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 dc-power-flowgit 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/dc-power-flow)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/dc-power-flow"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/dc-power-flow/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/dc-power-flow"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/dc-power-flow.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 | $0.00041 | $0.00846 |
| Opus 5 | $0.00020 | $0.00423 |
| Sonnet 5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
dc-power-flow 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 7d 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:
- dc-power-flow — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DC Power Flow
DC power flow is a linearized approximation of AC power flow, suitable for economic dispatch and contingency analysis.
DC Approximations
- Lossless lines - Ignore resistance (R ≈ 0)
- Flat voltage - All bus voltages = 1.0 pu
- Small angles - sin(θ) ≈ θ, cos(θ) ≈ 1
Result: Power flow depends only on bus angles (θ) and line reactances (X).
Bus Number Mapping
Power system bus numbers may not be contiguous (e.g., case300 has non-sequential bus IDs). Always create a mapping from bus numbers to 0-indexed array positions:
# Create mapping: bus_number -> 0-indexed position
bus_num_to_idx = {int(buses[i, 0]): i for i in range(n_bus)}
# Use mapping for branch endpoints
f = bus_num_to_idx[int(br[0])] # NOT br[0] - 1
t = bus_num_to_idx[int(br[1])]
Susceptance Matrix (B)
Build from branch reactances using bus number mapping:
# Run: scripts/build_b_matrix.py
# Or inline:
bus_num_to_idx = {int(buses[i, 0]): i for i in range(n_bus)}
B = np.zeros((n_bus, n_bus))
for br in branches:
f = bus_num_to_idx[int(br[0])] # Map bus number to index
t = bus_num_to_idx[int(br[1])]
x = br[3] # Reactance
if x != 0:
b = 1.0 / x
B[f, f] += b
B[t, t] += b
B[f, t] -= b
B[t, f] -= b
Power Balance Equation
At each bus: Pg - Pd = B[i, :] @ θ
Where:
- Pg = generation at bus (pu)
- Pd = load at bus (pu)
- θ = vector of bus angles (radians)
Slack Bus
One bus must have θ = 0 as reference. Find slack bus (type=3):
slack_idx = None
for i in range(n_bus):
if buses[i, 1] == 3:
slack_idx = i
break
constraints.append(theta[slack_idx] == 0)
Line Flow Calculation
Flow on branch from bus f to bus t (use bus number mapping):
f = bus_num_to_idx[int(br[0])]
t = bus_num_to_idx[int(br[1])]
b = 1.0 / br[3] # Susceptance = 1/X
flow_pu = b * (theta[f] - theta[t])
flow_MW = flow_pu * baseMVA
Line Loading Percentage
loading_pct = abs(flow_MW) / rating_MW * 100
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 117 lines · 41 tokens per session scan A 461a4a93c6ba
dc-power-flow is a skill published in the GitHub repository benchflow-ai/skillsbench (1,757 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 846 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 2026-09-03.
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…
data-matching
Matching observation data to simulation output with exact datetime and depth binning.
dbscan-custom-metric
Run DBSCAN clustering with a custom distance metric using sklearn, including how to define weighted Euclidean metrics and extract cluster centroids.
plate-tectonics-geospatial
Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.
fortran-namelist
Reading and modifying Fortran namelist configuration files for scientific models.
model-calibration
Calculating RMSE metrics and parameter calibration for lake model validation.