Surge

Organization

Power-Agent

surge

Use this skill for transmission power-system studies — AC/DC power flow, DC-OPF / AC-OPF / SCOPF, N-1 / N-2 contingency analysis, PTDF / LODF / OTDF sensitivities, NERC and AC Available Transfer Capability (ATC), SCED economic dispatch, and SCUC unit commitment. Also use for building or editing a transmission network (add / remove / scale buses, lines, transformers, generators, loads, storage). Use whenever the user references an IEEE benchmark case (case9, case14, case30, case57, case118, case300, market30) or IEEE 14-/30-/57-/118-/300-bus network, or asks to load a MATPOWER .m, PSS/E RAW, XIIDM, or CIM/CGMES file and run a steady-state study. Trigger on phrases like "power flow", "run OPF", "contingency analysis", "PTDF", "ATC", "economic dispatch", "unit commitment", "build a network", or "scale load by X%" — even if the user does not mention Surge by name. Not for transient-stability dynamics (route to ANDES) or harmonic / unbalanced distribution feeders (route to OpenDSS).

Overview

Publisher	Power-Agent
Repository	`PowerSkills`
Skill name	`surge`
Stars	77
Forks	23
Bundled files	16
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
16 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by Power-Agent on GitHub. Read the source before you install it.

Installation

Install the Surge AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/Power-Agent/PowerSkills/tree/main/powerskills-tool/skills/surge
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/Power-Agent/PowerSkills.git /tmp/PowerSkills
mkdir -p .claude/skills
cp -r /tmp/PowerSkills/powerskills-tool/skills/surge .claude/skills/surge

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Surge in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Surge on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Surge is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Surge workflow

Start by loading a network with load_builtin_case, load_network, or create_empty_network. Solve the base case before any advanced study — contingency, sensitivity, and OPF results are meaningless on a non-convergent base.

Default tool ladder

load_builtin_case(name) (e.g. case118), load_network(file_path, format?), or create_empty_network(...).
get_network_info() for counts, totals, areas, zones, voltage levels. get_topology(...) / get_islands() / find_path(...) for connectivity reasoning.
run_ac_power_flow(...) for the base operating point. run_dc_power_flow(...) only when a linearized study is explicitly requested.
Sensitivities: compute_ptdf, compute_lodf, compute_otdf for screening and transfer analysis.
run_n1_branch_contingency / run_n1_generator_contingency / run_n2_branch_contingency once the base case solves.
run_dc_opf → run_ac_opf → run_scopf for optimization. Pass explicit lp_solver / nlp_solver only when the deployment requires it.
run_sced (single-period) and run_scuc (multi-period commitment). Call get_dispatch_request_schema() before constructing the request dict.
compute_nerc_atc / compute_ac_atc for transfer capability. Build source/sink bus lists from list_buses output.
export_tables(output_dir) to hand CSVs back to the user.

Network construction & editing

For synthetic cases, scenario edits (outage, dispatch change, load scaling), or mutations to a loaded case. Re-solve run_ac_power_flow after any material edit.

Build: create_empty_network, add_bus, add_generator, add_load, add_line, add_transformer, add_storage.
Edit: set_branch_rating, set_branch_in_service (outages), set_generator_limits, set_generator_in_service.
Scale: scale_loads(factor, area?), scale_generators(factor, area?).
Remove: remove_bus, remove_branch, remove_generator, remove_load.

Working rules

Do not read contingency or sensitivity results from a non-convergent base case.
Sensitivity tools default to format="summary". Use "sparse" or "full" only when CSR or dense output is actually needed.
Solver selection is a deployment question. Default to auto-detect ("default"); pass "highs" / "ipopt" for open-source runs, "gurobi" for large MIPs. See references/SOLVER_GUIDE.md.
Call get_dispatch_request_schema() before building a run_sced / run_scuc request dict.
Hand off RMS / transient-stability questions to ANDES, harmonic / unbalanced questions to OpenDSS.

Escalation triggers

Map observed violations to the mitigation skill that handles them. If multiple triggers fire, escalate voltage → thermal → contingency.

Observation	Escalate to
Any bus `vm_pu < 0.95` or `> 1.05`	`voltage-violation-mitigation`
Any branch loading > 100% of `rate_a_mva`	`thermal-overload-mitigation`
`run_n1_*` returns ≥ 1 binding contingency	`contingency-mitigation`
`get_islands()` returns > 1 island after a contingency	`contingency-mitigation`
SCED / SCUC infeasible, reserve shortage, or LMP volatility	`operations-planning-mitigation`
`run_ac_power_flow` fails to converge on the base case	`convergence-failure-mitigation`
The study is a new generator, storage, or large-load connection at a POI	`interconnection-impact-mitigation`

Report the specific numbers that triggered the escalation (bus + vm_pu, branch + loading %, contingency label). Do not say "violations exist" without values.

Local assets

scripts/network_analysis.py — inspection and base PF review.
scripts/sensitivity_analysis.py — PTDF, LODF drill-down.
scripts/contingency_analysis.py — N-1 / N-2 summaries.
scripts/contingency_ranking.py — N-1 → severity rank → CSV → mitigation-skill mapping. python contingency_ranking.py <case> <out_dir>.
scripts/opf_analysis.py — DC / AC / SCOPF with solver-selection examples.
scripts/dispatch_analysis.py — SCED / SCUC.
scripts/transfer_capability.py — NERC ATC and AC ATC path setup.
scripts/test_scripts.py — end-to-end smoke test on a built-in case.
references/API_REFERENCE.md — 44-tool catalog.
references/SOLVER_GUIDE.md — HiGHS / Gurobi / Ipopt selection.
references/EXAMPLES.md — multi-tool workflows.
references/DISPATCH_REQUEST_SCHEMA.json — JSON schema for run_sced / run_scuc request. Also served by get_dispatch_request_schema().

Report back

Case loaded (name or path) and key counts from get_network_info.
Base-case convergence. If not converged, stop and report the mismatch.
Main result of the requested study (violations, LMPs, ATC MW, top sensitivity entries).
Which mitigation skill is next, if any.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

evals/evals.json4 KB
evals/mcp_config.example.json1 KB
evals/run_eval_with_mcp.py11 KB
references/API_REFERENCE.md9 KB
references/DISPATCH_REQUEST_SCHEMA.json93 KB
references/EXAMPLES.md4 KB
references/SOLVER_GUIDE.md2 KB
requirements.txt1 KB
scripts/contingency_analysis.py5 KB
scripts/contingency_ranking.py6 KB
scripts/dispatch_analysis.py3 KB
scripts/network_analysis.py5 KB
scripts/opf_analysis.py5 KB
scripts/sensitivity_analysis.py5 KB
scripts/test_scripts.py3 KB
scripts/transfer_capability.py4 KB

Frequently asked questions

What does the Surge AI skill do?

Why use Surge on TypingMind?

Because you install it once and use it with any model. Surge is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Surge in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Power-Agent/PowerSkills/tree/main/powerskills-tool/skills/surge. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Surge?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Surge?

As many as you like. As long as a model supports skills, you can use Surge with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Surge AI skill free?

Yes. It is published on GitHub by Power-Agent under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Release Openclaw Plugin Testing

openclaw

OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

Solid

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

Auto Qa

Run OpenClaw-wide autonomous QA and live/stress campaigns across independent subsystem lanes, with verified fixes and a resumable evidence report.

Autoreview

Structured code review when explicitly requested, preferring OpenAI/Codex before Claude.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Surge workflow

Default tool ladder

Network construction & editing

Working rules

Escalation triggers

Local assets

Report back

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now