一键在 Manus 中运行任何 Skill

install-opencode-plugin

星标7

分支3

更新时间2026年6月20日 23:39

Compatibility shim for OpenCode installs. Use when a developer asks to install, update, enable, reinstall, remove, or verify Understudy in OpenCode - "install Understudy in OpenCode", "add the OpenCode skills", "make OpenCode see the skills". Route to install-agent-adapter with platform opencode.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

understudylabs

understudylabs/understudy-agent-tools

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

相关职业SOC

基于 SOC 职业分类

软件开发工程师计算机与数学类职业·SOC 15-1252

SKILL.md

readonly

同仓库更多 Skills

同仓库

compare-model-sweep

understudylabs/understudy-agent-tools

Use when a developer wants to compare candidate models — any mix of local, gateway, or frontier — on the same eval and see quality, latency, cost, and reliability side by side. "Which model should I use", "sweep these models on my benchmark", "compare Gemma vs the frontier on my eval". To stand up and serve a local candidate first, use run-local-model-lab.

2026-07-247

optimize-agentic-workload

understudylabs/understudy-agent-tools

Use when a developer's agent — a multi-turn tool-calling loop — should get cheaper, faster, or better. "My agent is too slow", "this workflow costs too much", "test a cheaper model in my tool-calling loop", "A/B the policy model". Covers read-only search loops and state-mutating API workflows alike.

2026-07-247

operate-benchmark-lab

understudylabs/understudy-agent-tools

Use when a coding agent must operate the full benchmark lifecycle over local benchmark dirs — "build a benchmark from my traces and run models on it", "review and calibrate the eval", "queue a prompt experiment", "is an executor running", "read the rigor report". Covers traces → build-benchmark → review/feedback → calibration floors → candidate and prompt-override runs → rigor/CI reading → app-replay regression, via the benchmarks MCP server or CLI verbs, plus the run-executor daemon lifecycle.

2026-07-237

design-simulated-environment

understudylabs/understudy-agent-tools

Use to build a simulated, seeded environment (AutomationBench / verifiers style) so any model can run a captured agentic workload end-to-end and be scored on final state — "simulate this workload's tools", "build a validator for these traces", "let a small model attempt the whole task", "score recall/precision against gold", or any handoff from understand-workload toward whole-case model comparison.

2026-07-237

manage-local-models

understudylabs/understudy-agent-tools

Use to acquire, cache, organize, and explain local open-weight models — "download a model", "what models do I have", "where did the weights go", "free up model disk", "which Gemma/Nemotron should I pull", "how do open models work". Covers where weights come from and live, formats/quantization, gated weights and HF tokens, disk budgeting, start-small-and-cache, and the local→cloud graduation path. American families (Gemma 4, Nemotron 3). To score a local model on a workload, use run-local-model-lab.

2026-07-227

product-knowledge

understudylabs/understudy-agent-tools

Use when a user asks what Understudy is, how Understudy Desktop works, how local model serving, Fusion sidekick, evals, model candidate results, rollout labs, Product Knowledge, or Understudy product capabilities should be explained to developers, customers, or agents.

2026-07-227

name	install-opencode-plugin
description	Compatibility shim for OpenCode installs. Use when a developer asks to install, update, enable, reinstall, remove, or verify Understudy in OpenCode - "install Understudy in OpenCode", "add the OpenCode skills", "make OpenCode see the skills". Route to install-agent-adapter with platform opencode.
metadata	{"understudy":{"mode":"automatic","safety":"local-first","cli_required":false}}

Install the Understudy OpenCode skills

This skill is a compatibility shim. The consolidated setup surface is install-agent-adapter.

The legacy skill name says "plugin" for compatibility with older prompts, but the OpenCode implementation is not a JS/TS OpenCode plugin. It is a native skills/commands adapter: symlink SKILL.md directories into OpenCode's global skills directory and link the /understudy-onboard markdown command.

Procedure

Load install-agent-adapter and run it with platform opencode.

Use its reference.md for the current native skill symlink install:

mkdir -p "$HOME/.config/opencode/skills" "$HOME/.config/opencode/commands"

The reference links each skills/<name>/ directory into OpenCode's global skill directory and links .opencode/commands/understudy-onboard.md.

Activation:

Restart OpenCode or open a new TUI session.
/understudy-onboard

Safety Gates

Local-first and free: installing the OpenCode adapter only links local skills. It must not authenticate, upload data, inspect secret values, download model weights, start hosted jobs, or make provider calls.

Do not overwrite existing non-Understudy OpenCode skills or commands.
Do not copy private traces, keys, or .understudy/ state into OpenCode config.
Use symlinks back to this repo's shared skills/ tree.
If OpenCode asks before reading symlinked external resources, let the user make that permission decision; do not copy skill content to bypass it.

Resolve CLI

No Understudy CLI command is required. Use shell to create symlinks after confirming the repo contains skills/understudy/SKILL.md.

Output Standard

End with: that this routed through install-agent-adapter; whether OpenCode skills were linked/refreshed/skipped due to conflicts; the restart/new-session step; /understudy-onboard; and the uninstall command.