跳到正文
cccskills
免费在 GitHub 公开

large-file-write-mkdir

Save large text files when write_file or shell_agent encounters payload size limits. Create the parent directory first, write the content with Python through run_shell, and verify the resulting file.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Reliable fallback technique for writing large file contents when write_file and shell_agent both fail with 'unknown error' due to payload size limits — uses run_shell with a Python heredoc to bypass tool constraints, with an explicit mkdir -p step to ensure the target directory exists before writing.

查看安装方法

适用场景

  • Saving large source files after write errors
  • Writing files into new nested directories
  • Saving long JSON or Markdown content

包含的文件(2)

  • SKILL.md4.7 KB
  • .skill_id48 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Large File Write Fallback (with Directory Pre-creation)

Problem

When writing large files (typically several KB or more), two common tools may fail with unknown error due to internal payload size limits:

  • write_file — has a maximum content size it can handle in a single call.
  • shell_agent — may also hit payload limits when the task description includes large inline content.

A second class of failure occurs when the target directory does not exist: Python's open() will raise FileNotFoundError if any intermediate directory is missing. Always pre-create the parent directory to prevent this.

Solution

Use run_shell with a mkdir -p prefix and a Python heredoc pattern. The mkdir -p ensures the target directory exists; the heredoc streams the file content through stdin directly into Python's open(), bypassing the payload constraints of the other tools.

Template

mkdir -p "<PARENT DIRECTORY OF TARGET PATH>" && python3 - << 'EOF'
content = """<FILE CONTENTS HERE>"""
with open("<TARGET PATH>", "w") as f:
    f.write(content)
EOF

Pass this as the command parameter to run_shell.

Tip: If the parent directory is not known in advance, use the shell dirname helper: mkdir -p "$(dirname '<TARGET PATH>')" && python3 - << 'EOF'

Step-by-Step Instructions

  1. Attempt the normal write using write_file first. If it succeeds, you are done.

  2. If write_file fails (especially with unknown error or a timeout on large content), do NOT retry with shell_agent using inline content — it will likely fail for the same reason.

  3. Use the run_shell heredoc fallback:

    • Pre-create the parent directory with mkdir -p <parent_dir>. This is a no-op when the directory already exists, so it is always safe to include. Skipping this step causes Python's open() to raise FileNotFoundError for any new or deeply-nested path.
    • Embed the full file content inside a Python triple-quoted string.
    • Specify the target path inside the open() call.
    • Pass the entire block (mkdir + heredoc) as the command to run_shell.
  4. Escape carefully inside the heredoc:

    • Backslashes that should be literal in the file must be doubled (\\).
    • Triple-quotes inside the content must be escaped (\"\"\").
    • The heredoc delimiter EOF must not appear on a line by itself inside the content (rename it to PYEOF or FILEEOF if needed).
  5. Verify the write by following up with a run_shell call such as:

    wc -l <TARGET PATH> && head -5 <TARGET PATH>
    

Full Example

Suppose you need to write a large TypeScript file to src/components/Dashboard.ts:

mkdir -p "src/components" && python3 - << 'PYEOF'
content = """import { foo } from './foo';

export interface DashboardData {
  title: string;
  items: string[];
}

export function createDashboard(data: DashboardData): string {
  return `<div>${data.title}</div>`;
}
"""
with open("src/components/Dashboard.ts", "w") as f:
    f.write(content)
PYEOF

Pass the above (without the surrounding code fence) as the command argument to run_shell.

When to Use This Pattern

SituationRecommended tool
Small file (< ~2 KB)write_file
Medium file, no errors yetwrite_file (try first)
Large file or write_file failedrun_shell + mkdir -p + Python heredoc
shell_agent also fails on large inline contentrun_shell + mkdir -p + Python heredoc
Target directory may not existAlways add mkdir -p <parent_dir> first

Notes

  • This pattern works for any text-based file (TypeScript, Python, JSON, YAML, Markdown, etc.).
  • For binary files, adapt the approach to use base64 decoding inside the Python script.
  • The heredoc delimiter (EOF, PYEOF, FILEEOF) can be any string not present as a standalone line in your content — choose accordingly.
  • This technique is also useful when content contains characters that would need heavy shell escaping in a plain echo or printf approach.
  • The mkdir -p command is idempotent: it succeeds whether or not the directory already exists, so it is always safe to include.
  • To derive the parent directory from a target path in shell: mkdir -p "$(dirname '<TARGET PATH>')" works as a generic alternative when the parent path is not already known.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.

中文简介正在准备中。当前显示英语简介。

  • Match audio parts with different durations
  • Extend drums and melodic parts using suitable methods
  • Check audio specifications before mixing
HKUDS/OpenSpace77572026年8月13日 更新

Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.

中文简介正在准备中。当前显示英语简介。

  • Align instrument tracks to a reference audio file
  • Choose how to extend tracks that are too short
  • Verify audio properties after generation and effects
HKUDS/OpenSpace77572026年8月13日 更新

Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.

中文简介正在准备中。当前显示英语简介。

  • Connect a dashboard to external APIs without exposing API keys
  • Create endpoints for stock quotes and news
  • Standardize API responses and error handling
HKUDS/OpenSpace77572026年8月13日 更新

Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.

中文简介正在准备中。当前显示英语简介。

  • Export a master track with separate audio parts
  • Apply filters and reverb to audio
  • Check duration and format across deliverables
HKUDS/OpenSpace77572026年8月13日 更新

Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.

中文简介正在准备中。当前显示英语简介。

  • Continue drafting after repeated web retrieval failures
  • Preserve task requirements during network errors
  • Mark information that could not be externally verified
HKUDS/OpenSpace77572026年8月13日 更新

When Python execution repeatedly fails in execute_code_sandbox, use a file-based alternative: save the script, run it through the shell, and capture results or errors. The guidance covers paths, imports, timeouts, structured output, and optional cleanup.

中文简介正在准备中。当前显示英语简介。

  • Retry Python work through the shell after repeated sandbox failures
  • Run longer tasks with an adjusted timeout
  • Execute Python work that needs multiple files or system utilities
HKUDS/OpenSpace77572026年8月13日 更新

查看 HKUDS 的全部技能

报告此技能的问题