New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Hmt Monte Carlo

by psu-efd in psu-efd/pyHMT2D

Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities.

MITAuto-check passed

Install Hmt Monte Carlo

skills CLI
$ npx skills add psu-efd/pyHMT2D --skill hmt-monte-carlo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install psu-efd/pyHMT2D hmt-monte-carlo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/psu-efd/pyHMT2D.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/hmt-monte-carlo .claude/skills/hmt-monte-carlo && rm -rf skills-src

Use ~/.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/

Facts

Skill name
hmt-monte-carlo
GitHub stars
133
Token cost
~672 tokens
SKILL.md length
185 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities.

  • Works in 10 steps: Check that a project is open. → Show available materials. → Ask the user for uncertain parameters.… → …
  • Wants uncertainty analysis
  • SKILL.md covers Prerequisites and Steps
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hmt Monte Carlo is an agent skill from psu-efd/pyHMT2D. Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities. Use this when the user wants uncertainty analysis, Monte Carlo simulation, or probabilistic results.

Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Python Hydraulic Modeling Tools - 2D. The licence is MIT.

When your agent uses it

  • Wants uncertainty analysis
  • Monte Carlo simulation
  • Probabilistic results

Example prompts

  • “/hmt-monte-carlo”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Check that a project is open.
  2. Show available materials.
  3. Ask the user for uncertain parameters. For each
  4. Build validated parameter specifications.
  5. Ask for MC settings: number of samples (50–200), random seed (default 42),
  6. Generate samples.
  7. Run Monte Carlo simulations.
  8. Report: successful/failed runs, results JSON path.
  9. Compute statistics. Ask for observation point coordinates if the user wants point statistics.
  10. Report the spatial exceedance VTK path for ParaView visualization.

What it can do on your machine

Read from SKILL.md and the folder at commit 57645ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hmt Monte Carlo loads about 672 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 185 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~672

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from psu-efd/pyHMT2D at commit 57645ff, republished under its MIT licence (© psu-efd). 185 words, ~672 tokens.

Download SKILL.mdSave it as .claude/skills/hmt-monte-carlo/SKILL.md (or your agent's skills folder).
name
hmt-monte-carlo
description
Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities. Use this when the user wants uncertainty analysis, Monte Carlo simulation, or probabilistic results.

Run Monte Carlo uncertainty analysis on a hydraulic model.

Prerequisites

  • Project in a base_case/ subdirectory
  • Parameter uncertainty distributions defined by user
  • Solver paths configured in hmt_config.json

Steps

  1. Check that a project is open. If not, ask the user to run /hmt-open pointing to base_case/<project_file>.

  2. Show available materials.

    bash
    hmt-cli get_materials

  3. Ask the user for uncertain parameters. For each:

    • Material name or BC ID
    • Distribution: "truncated_normal" (default) or "uniform"
    • For truncated_normal: mean, std, min, max
    • For uniform: min, max

  4. Build validated parameter specifications.

    bash
    hmt-cli build_param_specs --args '{"specs": [
  {"type": "manning_n", "material_name": "<name>", "distribution": "truncated_normal",
   "mean": <mean>, "std": <std>, "min": <min>, "max": <max>},
  ...
]}'

    Confirm the distributions with the user.

  5. Ask for MC settings: number of samples (50–200), random seed (default 42), output directory (default ./mc_runs), parallel processes (default 1).

  6. Generate samples.

    bash
    hmt-cli generate_mc_samples --args '{"param_specs": <specs>, "n_samples": <N>, "random_seed": <seed>, "output_csv": "mc_samples.csv"}'

    Show a preview of the first 5 sample rows.

  7. Run Monte Carlo simulations.

    bash
    hmt-cli run_monte_carlo --args '{"base_case_dir": "./base_case", "param_specs": <specs>, "n_samples": <N>, "n_processes": <procs>, "random_seed": <seed>, "sample_csv": "mc_samples.csv", "delete_cases": true, "output_dir": "<output_dir>"}'

    Periodically show progress while waiting:

    bash
    tail -20 mc_progress.log

  8. Report: successful/failed runs, results JSON path.

  9. Compute statistics. Ask for observation point coordinates if the user wants point statistics.

    bash
    hmt-cli get_mc_statistics --args '{"results_json": "<path>", "observation_points": [{"name": "<name>", "x": <x>, "y": <y>}], "exceedance_probabilities": [99, 90, 50, 10, 1]}'

    Present exceedance table: Point | P99 | P90 | P50 | P10 | P1

  10. Report the spatial exceedance VTK path for ParaView visualization.

Troubleshooting:

  • Many failed cases → check pyHMT2D.log
  • Variable detection fails → pass "variable": "<name>" explicitly

© psu-efd, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/hmt-monte-carlo of psu-efd/pyHMT2D.

Open the folder on GitHubat commit 57645ff

Compare with similar skills

Hmt Monte Carlo 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.

Hmt Monte Carlo compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hmt Monte Carlo this skillpsu-efd/pyHMT2D133—~672Automated safety check: PassMIT
Monte Carlo Remediationsickn33/agentic-awesome-skills47k1 repos~4kAutomated safety check: PassApache-2.0
Monte Carlo Preventsickn33/agentic-awesome-skills47k1 repos~3.3kAutomated safety check: PassMIT
Monte Carlo Context Detectionsickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: WarnMIT
Monte Carlo Push Ingestionsickn33/agentic-awesome-skills47k1 repos~4.6kAutomated safety check: PassMIT
Monte Carlo Asset Healthsickn33/agentic-awesome-skills47k1 repos~2.4kAutomated safety check: PassApache-2.0

Similar skills

  • Monte Carlo Remediation

    sickn33/agentic-awesome-skills

    Investigate and remediate data quality alerts using Monte Carlo MCP tools.

