delegate-to-minimax
Offload bulk text tasks like summarization, conversion, and drafts to the MiniMax API to save your main model's rate limits.
Install
mkdir -p .claude/skills/delegate-to-minimax && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15984" && unzip -o skill.zip -d .claude/skills/delegate-to-minimax && rm skill.zipInstalls to .claude/skills/delegate-to-minimax
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Route bulk text processing tasks to MiniMax MCP tools to conserve GLM rate limits. Use this skill whenever the user asks for summarization, format conversion, test data generation, email drafts, commit messages, keyword extraction, data cleaning, boilerplate code generation, or document drafting. Also trigger when processing large volumes of files or content. Do NOT use for translation (MiniMax mixes Chinese into Japanese), code changes to existing codebases, architecture design, debugging, code review, or security decisions — those stay with GLM.Key capabilities
- →Summarize file or URL content
- →Convert data formats like JSON, YAML, CSV, XML, TOML
- →Generate test data or mock data
- →Draft business emails
- →Extract keywords or key points from text
- →Generate boilerplate or template code
How it works
The skill identifies the task type and routes it to a specific MiniMax MCP tool for execution, then reports the results.
Inputs & outputs
When to use delegate-to-minimax
- →Summarizing large documents
- →Converting data formats like JSON to YAML
- →Generating mock test data
- →Drafting business emails
- →Extracting keywords from text
About this skill
MiniMax Task Delegation
Route text-heavy, non-critical tasks to MiniMax MCP tools to conserve GLM (ZAI API) rate limits. MiniMax is free and abundant — use it aggressively for bulk work.
Routing Table
Delegate to MiniMax (use specific MCP tool)
| Task | MCP Tool |
|---|---|
| File/URL content summarization | minimax_summarize_file or minimax_ask |
| Format conversion (JSON↔YAML↔CSV↔XML↔TOML) | minimax_convert_format |
| Test data / mock data generation | minimax_generate_test_data |
| Business email drafting | minimax_write_email |
| Commit message generation | glm_git_commit_message (GLM, but lightweight) |
| CHANGELOG generation | glm_generate_changelog (GLM, but lightweight) |
| Keyword / key point extraction | minimax_extract_keywords |
| Bulk file processing (2+ files) | minimax_batch_process |
| Data cleaning / normalization | minimax_clean_data |
| Boilerplate / template code generation | minimax_generate_code |
| Document drafting (README, CLAUDE.md drafts) | minimax_write_document or glm_write_document |
| Code generation (standalone, no existing deps) | minimax_generate_code |
| Regex generation / explanation | glm_generate_regex |
| Cron expression generation | minimax_cron_helper |
| Diff summary (git diff) | minimax_diff_summary |
| Schema generation from sample data | minimax_generate_schema |
| Env/config validation | minimax_env_check |
| Error log grouping | minimax_error_group |
| Log analysis | minimax_log_analysis |
Keep on GLM (do NOT delegate)
| Task | Reason |
|---|---|
| Translation (any language pair) | MiniMax mixes Chinese into output |
| Code changes / refactoring | Depends on existing codebase context |
| Architecture design / proposals | Requires project knowledge |
| Debugging / error analysis | Requires accurate reasoning |
| Code review / audit | Quality gate must be GLM-level |
| Security decisions | Risk assessment needs precision |
Workflow
- Identify the task type from the routing table above
- Select the most specific MiniMax MCP tool — prefer specialized tools over
minimax_ask - Execute the task via the selected MCP tool
- Review — if the output is code, architectural decisions, or affects existing codebase, have GLM review before applying
- Report results to the user
Anti-patterns
- Do not use MiniMax for tasks that require understanding existing project structure or dependencies
- Do not use MiniMax for translation — always route to GLM
- If MiniMax output needs correction, fix it via GLM rather than re-prompting MiniMax (costs more GLM to fix than to do it right the first time)
When not to use it
- →For translation tasks, as MiniMax mixes Chinese into output
- →For code changes or refactoring that depend on existing codebase context
- →For architecture design or proposals requiring project knowledge
Limitations
- →MiniMax mixes Chinese into translation output
- →Not suitable for tasks requiring understanding of existing project structure
- →Not suitable for code review or security decisions
How it compares
This workflow offloads text-heavy, non-critical tasks to MiniMax MCP tools, preserving GLM capacity for complex tasks like code changes and debugging.
Compared to similar skills
delegate-to-minimax side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| delegate-to-minimax (this skill) | 0 | 1mo | No flags | Beginner |
| using-superpowers | 95 | 3mo | No flags | Beginner |
| ultrawork | 11 | 2mo | No flags | Advanced |
| clawhub | 25 | 3mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
using-superpowers
obra
Use when starting any conversation - establishes mandatory workflows for finding and using skills, including using Skill tool before announcing usage, following brainstorming before coding, and creating TodoWrite todos for checklists
ultrawork
Yeachan-Heo
Parallel execution engine for high-throughput task completion
clawhub
openclaw
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.
skill-installer
openai
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
continuous-learning
affaan-m
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
memory-keeper-proactive-context-maintenance
b4CU-R4U
Automatically detect and maintain memory freshness by monitoring context staleness, significant code changes, task completions, and phase transitions. Proactively suggests and executes memory sync operations with user confirmation. Use when the user says "sync memory", "update context", or when the Skill detects that context is stale (>2 hours), significant changes have occurred (new commits), tasks completed, or major milestones reached. Replaces passive "context is stale" warnings with active maintenance.