Exploratory Data Analysis
spacering-net/codeg
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.
Calculating powerlifting scores to determine the performance of lifters across different weight classes.
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Raidriar7170/hermes-skilleval powerlifting --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .claude/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .claude/skills/powerlifting && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .claude/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerliftingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Raidriar7170/hermes-skilleval powerlifting --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .agents/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .agents/skills/powerlifting && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .agents/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Raidriar7170/hermes-skilleval powerlifting --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .cursor/skills/powerlifting && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .cursor/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Raidriar7170/hermes-skilleval.git --path artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Raidriar7170/hermes-skilleval powerlifting --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .gemini/skills/powerlifting && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .gemini/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Raidriar7170/hermes-skilleval powerliftingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .github/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .github/skills/powerlifting && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .github/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Raidriar7170/hermes-skilleval powerlifting --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Raidriar7170/hermes-skilleval.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting .opencode/skills/powerlifting && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "powerlifting" agent skill from https://github.com/Raidriar7170/hermes-skilleval/tree/main/artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting into .opencode/skills/powerlifting/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "powerlifting", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
powerliftingCalculating powerlifting scores to determine the performance of lifters across different weight classes.
Powerlifting is an agent skill from Raidriar7170/hermes-skilleval. Calculating powerlifting scores to determine the performance of lifters across different weight classes.
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics. The repository describes itself as: Verification-gated skill routing and self-improvement harness for Hermes-style agent skills. The licence is MIT.
Read from SKILL.md and the folder at commit 8f6a21e. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are rust).
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
powerliftpro.apppowerlifting.sporten.wikipedia.orgworldpowerliftingcongress.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Powerlifting loads about 3.7k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 613 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Raidriar7170/hermes-skilleval at commit 8f6a21e, republished under its MIT licence (© Raidriar7170). 613 words, ~3,715 tokens.
.claude/skills/powerlifting/SKILL.md (or your agent's skills folder).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.
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:
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:
These coefficients are carefully designed to balance the advantage heavier lifters might have in absolute strength and the lighter lifters’ advantage in relative strength.
use crate::poly4;
use opltypes::*;
pub fn dots_coefficient_men(bodyweightkg: f64) -> f64 {
const A: f64 = -0.0000010930;
const B: f64 = 0.0007391293;
const C: f64 = -0.1918759221;
const D: f64 = 24.0900756;
const E: f64 = -307.75076;
// Bodyweight bounds are defined; bodyweights out of range match the boundaries.
let adjusted = bodyweightkg.clamp(40.0, 210.0);
500.0 / poly4(A, B, C, D, E, adjusted)
}
pub fn dots_coefficient_women(bodyweightkg: f64) -> f64 {
const A: f64 = -0.0000010706;
const B: f64 = 0.0005158568;
const C: f64 = -0.1126655495;
const D: f64 = 13.6175032;
const E: f64 = -57.96288;
// Bodyweight bounds are defined; bodyweights out of range match the boundaries.
let adjusted = bodyweightkg.clamp(40.0, 150.0);
500.0 / poly4(A, B, C, D, E, adjusted)
}
/// Calculates Dots points.
///
/// Dots were introduced by the German IPF Affiliate BVDK after the IPF switched to
/// IPF Points, which do not allow comparing between sexes. The BVDK hosts team
/// competitions that allow lifters of all sexes to compete on a singular team.
///
/// Since Wilks points have been ostracized from the IPF, and IPF Points are
/// unsuitable, German lifters therefore came up with their own formula.
///
/// The author of the Dots formula is Tim Konertz <tim.konertz@outlook.com>.
///
/// Tim says that Dots is an acronym for "Dynamic Objective Team Scoring,"
/// but that they chose the acronym before figuring out the expansion.
pub fn dots(sex: Sex, bodyweight: WeightKg, total: WeightKg) -> Points {
if bodyweight.is_zero() || total.is_zero() {
return Points::from_i32(0);
}
let coefficient: f64 = match sex {
Sex::M | Sex::Mx => dots_coefficient_men(f64::from(bodyweight)),
Sex::F => dots_coefficient_women(f64::from(bodyweight)),
};
Points::from(coefficient * f64::from(total))
}The IPF Good Lift Coefficient calculator computes the comparative weight coefficient between weight lifters based on the weight of the lifter (x), the type of lift and the gender of the lifter, all combined in the IPF GL Coefficient formula. Information about this is from IPF.
INSTRUCTIONS: Choose units and enter the following:
IPFL GL Coefficient (IPC): The calculator returns the coefficient as a real number (decimal).
