When a user casually mentions something broken during testing or says "file an issue," this skill turns the conversation into a properly structured GitHub issue written in your project's own vocabulary. It asks one or two clarifying questions, explores the codebase in parallel to learn domain terms, checks for duplicates, then files directly without making you review a draft. The clever part is the anti-staleness rule: no file paths, no line numbers, no function names. Just behavior described in the language your team already uses, so the issue still makes sense after a refactor. It knows when to file one issue versus breaking a report into multiple blocked children.

skills.sh installs
162
GitHub stars
2.9K
last updated
Jun 8, 2026

Install

$ npx -y skills add rohitg00/pro-workflow --skill bug-capture --agent claude-code

Installs into .claude/skills of the current project.

Files

bug-capture

Turn a conversation into an issue that still reads correctly after a major refactor.

Flow

1. Listen, then clarify minimally

Let the user describe the problem in their own words. Ask at most two short clarifying questions, drawn from:

  • Expected behavior vs. actual behavior.
  • Concrete reproduction steps if not already implied.
  • Frequency: deterministic, intermittent, or one-off.

If the description already answers these, skip straight to filing. Over- interviewing is a tax the reporter pays for your uncertainty.

2. Explore in parallel

While the user is answering, start a background exploration of the relevant area. The goal is not to propose a fix. The goal is to absorb the project's own vocabulary — the nouns and verbs the codebase uses for this feature — so the issue reads like it was written by a maintainer.

If the repo has a glossary file (common names: GLOSSARY.md, UBIQUITOUS_LANGUAGE.md, docs/domain.md), read it first.

3. Check for duplicates before filing

Sponsors

Details

Repository
github.com/rohitg00/pro-workflow
Categories
Testing & QA, Git & Pull Requests, Debugging, Automation & Workflows
First seen
Jun 11, 2026

More from rohitg00/pro-workflow

All 35
1qodex-ai avatarbrowser-automation-frameworkqodex-ai/ai-agent-skillsAutomate browser interactions and web testing. Provides scriptable browser control for web scraping, testing, and automation.160skills.sh installs
2rysweet avatarmodel-evaluation-benchmarkrysweet/amplihackAutomated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluati160skills.sh installs
3aws-samples avatarcode-interpreteraws-samples/sample-strands-agent-with-agentcoreTest and prototype code in a sandboxed environment. Use for debugging, verifying logic, or installing packages.159skills.sh installs
4awslabs avatarmodel-evaluationawslabs/agent-pluginsGenerates python code that evaluates SageMaker models. Supports two evaluation types: LLM-as-Judge and Custom Scorer. Use when the user says "evaluate my model"140skills.sh installs
5sundial-org avataragent-browsersundial-org/awesome-openclaw-skillsA fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured comma129skills.sh installs
6cherryhq avatarskill-creatorcherryhq/cherry-studioCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an e0skills.sh installs