一键导入
reproduce-bug
Step-by-step procedure to reproduce a bug. Use this FIRST before trying to fix anything. Produces a minimal script that demonstrates the failure.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Step-by-step procedure to reproduce a bug. Use this FIRST before trying to fix anything. Produces a minimal script that demonstrates the failure.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Structured procedure to locate the root cause of a confirmed bug. Uses keyword search → focused reading → call-graph tracing. Outputs a specific file + line + hypothesis.
AgentM SDK development guide — manifest-as-agent-unit philosophy, SDK programmatic invocation, dynamic workflow orchestration, atom contract, Operations abstraction, event system, service communication, CLI conventions, scenario authoring, logging, structured output, and config resolution. Use whenever writing, editing, or reviewing code under src/agentm/ (atoms, core, gateway), contrib/scenarios/ (manifests), or contrib/extensions/ (workspace-member atoms). Also trigger when creating new atoms, modifying MANIFEST declarations, registering tools or events, touching FileOperations / BashOperations / ResourceWriter, writing CLI subcommands, configuring model profiles, spawning child sessions, building multi-agent orchestrators, writing workflow scripts, or when a code change looks like it might bypass the SDK's existing abstractions. If you catch yourself about to write raw os.stat / open() / subprocess.run in an atom, importing openai/anthropic directly instead of going through the provider layer, or shelling
Guide for adding new benchmarks to the agentm-eval framework and running experiments through the unified `agentm eval` CLI. Covers the adapter interface, experiment lifecycle, result schema, ClickHouse linking, and output conventions. Use whenever creating a new eval adapter, modifying an existing benchmark integration, writing code under contrib/evals/src/agentm_eval/, discussing experiment management, or when the user mentions "add a benchmark", "new eval", "接入评估", "新benchmark", "实验管理", "eval adapter". Also trigger when reviewing eval-related code or debugging experiment output structure.
How to write workflow scripts that orchestrate multiple agents in AgentM. Covers agent(), parallel(), pipeline(), phase(), return values, atom_config data passing, and the journal-based resume / invalidation / partial re-run mechanism (workflow_lineage, workflow_invalidate). Trigger when writing a workflow script, choosing an orchestration pattern, recovering from a wrong node result, or when the user says 编排 / workflow / 多 agent / 并行 / 扇出 / 调度 / 写个 workflow / 失效 / 部分重跑 / 重算. Also trigger when you catch yourself building prompts inside a workflow script — pass data via atom_config instead and let the agent build its own prompt.
Analyze agentm session traces using `agentm trace` atomic commands. Use when inspecting trajectories, token economics, tool calls, or aggregating stats across a trace tree (parent + child sessions). Compose atomic commands via shell pipes — never parse OTLP JSONL directly.
Develop, test, and validate Terminal User Interface applications using tmux as your "headless browser" for terminals. Use when asked to run a TUI application, capture its output, verify its behavior, or debug rendering issues. This skill provides a structured workflow for TUI development, including session management, interaction patterns, state capture, and regression detection.
| name | reproduce-bug |
| description | Step-by-step procedure to reproduce a bug. Use this FIRST before trying to fix anything. Produces a minimal script that demonstrates the failure. |
You are reproducing a bug. Follow these steps exactly in order. Do not skip steps or read additional files beyond what each step specifies.
ls package.json 2>/dev/null && cat package.json | grep -E "vitest|jest|mocha|tap" | head -5
ls *.toml 2>/dev/null | head -3
Note which test runner is available (vitest, jest, etc.).
find . -name "*.test.*" -o -name "*.spec.*" | grep -i "<keyword from bug description>" | head -10
If you find relevant test files, read them to understand how the codebase tests similar functionality.
Create a file called repro.ts (or repro.js / repro.py depending on
the project language) that:
Keep it under 50 lines. Use the write tool to create the file.
npx tsx repro.ts 2>&1
Or the appropriate runner for the language. Report:
State clearly:
If not reproduced, adjust the repro script (maybe the setup is wrong) and try ONE more time. If still not reproduced after 2 attempts, report that.