Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/MiniMax-AI/MiniMax-Code-Plugins.Loading the repository README…
Showing 40 of 152 collected skills.
Inspect and visualize MiniMax Code session trajectories from the local runtime's read-only SQLite projection. Use when the user asks what happened in a session, why a task was slow or expensive, how many turns or tool calls a run took, which tools failed, how…
Coordinate a life-science research request that spans design, public databases, omics, statistics, writing, figures, reproducibility, or independent review. Use for multi-stage research work; do not use for a single narrow lookup.
Independently review a life-science manuscript, analysis, figure package, or repository for claim support, citation validity, numeric traceability, figure-code-data consistency, reproducibility, and privacy. Use as a final gate, not as author self-approval.
Audit whether biological materials, sampling, controls, replication, and measurements can answer a proposed question before experiments or analysis. Use for study planning and Go/No-Go decisions.
Detect and selectively use local life-science desktop or structural tools, including safe PyMOL rendering and explicit file opening in SnapGene, Cytoscape, or Fiji. Use when a user asks to work with these installed applications; never install tools silently…
Draft or restructure life-science Introduction and Discussion sections from supplied claims, results, figures, and verified literature. Use for argument construction; do not invent evidence, citations, or causal strength.
Plan, audit, or interpret public or user-authorized sequencing and omics workflows, including bulk RNA-seq, single-cell, amplicon, metagenomic, variant, and metabolomic analyses. Use only after design and metadata fit are checked.
Query public biological databases for genes, proteins, domains, structures, literature, networks, motifs, or general Solanaceae metadata through the bundled allowlisted MCP. Use for evidence lookup; never route private or pepper-specific data through it.
Design or review statistical, mixed-model, Bayesian, or machine-learning analyses for life-science data. Use when the main risk is estimand, dependence, model choice, diagnostics, leakage, or uncertainty.
Turn a life-science analysis into a cleanly rerunnable workflow with protected raw data, centralized parameters, fixed seeds, environment capture, provenance, and verified outputs. Use for publication or handoff-quality analysis.
Create and audit common RNA-seq result figures locally, including volcano, PCA, heatmap, expression boxplot, and enrichment dotplot, with PNG/PDF delivery and inline conversation preview. Use for RNA result plotting from user-selected tables; do not use…
Create, revise, or audit publication-grade life-science figures with source-data traceability, export QA, and a PNG preview shown directly in the agent conversation. Use for manuscript figures, not dashboards or decorative infographics.
Decide whether a life-science computation should run locally, on a controlled HPC over SSH, or on an external cloud GPU based on data sensitivity, scale, cost, and reproducibility. Use before moving data or launching remote work.
Plan and coordinate complex tasks as editable JavaScript workflows with multiple MCode agents. Create a pending-review draft, automatically open its topology in the MCode built-in browser, let the user edit and start it, then track parallel research, code…
Use this skill when the user asks for a new pink-octopus office-worker GIF meme, a Smooth Squishmallow-style worker octopus sticker, a 4-character Chinese caption on a 720x720 looping GIF, or wants to add a scene to an existing meme library. Drives a 4-stage…
Push the user's terminal out of focus to a Windows desktop Dynamic Island pill so the user can watch your work without switching back to mcode. On mcode 0.2.4+ with the `io.minimax.mcode` Hooks extension enabled (forward-compatible with MiniMax-Code-Plugins PR
Observer example for the mcode 0.4.0+ plugin format. Activates when a Plugin author needs a reference layout for inline Hooks under .claude-plugin/plugin.json.
Observer example for the mcode 0.4.0+ plugin format. Activates when a Plugin author needs a reference layout for inline Hooks under .claude-plugin/plugin.json.
