Coding standards, frameworks, refactoring, and code review (16.4K skills)
Diagnose Python script failures by showing error output and exit codes alongside the working directory and file listing. Use these clues to investigate missing files, missing modules, permission errors, or scripts that produce no output.
Continue library-dependent Python tasks when sandbox execution fails by switching to a shell script. Covers recognizing import errors, preserving script text, checking execution output, and troubleshooting package availability for tasks such as PDF generation or visualization.
Recover from repeated code execution tool failures by writing a script through the shell and running it with an absolute path. Check output files and investigate syntax, permissions, disk space, or execution errors when needed.
Use shell heredocs, which pass multiline text directly to a command, when write_file fails on complex code. Save TypeScript, JSX, JSON, or shell scripts with literal quotes and formatting, then verify the file and its contents.
Inspect website responses with curl, using browser-like request headers and checking file size, content, and format. Identify placeholder pages and choose a browser-based or direct API approach when the expected content is missing.
Investigate unclear errors in Python PDF generation by displaying output immediately and inspecting error details. Use the resulting traceback, a record of where execution failed, to identify missing dependencies, font problems, or invalid file paths.
Package project files into a ZIP archive and verify that the deliverable exists and is not empty before completing a task. It also defines a fallback for archiving available files when the agent approaches its iteration limit.
Recover from repeated sandbox execution failures by saving Python code to a script and running it through run_shell. Check output, error messages, and exit codes to confirm results or diagnose remaining execution problems.
Continue Python tasks after repeated sandbox failures by saving code as a script and running it through the shell, a command interface. The workflow covers execution checks, result retrieval, and optional cleanup.
Investigate Python failures in a sandbox, an isolated execution environment, by capturing partial logs, testing functions separately, and checking output files one at a time. Use the findings to identify failing steps and rebuild a working script.
Debug repeated execution failures by saving Python code to a script file and running it through run_shell. Keep the script available for inspection, review intermediate output and errors, and edit it for another run.
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.
Recover from failed code execution by simplifying code, switching to shell commands, or handing complex tasks to shell_agent. Explicit working directories and output checks help keep generated files in the expected location.
Continue Python tasks when the e2b sandbox, an isolated execution environment, is unavailable. Guides switching from execute_code_sandbox to run_shell, preparing dependencies, checking execution results, and saving intermediate data between calls.
Run Python code through a saved script and shell when repeated sandbox failures point to environment problems. Captures execution output and checks exit codes and expected files to verify whether the task completed.
Recover from failed file and directory operations by switching to run_shell, a shell command tool. Create nested folders, write files, and verify each result before continuing with tasks that depend on those files.
Run Python through a saved script when execute_code_sandbox or shell_agent repeatedly fails. The workflow writes code to a file, executes it through run_shell, and checks errors and expected outputs such as spreadsheets or documents.
Continue file reading and data processing when execute_code_sandbox or read_file fails. This skill runs multiline Python through run_shell, with examples for text, JSON, spreadsheets, PDF and Word documents, plus basic summaries and grouped calculations.
Translate user needs into concise stories that explain who benefits, what they want, and why. Add Gherkin acceptance criteria—preconditions, an action, and an expected result—to support development discussions and testable definitions of success.
Turn product management notes or workshop material into a structured skill, or update an existing one. Follow a workflow covering duplicate checks, drafting, validation, catalog updates, and optional ZIP packaging for upload.
Turn product management notes, frameworks, or rough ideas into a complete SKILL.md draft. Guided questions help choose the skill type, narrow its purpose, and organize instructions, examples, and common mistakes into the required structure.
Build, refactor, and troubleshoot ChatGPT apps with an MCP server, which exposes tools to the assistant, and an interactive widget. Use official documentation and examples to plan tools, scaffold code, configure security settings, and validate local operation.
Turn a selected screenshot, mockup, or generated image into a responsive website or web app. Recreate its layout and visual assets, implement core interactions, and compare the running result with the reference in a browser.
Guides development of apps for viewing USD, a 3D scene format. Selects browser streaming or local implementation references, covering rendering, camera controls, selection, interface layout, and validation while keeping users’ scene files unchanged.