Senior Data Scientist
Raidriar7170/hermes-skilleval
World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics.
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference).
Install Forecasting Reverso
$ npx skills add oaustegard/claude-skills --skill forecasting-reverso -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install oaustegard/claude-skills forecasting-reverso --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/oaustegard/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/forecasting-reverso .claude/skills/forecasting-reverso && 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 "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .claude/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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/oaustegard/claude-skills/tree/main/forecasting-reversoType 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 oaustegard/claude-skills --skill forecasting-reverso -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install oaustegard/claude-skills forecasting-reverso --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/forecasting-reverso .agents/skills/forecasting-reverso && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .agents/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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 oaustegard/claude-skills --skill forecasting-reverso -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install oaustegard/claude-skills forecasting-reverso --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/forecasting-reverso .cursor/skills/forecasting-reverso && 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 "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .cursor/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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/oaustegard/claude-skills.git --path forecasting-reverso--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 oaustegard/claude-skills --skill forecasting-reverso -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install oaustegard/claude-skills forecasting-reverso --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/forecasting-reverso .gemini/skills/forecasting-reverso && 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 "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .gemini/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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 oaustegard/claude-skills forecasting-reversoInstalls 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 oaustegard/claude-skills --skill forecasting-reverso -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/forecasting-reverso .github/skills/forecasting-reverso && 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 "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .github/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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 oaustegard/claude-skills --skill forecasting-reverso -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install oaustegard/claude-skills forecasting-reverso --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/oaustegard/claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/forecasting-reverso .opencode/skills/forecasting-reverso && 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 "forecasting-reverso" agent skill from https://github.com/oaustegard/claude-skills/tree/main/forecasting-reverso into .opencode/skills/forecasting-reverso/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "forecasting-reverso", 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.
Facts
- Skill name
forecasting-reverso- GitHub stars
- 150
- Token cost
- ~1.5k tokens
- SKILL.md length
- 448 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 67
- Repo updated
- First seen
- Licence
- MIT
At a glance
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference).
- S provide time series data and request forecasts
- SKILL.md covers Setup (run once per…, Obtaining Weights, Model Configuration and Forecasting, plus 5 more sections
- Runs Python scripts from its folder; calls uv; reaches huggingface.co
- Tabular data with a temporal dimension needs future-value estimation
What it does
Forecasting Reverso is an agent skill from oaustegard/claude-skills. Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params). Triggers on "forecast", "predict", "time series", "Reverso", or when tabular data with a temporal dimension needs future-value estimation.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `README.md`, `references/architecture.md` and `scripts/load_checkpoint.py`).
It sits in Data & Analytics, covering Forecasting and time series. It works with NumPy and Hugging Face. The repository describes itself as: My collection of Claude skills. The licence is MIT.
When your agent uses it
- S provide time series data and request forecasts
- Tabular data with a temporal dimension needs future-value estimation
Example prompts
- “forecast”
- “predict”
- “time series”
- “/forecasting-reverso”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 90b0f1b. 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
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
huggingface.co
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
Forecasting Reverso loads about 1.5k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 103 tokens; SKILL.md has 448 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.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from oaustegard/claude-skills at commit 90b0f1b, republished under its MIT licence (© oaustegard). 448 words, ~1,470 tokens.
Download SKILL.mdSave it as
.claude/skills/forecasting-reverso/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- forecasting-reverso
- description
- Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Activate when users provide time series data and request forecasts, predictions, or extrapolations. Supports Reverso Small (550K params). Triggers on "forecast", "predict", "time series", "Reverso", or when tabular data with a temporal dimension needs future-value estimation.
- metadata.version
- 0.1.0
Reverso Time Series Forecasting
Produce zero-shot univariate time series forecasts using the Reverso foundation model family (arXiv:2602.17634), implemented in NumPy/Numba for CPU-only container execution.
Setup (run once per conversation)
uv pip install numba --system --break-system-packages
cp /mnt/skills/user/forecasting-reverso/scripts/reverso.py /home/claude/reverso.py
cp /mnt/skills/user/forecasting-reverso/scripts/load_checkpoint.py /home/claude/load_checkpoint.pyObtaining Weights
Two paths depending on network access:
Path A: Direct download (HuggingFace allow-listed)
import urllib.request, os
os.makedirs("/tmp/reverso", exist_ok=True)
url = "https://huggingface.co/shinfxh/reverso/resolve/main/checkpoints/reverso_small/checkpoint.pth"
urllib.request.urlretrieve(url, "/tmp/reverso/checkpoint.pth")Path B: User upload (HuggingFace not accessible)
If the download fails with a network error, tell the user:
I can't reach HuggingFace from this environment. Please download the checkpoint from https://huggingface.co/shinfxh/reverso/blob/main/checkpoints/reverso_small/checkpoint.pth and upload it here.