Delegate a coding task from MiniMax Code to a locally installed coding CLI (Claude Code, Codex, Kimi Code, ZCode, or DSH). Use this Skill whenever the user asks to offload implementation to another coding agent, cross-check work with a second agent,…
Create, read, edit, or review Microsoft Word .docx documents. Use this Skill whenever the task involves a .docx file - generating reports, letters, or structured documents from scratch; extracting or reorganizing content; applying consistent formatting…
Create, extract, transform, or analyze PDF documents. Use this Skill whenever a .pdf file is the input or output - generating reports, one-pagers, posters or structured documents as real selectable-text PDFs; extracting text, tables or images from existing…
Create, read, edit, or analyze PowerPoint .pptx presentations. Use this Skill whenever the task involves slides or a deck - building a presentation from an outline or content file; editing text, tables, or charts in an existing deck; extracting slide content…
Read, edit, create, or fix spreadsheet files - .xlsx, .xlsm, .xltx, .csv, .tsv. Use this Skill whenever a spreadsheet is the primary input or output: opening and inspecting workbooks, editing cells or adding sheets, writing real formulas instead of pasted…
Before saying "done", derive requirements, find authoritative evidence, verify each is ✅. USE WHEN: about to say "done" / "complete" / "ship it" / "I finished" / "做完了" on non-trivial task, about to mark `todowrite` step done, about to update goal to…
Compress a long-running multi-step task into a structured snapshot before continuing. USE WHEN: `todowrite` > 5 items, after ~20 tool calls, context getting full, agent has lost track of goal, user said "compact" / "summarize" / "refocus" / "压缩" / "总结" /…
Hand off a sub-task to a sub-agent with a tight, complete brief in the `prompt` — not the full conversation history. Apply the 4-part message envelope (Task name / Sender / Task / Payload + return path). USE WHEN: about to call `task()` to hand off a…
Classify error into 4 buckets (transient / deterministic / stale / unknown) and pick one of 5 actions (retry / switch / fallback / refresh-then-retry / ask-user / skip). USE WHEN: tool returns non-success, sub-agent `status: closed-failed`, exception escapes,…
Decide how much parent context to include in a sub-agent's `prompt` before spawning it. Pick "all / N turns / brief only" explicitly, not by accident. USE WHEN: about to call `task()` to hand off work, designing a multi-agent flow, sub-agent failed and…
Maintain explicit north-star goal for the whole thread that survives compactions and detects drift. USE WHEN: non-trivial task stated, user redirected mid-task ("actually do X instead" / "wait scrap that" / "现在改成"), before `context-pressure-compact`, about to…
Track running token usage against goal's `token_budget`, surface at 50/80/100% thresholds, stop at 100%. USE WHEN: `goal-persistence` active AND user provided `token_budget`, user said "do X within Y tokens" / "用 Y token 完成" / "不要超预算" / "stayed within budget"…
Design a cross-session long-term memory system that extracts, consolidates, and cites durable knowledge from conversation rollouts. USE WHEN: building any system that needs to persist insights across sessions, designing "what should the next agent remember"…
Classify sub-task complexity (cheap / medium / main) and decide whether to spawn a sub-agent at all. On MiniMax Code 0.2.4 the `task` tool does not expose per-call model selection, so the 3-tier rubric here is a thinking framework for session-level model…
Decompose a task into 2+ truly independent sub-tasks and dispatch them concurrently via separate `task()` calls. Pick whether to fan out explicitly, not by accident. USE WHEN: the user task is clearly decomposable into 2+ independent sub-tasks (independent…
Before touching files on a non-trivial task, emit a structured plan and surface to the user for early course-correction. USE WHEN: non-trivial task, multi-step task, ambiguous requirement, would take > 3 tool calls, user has not approved an approach yet, user…
Design, validate, and ship a marketplace Plugin (or Skill bundle) with proper manifest format, multi-ecosystem compatibility, version pinning, manifest fallback, install idempotency, and three-layer startup sync. USE WHEN: writing a new Plugin manifest,…
Execute explicit retry policy: max 3, base 2s, max 30s, full jitter, 60s total budget, respects `Retry-After`. USE WHEN: `error-recovery-strategy` classified error as `transient` and chose `retry`, HTTP 429 with `Retry-After` header, network…
Switch to critic mode after finishing a chunk, produce PASS / FIX / REDO verdict. USE WHEN: sub-task boundary reached, user said "review" / "double-check" / "is this right" / "spot the bug" / "看一下" / "review 一下", before reporting "done" on anything user will…
Design a session-level fork / revert / recover / suspend mechanism over a paginated history with lineage tracking, immutable segments, global lock, ModelContext reconstruction, and bounded replay. USE WHEN: designing session persistence, building a "fork this…
At session end, write a structured handoff file so next session can pick up in 30 seconds. USE WHEN: user says "今天先到这" / "done for today" / "see you tomorrow" / "we'll continue later" / "下次再继续" / "end session" / "收尾", context about to compact, long task in…
Design a Skill (or Plugin) that an LLM agent can reliably discover, select, and invoke based on its description, with explicit selection syntax, name-collision handling, and three-layer matching. USE WHEN: authoring a new skill for a Plugin, designing skill…
Repository README source: README.md
Read the source README