Browse executable prompts and workflows by task, content type, and runtime. Each card shows inputs, verification status, and the original source.
Runtimes vary by resource and may include an API, CLI, agent framework, or browser coding environment. Check each card for details.
Editor picks
Editor picks
2
UnverifiedGitHub / MiniMax-AI/MiniMax-M2.7
MiniMax M2.7 Official Default Prompt and XML Tool-Calling Template
Starting from MiniMax M2.7’s public default identity prompt, define an XML turn for a code-check tool; parse arguments before execution and verify that the result answers the original request.
Content typeConfiguration
InputsPublic default system prompt, Tool name and parameter schema, Code sample, XML parse/rejection rules
StatusMiniMax M2.7 service or compatible runner; public tool schema, code sample, and XML parser.
UnverifiedMiniMax official news / MiniMax M2.7: Early Echoes of Self-Evolution
MiniMax M2.7 Self-Feedback, Memory, and Agent Self-Optimization Workflow
Split a small fix into plan, implementation, test, and reflection turns; write only verifiable failure causes to memory and compare whether the next run removes the same test failure.
Content typeWorkflow
InputsIssue or reproduction steps, Repository snapshot, Test command, Memory write rule, Before/after comparison metric
StatusRunnable repository, test command, versioned memory file, and isolated branch; never store credentials in memory.
MiniMax M2.7 Official Default Prompt and XML Tool-Calling Template
Starting from MiniMax M2.7’s public default identity prompt, define an XML turn for a code-check tool; parse arguments before execution and verify that the result answers the original request.
Content typeConfiguration
InputsPublic default system prompt, Tool name and parameter schema, Code sample, XML parse/rejection rules
StatusMiniMax M2.7 service or compatible runner; public tool schema, code sample, and XML parser.
UnverifiedMiniMax official news / MiniMax M2.7: Early Echoes of Self-Evolution
MiniMax M2.7 Self-Feedback, Memory, and Agent Self-Optimization Workflow
Split a small fix into plan, implementation, test, and reflection turns; write only verifiable failure causes to memory and compare whether the next run removes the same test failure.
Content typeWorkflow
InputsIssue or reproduction steps, Repository snapshot, Test command, Memory write rule, Before/after comparison metric
StatusRunnable repository, test command, versioned memory file, and isolated branch; never store credentials in memory.