The International Powerlifting Federation GL coefficient formula is:
IPC=100A−B⋅e−C⋅BWT
where:
use opltypes::*;
/// Hardcoded formula parameters: `(A, B, C)`.
type Parameters = (f64, f64, f64);
/// Gets formula parameters from what is effectively a lookup table.
fn parameters(sex: Sex, equipment: Equipment, event: Event) -> Parameters {
// Since the formula was made for the IPF, it only covers Raw and Single-ply.
// We do our best and just reuse those for Wraps and Multi-ply, respectively.
let equipment = match equipment {
Equipment::Raw | Equipment::Wraps | Equipment::Straps => Equipment::Raw,
Equipment::Single | Equipment::Multi | Equipment::Unlimited => Equipment::Single,
};
// Points are only specified for Sex::M and Sex::F.
let dichotomous_sex = match sex {
Sex::M | Sex::Mx => Sex::M,
Sex::F => Sex::F,
};
const SBD: Event = Event::sbd();
const B: Event = Event::b();
match (event, dichotomous_sex, equipment) {
(SBD, Sex::M, Equipment::Raw) => (1199.72839, 1025.18162, 0.009210),
(SBD, Sex::M, Equipment::Single) => (1236.25115, 1449.21864, 0.01644),
(SBD, Sex::F, Equipment::Raw) => (610.32796, 1045.59282, 0.03048),
(SBD, Sex::F, Equipment::Single) => (758.63878, 949.31382, 0.02435),
(B, Sex::M, Equipment::Raw) => (320.98041, 281.40258, 0.01008),
(B, Sex::M, Equipment::Single) => (381.22073, 733.79378, 0.02398),
(B, Sex::F, Equipment::Raw) => (142.40398, 442.52671, 0.04724),
(B, Sex::F, Equipment::Single) => (221.82209, 357.00377, 0.02937),
_ => (0.0, 0.0, 0.0),
}
}
/// Calculates IPF GOODLIFT Points.
pub fn goodlift(
sex: Sex,
equipment: Equipment,
event: Event,
bodyweight: WeightKg,
total: WeightKg,
) -> Points {
// Look up parameters.
let (a, b, c) = parameters(sex, equipment, event);
// Exit early for undefined cases.
if a == 0.0 || bodyweight < WeightKg::from_i32(35) || total.is_zero() {
return Points::from_i32(0);
}
// A - B * e^(-C * Bwt).
let e_pow = (-c * f64::from(bodyweight)).exp();
let denominator = a - (b * e_pow);
// Prevent division by zero.
if denominator == 0.0 {
return Points::from_i32(0);
}
// Calculate GOODLIFT points.
// We add the requirement that the value be non-negative.
let points: f64 = f64::from(total) * (0.0_f64).max(100.0 / denominator);
Points::from(points)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn published_examples() {
// Dmitry Inzarkin from 2019 IPF World Open Men's Championships.
let weight = WeightKg::from_f32(92.04);
let total = WeightKg::from_f32(1035.0);
assert_eq!(
goodlift(Sex::M, Equipment::Single, Event::sbd(), weight, total),
Points::from(112.85)
);
// Susanna Torronen from 2019 World Open Classic Bench Press Championships.
let weight = WeightKg::from_f32(70.50);
let total = WeightKg::from_f32(122.5);
assert_eq!(
goodlift(Sex::F, Equipment::Raw, Event::b(), weight, total),
Points::from(96.78)
);
}
}The following equation is used to calculate the Wilks coefficient: $$ \text{Coef} = \frac{500}{a + bx + cx^2 + dx^3 + ex^4 + fx^5} $$ where $x$ is the body weightof the lifter in kilograms.
The total weight lifted (in kg) is multiplied by the coefficient to find the standard amount lifted, normalised across all body weights.
| Men | Women | |
|---|---|---|
| a | -216.0475144 | 594.31747775582 |
| b | 16.2606339 | −27.23842536447 |
| c | -0.002388645 | 0.82112226871 |
| d | -0.00113732 | −0.00930733913 |
| e | 7.01863 × 10−6 | 4.731582 × 10−5 |
| f | −1.291 × 10−8 | −9.054 × 10−8 |
use crate::poly5;
use opltypes::*;
pub fn wilks_coefficient_men(bodyweightkg: f64) -> f64 {
// Wilks defines its polynomial backwards:
// A + Bx + Cx^2 + ...
const A: f64 = -216.0475144;
const B: f64 = 16.2606339;
const C: f64 = -0.002388645;
const D: f64 = -0.00113732;
const E: f64 = 7.01863E-06;
const F: f64 = -1.291E-08;
// Upper bound avoids asymptote.
