bugs in one report — one defect per ticket
Based On
Defect-reporting practice — reproducibility-first reports with precise titles, expected/actual separation, environment capture, and impact/urgency distinction.
Related Skills
ai-job-search
44.7kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
41.7kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
