409 skills · sorted by relevance
Recover Python tasks when execute_code_sandbox fails with errors or timeouts. Install required packages, run the code through run_shell, and inspect messages and generated files to check the result.
Resume Python tasks after execute_code_sandbox errors or timeouts by saving the attempted code as a script and running it through run_shell. The workflow includes dependency checks, execution timeouts, and verification of generated files such as Excel reports.
Run Python through shell commands when sandbox execution fails because required packages are unavailable. The skill explains short commands, multiline scripts, package checks, and output verification, with examples for creating Excel and Word files.
Run Python through run_shell when execute_code_sandbox fails unexpectedly. The skill explains how to pass multiline code using a heredoc, a shell syntax for inline text, then check standard output and error messages.
Recover failed Python tasks by saving the code as a script and running it through the shell. Provides steps to inspect errors and confirm generated files for spreadsheet creation, data processing, and calculations.
Run multiline Python code by saving it to a script file before executing it through the shell. The workflow covers working directories, timeouts, error checks, and optional cleanup to make execution easier to debug.
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.
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.
Supports authorized security exercises that test data transfer outside a network. Organizes channel choices, compression, encryption, splitting, and receipt verification, alongside the monitoring signals defenders can use to identify different transfer methods.
Organize red team exercises that simulate adversaries to assess an organization's detection and response. Covers engagement rules, infrastructure, operational controls, evidence handling, and reports that help security teams review gaps and prioritize improvements.
Build isolated code execution environments on Cloudflare Workers for AI-generated code, scripts, and build pipelines. Covers running commands, managing files, preserving interpreter state, exposing service previews, and cleaning up sandbox resources.
Design and review how a system is divided into modules, cohesive parts with clear responsibilities. Evaluate data ownership, communication rules, dependencies, and failure handling, and decide when to split or merge parts without assuming a particular technology.
Handle Jupiter verification requests for Solana tokens by checking eligibility, preparing and executing the payment transaction, and submitting verification or token information updates according to the permissions returned by the public API.
Start and monitor an Ouroboros development loop that revises project concepts and acceptance criteria, the conditions for judging completion. Run and evaluate successive generations, focus revisions on failed criteria, inspect progress, or rewind to an earlier generation.
Execute an existing Ouroboros Seed, a specification containing a goal and acceptance criteria, as a background job. The workflow checks each criterion, normally queues formal evaluation, and follows a bounded improvement loop if evaluation rejects the result.
Turn specifications into a detailed implementation plan before coding. Break work into small tasks with exact file paths, code, test commands, and interfaces so another developer or agent can follow the plan.
Helps a QwenPaw Worker choose between direct work, short parallel checks, and temporary agents with custom roles. It guides dependent task execution, shared files, progress updates, result merging, and removal of temporary agents after the work ends.
Record completed steps, decisions, issues, and next actions in dated progress logs. Maintain recent task history and sync updates to shared storage so an agent can recover context and resume work after a session reset.
Carry out assigned work as a Worker agent, from acknowledging the task to submitting a structured result. Keep deliverables in the task directory, record progress, request decisions when blocked, and publish results to the Task room.
Manage an assigned Worker task from acceptance through delivery using taskflow. Keep work and optional progress notes in the task directory, submit structured results with deliverable paths, and report completion or blockers to the coordinator.
Use ccwf to validate workflow JSON files, preview their steps in a browser, and produce Mermaid flowcharts. Export workflows as skill files for supported agents, or generate the files and launch Claude Code to proceed with execution.
Structure open-source intelligence research, meaning investigation using publicly available information, for authorized external assessments. Map organizational assets, record evidence and confidence levels, prioritize exposures, and prepare reports that explain technical findings and business risks.
Build a software quality assurance process with structured test cases, execution tracking, bug severity levels, and quality metrics. Includes templates for progress reports and team handoffs, plus prompts for agent-driven test execution.
Turn specifications into detailed implementation plans before coding. Break work into testable tasks with exact file paths, code, test commands, expected results, and interfaces so another developer or agent can carry out the work.