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 imc-tuning-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/imc-tuning-rules)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/imc-tuning-rules"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/imc-tuning-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/imc-tuning-rules"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/imc-tuning-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 | $0.00028 | $0.00943 |
| Opus 5 | $0.00014 | $0.00472 |
| Sonnet 5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
imc-tuning-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 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:
- imc-tuning-rules — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IMC Tuning Rules for PI/PID Controllers
Overview
Internal Model Control (IMC) is a systematic method for tuning PI/PID controllers based on a process model. Once you've identified system parameters (K and tau), IMC provides controller gains.
Why IMC?
- Model-based: Uses identified process parameters directly
- Single tuning parameter: Just choose the closed-loop speed (lambda)
- Guaranteed stability: For first-order systems, always stable if model is accurate
- Predictable response: Closed-loop time constant equals lambda
IMC Tuning for First-Order Systems
For a first-order process with gain K and time constant tau:
Process: G(s) = K / (tau*s + 1)
The IMC-tuned PI controller gains are:
Kp = tau / (K * lambda)
Ki = Kp / tau = 1 / (K * lambda)
Kd = 0 (derivative not needed for first-order systems)
Where:
Kp= Proportional gainKi= Integral gain (units: 1/time)Kd= Derivative gain (zero for first-order)lambda= Desired closed-loop time constant (tuning parameter)
Choosing Lambda (λ)
Lambda controls the trade-off between speed and robustness:
| Lambda | Behavior |
|---|---|
lambda = 0.1 * tau |
Very aggressive, fast but sensitive to model error |
lambda = 0.5 * tau |
Aggressive, good for accurate models |
lambda = 1.0 * tau |
Moderate, balanced speed and robustness |
lambda = 2.0 * tau |
Conservative, robust to model uncertainty |
Default recommendation: Start with lambda = tau
For noisy systems or uncertain models, use larger lambda. For precise models and fast response needs, use smaller lambda.
Implementation
def calculate_imc_gains(K, tau, lambda_factor=1.0):
"""
Calculate IMC-tuned PI gains for a first-order system.
Args:
K: Process gain
tau: Time constant
lambda_factor: Multiplier for lambda (default 1.0 = lambda equals tau)
Returns:
dict with Kp, Ki, Kd, lambda
"""
lambda_cl = lambda_factor * tau
Kp = tau / (K * lambda_cl)
Ki = Kp / tau
Kd = 0.0
return {
"Kp": Kp,
"Ki": Ki,
"Kd": Kd,
"lambda": lambda_cl
}
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 · 132 lines · 28 tokens per session scan A 2388dcb94f07
imc-tuning-rules is a skill published in the GitHub repository benchflow-ai/skillsbench (1,760 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 943 once invoked, about $0.0001 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
exploded-view-illustration
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
membrowse-integrate
Integrate MemBrowse memory tracking into a project that produces ELF binaries. Use when the user wants to set up MemBrowse, add memory analysis GitHub workflows, create membrowse-targets.json for tracking memory usage, or add a MemBrowse badge to the README. Works with embedded firmware (STM32, ESP32, nRF, RISC-V) and…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
akg-agents
An agent workflow for developing, generating, testing, and tuning AKG operators. AKG is a toolkit for generating optimized computational kernels.
fpga
FPGA development guidelines covering Vivado, SystemVerilog, timing closure, AXI interfaces, and hardware optimization.