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 powerliftinggit 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/powerlifting)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/powerlifting"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/powerlifting/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/powerlifting"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/powerlifting.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 | $0.00021 | $0.04271 |
| Opus 5 | $0.00010 | $0.02135 |
| Sonnet 5 | $0.00004 | $0.00854 |
| Haiku 4.5 | $0.00002 | $0.00427 |
Grade A, and why
powerlifting 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- powerlifting — 100% identical, 0 lines differ
- powerlifting — 100% identical, 0 lines differ
- powerlifting — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Calculating Powerlifting Scores as a Professional Coach
Dynamic Objective Team Scoring (Dots)
In the world of powerlifting, comparing lifters across different body weights is essential to /determine relative strength and fairness in competition. This is where the DOTS score—short for “Dynamic Objective Team Scoring”—comes into play. It’s a widely-used formula that helps level the playing field by standardizing performances regardless of a lifter’s body weight. Whether you’re new to powerlifting or a seasoned competitor, understanding the DOTS score is crucial for evaluating progress and competing effectively. This section is from powerliftpro.
What is the DOTS Score?
The DOTS score is a mathematical formula used to normalize powerlifting totals based on a lifter’s body weight. It provides a single number that represents a lifter’s relative strength, allowing for fair comparisons across all weight classes.
The score takes into account:
- The lifter's total: The combined weight lifted in the squat, bench press, and deadlift.
- Body weight: The lifter’s weight on competition day.
The DOTS Formula
For real powerlifting nerds who want to calculate their DOTS longhand (remember to show all work! sorry, old math class joke), the DOTS formula is as follows:
DOTS Score=Total Weight Lifted (kg)×a+b(BW)+c(BW2)+d(BW3)+e(BW4)500
Here:
- Total Weight Lifted (kg): Your combined total from the squat, bench press, and deadlift.
- BW: Your body weight in kilograms.
- a, b, c, d, e: Coefficients derived from statistical modeling to ensure accurate scaling across various body weights.
These coefficients are carefully designed to balance the advantage heavier lifters might have in absolute strength and the lighter lifters’ advantage in relative strength.
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 First seen · 398 lines · 21 tokens per session scan A 8767b92aa108
powerlifting is a skill published in the GitHub repository benchflow-ai/skillsbench (1,754 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 21 tokens to every session and 4,271 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
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
Plan Mode
Clarify requirements and produce an implementation plan before changing files.