SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill unit-commitment-operating-rulesgit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/unit-commitment-operating-rules)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/unit-commitment-operating-rules"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/unit-commitment-operating-rules/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/benchflow-ai/skillsbench/unit-commitment-operating-rules"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/unit-commitment-operating-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.02027 |
| Opus 5 | $0.00033 | $0.01014 |
| Sonnet 5 | $0.00013 | $0.00405 |
| Haiku 4.5 | $0.00007 | $0.00203 |
Grade A, and why
unit-commitment-operating-rules 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- unit-commitment-operating-rules — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unit Commitment Operating Rules
Use this skill when a task asks for a day-ahead or multi-period unit commitment schedule with generators, load, reserves, operating constraints, and cost tradeoffs.
This is a reusable UC operating guide. It gives formulation and validation patterns, not a complete task-specific mathematical model.
UC In One Paragraph
Unit commitment decides which generators are online over time, when they start or stop, how much they produce, and how much reserve they can physically provide. It is harder than hourly economic dispatch because startup/shutdown decisions, ramping, minimum up/down time, reserve deliverability, initial conditions, and cost curves couple one period to the next.
Keep These Concepts Separate
For each thermal unit g and period t:
u[g, t] # commitment/on status, binary
start[g, t] # startup transition, binary
stop[g, t] # shutdown transition, binary
p[g, t] # production variable: know whether actual MW or above-minimum MW
r[g, t] # scheduled reserve
Reports often require actual MW output. Many UC models internally use output above minimum:
actual_output = pmin[g] * u[g, t] + p_above_min[g, t]
p_above_min = actual_output - pmin[g] * u[g, t]
Do not mix these conventions in ramping, reserve, cost, or reporting.
Core Feasibility Checks
Before reporting a schedule, independently verify:
- every resource appears exactly once and all time-series have length
T; - commitment, startup, and shutdown are binary;
- offline thermal units have zero production and zero reserve;
- online thermal units respect min/max output;
- must-run units are online when required;
- startup/shutdown indicators match commitment transitions;
- demand balance holds in every period;
- renewable output stays within period-specific bounds;
- scheduled reserve meets the system requirement;
- reserve is deliverable under headroom, startup/shutdown capability, and ramp limits;
- minimum up/down time and initial conditions are respected;
- cost and summary fields are recomputed from arrays.
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.
- 8d ago First seen · 241 lines · 66 tokens per session scan A e44bbc07a1f2
unit-commitment-operating-rules is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,027 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
run-aeon-benchmark
Use when asked to run, benchmark, evaluate, or score an LLM with AEON Bench. You run the AEON Bench Pod on the user's machine, point it at a model, run the benchmark, and submit the signed result to the public leaderboard at aeon-bench.com. All work happens on the pod. The mothership only shows the board and accepts…
plate-tectonics-geospatial
Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.
data-matching
Matching observation data to simulation output with exact datetime and depth binning.
model-calibration
Calculating RMSE metrics and parameter calibration for lake model validation.
dbscan-custom-metric
Run DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.
greedy-bipartite-matching
Implement greedy bipartite matching for pairing cluster centroids with expert annotations.