bug-reproduction-root-cause-hunter
- Repo stars 1
- Author updated Live
- Author repo claude-skills
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @00PrabalK00 · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: bug-reproduction-root-cause-hunter
description: Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hyp…
category: engineering
runtime: no special runtime
---
# bug-reproduction-root-cause-hunter output preview
## PART A: Task fit
- Use case: Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hypotheses, and propose the smallest safe fix plan. Use for vague "it broke" reports, flaky regressions, failing tests, or production issue investigations..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Overview / Core Workflow / Deliver” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hypotheses, and propose the smallest safe fix plan. Use for vague "it broke" reports, flaky regressions, failing tests, or production issue investigations.”.
- **02** When the source has headings, the agent prioritizes “Overview / Core Workflow / Deliver” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Overview / Core Workflow / Deliver”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: bug-reproduction-root-cause-hunter
description: Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hyp…
category: engineering
source: 00PrabalK00/claude-skills
---
# bug-reproduction-root-cause-hunter
## When to use
- Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hypotheses, and propose t…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Overview / Core Workflow / Deliver” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "bug-reproduction-root-cause-hunter" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Overview / Core Workflow / Deliver
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Bug Reproduction Root Cause Hunter
Overview
Turn loose bug reports into a repeatable debugging workflow with evidence at each step.
Core Workflow
- Normalize the report. Capture expected behavior, actual behavior, exact errors, inputs, and environment details.
- Reproduce the failure. Use existing tests, app commands, logs, or a minimal repro path before theorizing.
- Narrow the surface. Identify the smallest set of files, conditions, flags, data states, or requests needed to trigger the bug.
- Test hypotheses. Inspect recent diffs, surrounding code, and related tests to validate likely causes.
- Propose the fix path. Recommend the smallest safe change, the regression test to add, and any rollout concerns.
Deliver
- Provide exact repro steps when reproduction succeeds.
- State the most likely root cause with concrete evidence.
- If reproduction fails, document what was tried, what remains plausible, and the next best experiment.
- Keep the fix plan separate from the diagnosis.
Guardrails
- Do not claim certainty without evidence.
- Prefer recent changes and environment differences as early suspects, not automatic conclusions.
- Preserve any raw error output needed to debug further.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review