    47k GitHub starsUsed in 1 repo~4k tokens
    DevelopmentAuto-check passed

  • Monte Carlo Prevent

    sickn33/agentic-awesome-skills

    Surfaces Monte Carlo data observability context (table health, alerts, lineage, blast radius) before SQL/dbt edits.

    47k GitHub starsUsed in 1 repo~3.3k tokens
    Data & AnalyticsAuto-check passed

  • Monte Carlo Context Detection

    sickn33/agentic-awesome-skills

    Route data-related requests to the right Monte Carlo skill or workflow.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Data & AnalyticsAuto-check: warnings

  • Monte Carlo Push Ingestion

    sickn33/agentic-awesome-skills

    Expert guide for pushing metadata, lineage, and query logs to Monte Carlo from any data warehouse.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    DatabasesAuto-check passed

  • Monte Carlo Asset Health

    sickn33/agentic-awesome-skills

    Curated upstream guidance for Monte Carlo Asset Health; use when the workflow matches the user goal.

    47k GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

  • Monte Carlo Monitor Creation

    sickn33/agentic-awesome-skills

    Guides creation of Monte Carlo monitors via MCP tools, producing monitors-as-code YAML for CI/CD deployment.

    47k GitHub starsUsed in 1 repo~2.9k tokens
    DevOps & CloudAuto-check passed

More from psu-efd/pyHMT2D

All 9 skills in this repo

  • Hmt Convert

    psu-efd/pyHMT2D

    Convert between hydraulic model formats. An agent skill from psu-efd/pyHMT2D.

    133 GitHub stars~605 tokensUpdated 2 mo ago
    Auto-check passed

  • Hmt Calibrate

    psu-efd/pyHMT2D

    Run automated Manning's n calibration against observed water surface elevations using Bayesian optimization or Nelder-Mead.

    133 GitHub stars~597 tokensUpdated 2 mo ago
    Auto-check passed

  • Hmt Modify

    psu-efd/pyHMT2D

    Modify Manning's n roughness coefficients, inlet flow rates, or exit water surface elevations for the currently open pyHMT2D project and save the changes.

    133 GitHub stars~470 tokensUpdated 2 mo ago
    Auto-check passed

  • Hmt Open

    psu-efd/pyHMT2D

    Open a pyHMT2D hydraulic model project (SRH-2D or HEC-RAS) and display its materials, boundary conditions, and available result variables.

    133 GitHub stars~593 tokensUpdated 2 mo ago
    Auto-check passed

  • Hmt Results

    psu-efd/pyHMT2D

    Load simulation results and query values at specific points, domain-wide statistics, flood extent, or cross-section profiles.

    133 GitHub stars~478 tokensUpdated 2 mo ago
    Auto-check passed

  • Hmt Export

    psu-efd/pyHMT2D

    Export simulation results and/or the computational mesh to VTK files for ParaView visualization.

    133 GitHub stars~272 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Hmt Monte Carlo

What does Hmt Monte Carlo do?

Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities. Hmt Monte Carlo is an agent skill from psu-efd/pyHMT2D. Run Monte Carlo uncertainty analysis on a hydraulic model by sampling parameters from statistical distributions and computing exceedance probabilities.

When should I use Hmt Monte Carlo?

Hmt Monte Carlo fits situations like: wants uncertainty analysis; monte Carlo simulation; probabilistic results.

How do I install Hmt Monte Carlo in Claude Code?

Run `npx skills add psu-efd/pyHMT2D --skill hmt-monte-carlo -a claude-code`. Or copy the skill folder (.agents/skills/hmt-monte-carlo in psu-efd/pyHMT2D) into .claude/skills/hmt-monte-carlo in your project. Claude Code loads it when a task matches its description.

How do I install Hmt Monte Carlo in Codex?

Run `npx skills add psu-efd/pyHMT2D --skill hmt-monte-carlo -a codex`. Or copy the skill folder (.agents/skills/hmt-monte-carlo in psu-efd/pyHMT2D) into .agents/skills/hmt-monte-carlo in your project. Codex loads it when a task matches its description.

Can I use Hmt Monte Carlo in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add psu-efd/pyHMT2D --skill hmt-monte-carlo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hmt-monte-carlo, .gemini/skills/hmt-monte-carlo, .github/skills/hmt-monte-carlo and .opencode/skills/hmt-monte-carlo in your project.

What does Hmt Monte Carlo need to run?

SKILL.md names no scripts, command-line tools or credentials: Hmt Monte Carlo is instructions for the agent only.

Does Hmt Monte Carlo access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hmt Monte Carlo safe to install?

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.

What licence does Hmt Monte Carlo use?

Hmt Monte Carlo is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hmt Monte Carlo use?

About 672 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Hmt Monte Carlo?

Skills that share tags, products or a category with Hmt Monte Carlo: Monte Carlo Remediation (sickn33/agentic-awesome-skills, 47k stars), Monte Carlo Prevent (sickn33/agentic-awesome-skills, 47k stars), Monte Carlo Context Detection (sickn33/agentic-awesome-skills, 47k stars) and Monte Carlo Push Ingestion (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hmt Monte Carlo?

psu-efd (a GitHub user) maintains it in psu-efd/pyHMT2D, which has 133 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 9, 2026.

Source: psu-efd/pyHMT2D on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.