Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add yxy050208/multisim-mcp --skill multisim-create-experimentgit clone --depth 1 https://github.com/yxy050208/multisim-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yxy050208/multisim-mcp/multisim-create-experiment)<a href="https://agentmods.dev/skills/yxy050208/multisim-mcp/multisim-create-experiment"><img src="https://agentmods.dev/badge/skills/yxy050208/multisim-mcp/multisim-create-experiment/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yxy050208/multisim-mcp/multisim-create-experiment"><img src="https://agentmods.dev/badge/skills/yxy050208/multisim-mcp/multisim-create-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01258 |
| Opus 5 | $0.00023 | $0.00629 |
| Sonnet 5 | $0.00009 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
multisim-create-experiment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
创建 Multisim 电路实验
本 skill 使用 Multisim MCP 工具。下文写原始工具名;DeepSeek Harness 默认会将其
显示为 mcp__multisim__<工具名>,如果配置使用了不同 serverName,请采用实际前缀。
- 收集电路功能、输入输出、供电、频率、容差、分析类型、输出目录和验收指标。 对会改变设计结论的缺失条件先向用户确认。
- 调用
runtime_status。完整工作流未就绪时,报告具体缺口,不要反复尝试 COM。 - 在生成网表前调用
plan_design_options。展示 2--4 个取舍不同的技术方案,说明 默认推荐、假设、风险和实现路径;规划结果是只读的,不会生成文件或启动仿真。 等用户明确选择plan_id和option_id后,调用select_design_option锁定摘要。 - 调用
prepare_design_specification,展示并补齐电气参数、模块、分析计划和验证门槛。 只有ready_for_netlist_draft=true且用户审阅规格后,才能进入下一步;不要把参数完整 表述为拓扑、额定值或仿真已经通过。 - 用户明确确认当前规格摘要后调用
prepare_netlist_draft,先展示逻辑模块、网络、待选 器件与派生约束。该结果不是 SPICE;不得把ready_for_component_resolution解释为 已可成图或仿真。 - 调用
resolve_component_requirements展示候选器件族、额定值计算依据和模型来源状态。 用户提交具体型号、额定值和模型摘要后,调用approve_component_resolution绑定人工 审阅。只有审批凭证的ready_for_executable_netlist=true时,才可调用compile_executable_netlist。当前编译器只支持signal-passive的明确器件族组合;其他 方案应报告支持缺口,不得自行拼接引脚。编译结果仍需向用户展示 SPICE、计算值、假设和 门禁,并停在approve_executable_netlist;没有新的明确审批前不得成图或仿真。外部模型 只允许来自服务端受限模型根目录,并必须重新哈希。 - 得到另行批准的完整网表和分析计划后,成图阶段将编译预览、网表审批凭证和其中的原样
spice_netlist传给create_schematic_from_netlist;该工具会重新校验绑定关系,只写入 获批原理图而不启动仿真。随后调用approve_simulation_plan,把同一网表审批绑定到ExperimentSpec的安全命令、测量信号和验收限制;再将三份凭证传给run_verified_circuit_experiment,由入口在成图和仿真前重新校验。有明确验收指标时优先调用run_verified_circuit_experiment;长任务可将同三份凭证传给submit_circuit_experiment,凭证会随作业保存并在隔离 worker 中再次校验;普通实验仍可调用run_circuit_experiment,长任务则查询提交作业的状态。 如果用户从工作台下载了multisim-approved-experiment-handoff.json,可以先在可信终端 执行multisim-mcp execute-handoff --handoff <file> --root <project> --json做一致性校验; 只有用户明确确认后才加--confirm,命令会严格先成图、再仿真,且默认不覆盖已有产物。 时间较长时可使用--submit --confirm:先成图,再将仿真计划排入 durable worker,并把返回 的 job 句柄交给工作台队列观察。 - 成功后调用
get_experiment_summary和list_experiment_artifacts。只有需要更多 文本证据时才分页调用read_experiment_artifact,不要读取二进制内容。 受控审批运行还应通过inspect-project或工作台回读目录 manifest,确认approval_provenance与当前 simulation-plan/netlist/compiled/spec 摘要一致; 旧实验或直接执行结果若显示未记录归属,不得冒充本次审批结果。 - 核对理论值、仿真测量、容差和验证结论。任何缺少数据支持的指标标记为“未验证”。
- 仅在用户要求导出时调用
export_experiment_artifact;导出目录必须已由服务端批准。
最终答复应列出电路假设、网表/分析、关键测量、PASS/FAIL/未验证结论和产物清单。 不要把“最接近要求”写成“通过”,也不要声称自动生成的设计已可直接生产。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago Changed · +28 lines a1bc47574645
- 10d ago First seen · 31 lines · 45 tokens per session scan A 5620c3d06b44
multisim-create-experiment is a skill published in the GitHub repository yxy050208/multisim-mcp (9 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,258 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sovereign-economics-engine
Unified business model evaluator, client filter, pricing engine, and distribution architect. Absorbs 31 business + 8 marketing + 13 content + 2 acquisition protocols.
agentic-code-orchestrator
Unified codebase manipulation, AI deployment, data analysis, and academic delivery engine. Absorbs 6 coding protocols + data-analysis + academic-delivery + spec-driven-dev.
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).