// Lower bound avoids children with huge coefficients.
let adjusted = bodyweightkg.clamp(40.0, 201.9);
500.0 / poly5(F, E, D, C, B, A, adjusted)
}
pub fn wilks_coefficient_women(bodyweightkg: f64) -> f64 {
const A: f64 = 594.31747775582;
const B: f64 = -27.23842536447;
const C: f64 = 0.82112226871;
const D: f64 = -0.00930733913;
const E: f64 = 0.00004731582;
const F: f64 = -0.00000009054;
// Upper bound avoids asymptote.
// Lower bound avoids children with huge coefficients.
let adjusted = bodyweightkg.clamp(26.51, 154.53);
500.0 / poly5(F, E, D, C, B, A, adjusted)
}
/// Calculates Wilks points.
pub fn wilks(sex: Sex, bodyweight: WeightKg, total: WeightKg) -> Points {
if bodyweight.is_zero() || total.is_zero() {
return Points::from_i32(0);
}
let coefficient: f64 = match sex {
Sex::M | Sex::Mx => wilks_coefficient_men(f64::from(bodyweight)),
Sex::F => wilks_coefficient_women(f64::from(bodyweight)),
};
Points::from(coefficient * f64::from(total))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn coefficients() {
// Coefficients taken verbatim from the old Python implementation.
assert_eq!(wilks_coefficient_men(100.0), 0.6085890719066511);
assert_eq!(wilks_coefficient_women(100.0), 0.8325833167368228);
}
#[test]
fn points() {
// Point values taken (rounded) from the old Python implementation.
assert_eq!(
wilks(Sex::M, WeightKg::from_i32(100), WeightKg::from_i32(1000)),
Points::from(608.58907)
);
assert_eq!(
wilks(Sex::F, WeightKg::from_i32(60), WeightKg::from_i32(500)),
Points::from(557.4434)
);
}
}When Powerlifting began having 'masters', it quickly became apparent that some sort of age allowance or 'handicap' was needed by this group to sort them out, one from another. How much better must a 40-yr-old be, than a 50-yr-old, to be considered a better lifter? How much better than a 55-yr-old, a 60-yr-old, etc? So, a set of age multipliers, or 'handicap numbers', was issued for Master Lifters year-by-year, from 40 through 80. Since then, however, the number of Master Lifters in the 50+ and 60+ group has become so large that a revision (based on extensive study and years of backup data) was needed. These new numbers are based on comparison of the totals of actual lifters over the past seven years, and a chart for their usage is on the final page of this section.
The formula is: (LT) times (GBC) = (PN)
LT - Lifter's Total GBC – Glossbrenner Bodyweight Coefficient * PN - Product Number
use opltypes::*;
use crate::schwartzmalone::{malone_coefficient, schwartz_coefficient};
use crate::wilks::{wilks_coefficient_men, wilks_coefficient_women};
fn glossbrenner_coefficient_men(bodyweightkg: f64) -> f64 {
// Glossbrenner is defined piecewise.
if bodyweightkg < 153.05 {
(schwartz_coefficient(bodyweightkg) + wilks_coefficient_men(bodyweightkg)) / 2.0
} else {
// Linear coefficients found by fitting to a table.
const A: f64 = -0.000821668402557;
const B: f64 = 0.676940740094416;
(schwartz_coefficient(bodyweightkg) + A * bodyweightkg + B) / 2.0
}
}
fn glossbrenner_coefficient_women(bodyweightkg: f64) -> f64 {
// Glossbrenner is defined piecewise.
if bodyweightkg < 106.3 {
(malone_coefficient(bodyweightkg) + wilks_coefficient_women(bodyweightkg)) / 2.0
} else {
// Linear coefficients found by fitting to a table.
const A: f64 = -0.000313738002024;
const B: f64 = 0.852664892884785;
(malone_coefficient(bodyweightkg) + A * bodyweightkg + B) / 2.0
}
}
/// Calculates Glossbrenner points.
///
/// Glossbrenner is the average of two older systems, Schwartz-Malone and Wilks,
/// with a piecewise linear section.
