← Back to Skills Marketplace
Issue Reproducer
by
vx：17605205782
· GitHub ↗
· v1.0.0
· MIT-0
168
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install issue-reproducer
Description
把 bug 描述整理成可复现步骤、环境、预期与实际结果和最小复现条件。；use for bug, reproduction, qa workflows；do not use for 伪造日志, 忽略用户给出的环境差异.
README (SKILL.md)
问题复现整理器
你是什么
你是“问题复现整理器”这个独立 Skill，负责：把 bug 描述整理成可复现步骤、环境、预期与实际结果和最小复现条件。
Routing
适合使用的情况
- 把这个 bug 描述整理成可复现单
- 生成最小复现条件
- 输入通常包含：报错描述、环境信息、复现线索
- 优先产出：问题摘要、环境、补充采样建议
不适合使用的情况
- 不要伪造日志
- 不要忽略用户给出的环境差异
- 如果用户想直接执行外部系统写入、发送、删除、发布、变更配置，先明确边界，再只给审阅版内容或 dry-run 方案。
工作规则
- 先把用户提供的信息重组成任务书，再输出结构化结果。
- 缺信息时，优先显式列出“待确认项”，而不是直接编造。
- 默认先给“可审阅草案”，再给“可执行清单”。
- 遇到高风险、隐私、权限或合规问题，必须加上边界说明。
- 如运行环境允许 shell / exec，可使用：
python3 "{baseDir}/scripts/run.py" --input \x3C输入文件> --output \x3C输出文件>
- 如当前环境不能执行脚本，仍要基于
{baseDir}/resources/template.md与{baseDir}/resources/spec.json的结构直接产出文本。
标准输出结构
请尽量按以下结构组织结果：
- 问题摘要
- 环境
- 复现步骤
- 预期结果
- 实际结果
- 补充采样建议
本地资源
- 规范文件：
{baseDir}/resources/spec.json - 输出模板：
{baseDir}/resources/template.md - 示例输入输出：
{baseDir}/examples/ - 冒烟测试：
{baseDir}/tests/smoke-test.md
安全边界
- 会强调缺失信息，不自动判断根因。
- 默认只读、可审计、可回滚。
- 不执行高风险命令，不隐藏依赖，不伪造事实或结果。
Usage Guidance
This skill appears to do what it says: produce structured reproduction reports and perform optional local audits. Before installing or running it, review the included scripts/run.py (already present) and: 1) run it in a safe directory (avoid pointing it at /, home, or directories with secrets), 2) do not pass sensitive files or credentials as input, 3) if you plan to let an agent invoke the skill autonomously, restrict the allowed input paths or review outputs first (the script can read arbitrary files but does not contact the network), and 4) verify the runtime (python3) and run smoke tests locally. If you need stronger assurance, inspect the remainder of run.py (the provided file was truncated in the listing) or run it in a sandboxed environment.
Capability Analysis
Type: OpenClaw Skill
Name: issue-reproducer
Version: 1.0.0
The 'issue-reproducer' skill bundle is a documentation utility designed to structure bug reports and perform basic file audits. The primary script (scripts/run.py) processes local text, CSV, and directory structures to generate Markdown reports based on a provided specification (resources/spec.json). Notably, the script includes a 'pattern_audit' mode that acts as a basic security scanner, searching for hardcoded secrets (which it masks) and dangerous shell commands (e.g., curl|bash) without executing them. The bundle lacks network access, obfuscation, or any indicators of malicious intent.
Capability Assessment
Purpose & Capability
Name/description (issue reproduction / structured brief) align with the included files: a template, spec.json, examples, and a Python script that builds structured reports, audits directories or CSVs, and scans for risky patterns. The single required binary (python3) is proportionate.
Instruction Scope
SKILL.md limits behavior (emphasizes read-only, no fabrication, list missing info) and explicitly suggests running the local script when allowed. The script legitimately reads files/directories (markdown, code, CSV, etc.) to build reports and to search for patterns; this is within scope for an audit/reporting skill. Note: because the script can be pointed at arbitrary paths, it can read local files (including potentially sensitive files) — the SKILL.md and README discourage sending secrets and recommend local-only operation.
Install Mechanism
No install spec; instruction-only skill with a local Python script. No network downloads or package installs are required. This is low risk and consistent with the stated behavior.
Credentials
No environment variables, no credentials, no config paths required. The tool only needs python3 and local file access, which is appropriate for its functionality.
Persistence & Privilege
always is false; the skill does not request permanent/system-wide privileges or modify other skills. It runs locally and does not persist elevated access.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install issue-reproducer - After installation, invoke the skill by name or use
/issue-reproducer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of issue-reproducer skill.
- Organizes bug descriptions into reproducible steps, environment, expected and actual results, and minimum reproduction criteria.
- Emphasizes explicit listing of missing information when details are insufficient.
- Provides structured, reviewable drafts and executable checklists for issue reproduction.
- Highlights safety boundaries: read-only, auditable, no fabrication of logs or results, and preserves environment details.
- Local resources and templates included to standardize outputs.
Metadata
Frequently Asked Questions
What is Issue Reproducer?
把 bug 描述整理成可复现步骤、环境、预期与实际结果和最小复现条件。；use for bug, reproduction, qa workflows；do not use for 伪造日志, 忽略用户给出的环境差异. It is an AI Agent Skill for Claude Code / OpenClaw, with 168 downloads so far.
How do I install Issue Reproducer?
Run "/install issue-reproducer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Issue Reproducer free?
Yes, Issue Reproducer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Issue Reproducer support?
Issue Reproducer is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Issue Reproducer?
It is built and maintained by vx：17605205782 (@52yuanchangxing); the current version is v1.0.0.
More Skills