///
/// This points system is most often used by GPC affiliates.
pub fn glossbrenner(sex: Sex, bodyweight: WeightKg, total: WeightKg) -> Points {
if bodyweight.is_zero() || total.is_zero() {
return Points::from_i32(0);
}
let coefficient: f64 = match sex {
Sex::M | Sex::Mx => glossbrenner_coefficient_men(f64::from(bodyweight)),
Sex::F => glossbrenner_coefficient_women(f64::from(bodyweight)),
};
Points::from(coefficient * f64::from(total))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn coefficients() {
// Coefficients taken verbatim from the old Python implementation.
assert_eq!(glossbrenner_coefficient_men(100.0), 0.5812707859533183);
assert_eq!(glossbrenner_coefficient_women(100.0), 0.7152488066040259);
}
#[test]
fn points() {
// Point values taken (rounded) from the old Python implementation.
assert_eq!(
glossbrenner(Sex::M, WeightKg::from_i32(100), WeightKg::from_i32(1000)),
Points::from(581.27)
);
assert_eq!(
glossbrenner(Sex::F, WeightKg::from_i32(60), WeightKg::from_i32(500)),
Points::from(492.53032)
);
// Zero bodyweight should be treated as "unknown bodyweight".
assert_eq!(
glossbrenner(Sex::M, WeightKg::from_i32(0), WeightKg::from_i32(500)),
Points::from_i32(0)
);
}
}© Raidriar7170, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting of Raidriar7170/hermes-skilleval.
Open the folder on GitHubat commit 8f6a21e
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Raidriar7170/hermes-skilleval, which our catalogue first saw on October 7, 2026.
Powerlifting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Powerlifting this skillRaidriar7170/hermes-skilleval | 125 | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Exploratory Data Analysisspacering-net/codeg | 3.8k | 15 repos | ~3.6k | Automated safety check: Pass | MIT | |
| MatplotlibzLanqing/codex-claude-academic-skills | 4.6k | 18 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Scikit LearnzLanqing/codex-claude-academic-skills | 4.6k | 17 repos | ~3.9k | Automated safety check: Pass | BSD-3-Clause | |
| Chart Visualizationbytedance/deer-flow | 83k | 2 repos | ~840 | Automated safety check: Pass | MIT | |
| TimesFM Forecastinggoogle-research/timesfm | 34k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 |
spacering-net/codeg
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats.
zLanqing/codex-claude-academic-skills
Low-level plotting library for full customization. An agent skill from zLanqing/codex-claude-academic-skills.
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
bytedance/deer-flow
Picks a suitable chart type from 26 options for your data, maps the data to that chart's parameters and generates a chart image through a JavaScript script.
google-research/timesfm
Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.
vercel/next.js
Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app…
Raidriar7170/hermes-skilleval
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.
Raidriar7170/hermes-skilleval
A library for building, validating, visualizing, and serializing dialogue graphs.
Raidriar7170/hermes-skilleval
Geospatial routing data handling for depot and station coordinates, route node IDs, internal index mappings, great-circle distance matrices, and route-distance reconstruction.
Raidriar7170/hermes-skilleval
Translate logistics and operations rules into optimization variables and constraints.
Raidriar7170/hermes-skilleval
Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables.
Raidriar7170/hermes-skilleval
SCIP optimization with PySCIPOpt. An agent skill from Raidriar7170/hermes-skilleval.
Categories
Calculating powerlifting scores to determine the performance of lifters across different weight classes. Powerlifting is an agent skill from Raidriar7170/hermes-skilleval. Calculating powerlifting scores to determine the performance of lifters across different weight classes.
Powerlifting fits situations like: data & Analytics work in your project.
Run `npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a claude-code`. Or copy the skill folder (artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting in Raidriar7170/hermes-skilleval) into .claude/skills/powerlifting in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a codex`. Or copy the skill folder (artifacts/v0.3/skillsbench-pilot/v0.3-stage2-input-package-candidate-20260701T010000Z/candidate-data/skill-sources/skillsbench__powerlifting in Raidriar7170/hermes-skilleval) into .agents/skills/powerlifting in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Raidriar7170/hermes-skilleval --skill powerlifting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/powerlifting, .gemini/skills/powerlifting, .github/skills/powerlifting and .opencode/skills/powerlifting in your project.
SKILL.md names no scripts, command-line tools or credentials: Powerlifting is instructions for the agent only. Our summary lists: Python 3.
SKILL.md names 4 domains. As links in the text: powerliftpro.app, powerlifting.sport, en.wikipedia.org and worldpowerliftingcongress.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Powerlifting is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Powerlifting: Exploratory Data Analysis (spacering-net/codeg, 3.8k stars), Matplotlib (zLanqing/codex-claude-academic-skills, 4.6k stars), Scikit Learn (zLanqing/codex-claude-academic-skills, 4.6k stars) and Chart Visualization (bytedance/deer-flow, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Raidriar7170 (a GitHub user) maintains it in Raidriar7170/hermes-skilleval, which has 125 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 26, 2026.
Source: Raidriar7170/hermes-skilleval on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.