Then load from /mnt/user-data/uploads/checkpoint.pth.
Loading weights
from load_checkpoint import load_checkpoint
weights = load_checkpoint("/tmp/reverso/checkpoint.pth") # or upload pathModel Configuration
Reverso Small uses this config (matching the published args.json):
from reverso import ReversoConfig
config = ReversoConfig(d_model=64, module_list=["conv", "attn", "conv", "attn"])Forecasting
from reverso import forecast, warmup_jit
warmup_jit() # ~2s one-time JIT compilation
result = forecast(
series=data, # 1-D array/list of floats
prediction_length=96, # how many future steps
weights=weights, # dict from load_checkpoint
config=config,
)The function handles preprocessing (NaN interpolation, padding, min-max normalization) and autoregressive rollout internally.
Key parameters
flip_equivariant=True — averages forward pass on original and vertically-flipped input. Slightly improves single-step predictions but can dampen amplitude over multi-step rollout. Default is False.
Input Handling
Accept time series as Python list, NumPy array, CSV column, or inline values. Convert to 1-D float array before calling forecast().
For CSV/DataFrame input, ask the user which column to forecast if ambiguous.
The model's context window is 2048 steps. Series shorter than 2048 are left-padded with the first value. Series longer than 2048 use only the most recent 2048 observations. Provide at least a few hundred real data points for meaningful results — heavily padded context degrades forecast quality because the long convolution kernels process mostly constant input.
Visualization
import matplotlib.pyplot as plt
fig, ax = plt.subplots(figsize=(12, 4))
n = len(history)
ax.plot(range(n), history, label="Historical", color="#2563eb")
ax.plot(range(n, n + len(preds)), preds,
label="Forecast", color="#dc2626", linewidth=2)
ax.axvline(x=n, color="gray", linestyle="--", alpha=0.4)
ax.set_xlabel("Time step"); ax.set_ylabel("Value")
ax.legend(); fig.tight_layout()
fig.savefig("/mnt/user-data/outputs/forecast.png", dpi=150)Performance
| Phase | Latency |
|---|---|
| numba install (uv) | ~1.6s |
| Weight loading (.pth) | <1s |
| JIT warmup | ~2s |
| Forward pass (L=2048) | ~80ms |
| 96-step forecast (2 chunks) | ~160ms |
| 192-step forecast (4 chunks) | ~320ms |
Show full SKILL.md (195 more words)Show less
Container Environment Limits
Each forward pass takes ~65ms at L=2048. In the ephemeral container, reject batch forecasting requests that would exceed ~1500 forward passes (~100s wall time) to avoid timeouts.
Detect the container environment by checking for /mnt/user-data or /mnt/skills:
import os
IN_CONTAINER = os.path.exists("/mnt/user-data")Estimate cost before running when processing multiple series:
n_forwards = n_series * n_windows * max(1, pred_length // 48)
est_seconds = n_forwards * 0.065
if IN_CONTAINER and est_seconds > 100:
# Reject or subsample
max_series = int(1500 / (n_windows * max(1, pred_length // 48)))Practical limits at ~100s budget:
| Scenario | Series | Windows | Pred steps | Forwards | Time |
|---|---|---|---|---|---|
| Single series, 96-step | 1 | 1 | 2 chunks | 2 | 0.1s |
| Small dataset (sz_taxi) | 156 | 6 | 48 | 936 | 61s |
| Medium dataset, short horizon | 300 | 4 | 48 | 1200 | 78s |
| Large dataset (m4_yearly) | 22974 | 1 | 48 | 22974 | 25min ✗ |
When a request exceeds the budget, inform the user with the estimated time and suggest either subsampling or running locally. For benchmark evaluation of large datasets, recommend running outside the container.
Limitations
The model is strongest with periodic or quasi-periodic signals and full 2048-point context. Short series (under ~200 points) are heavily padded and produce degraded forecasts — this is a model limitation, not an implementation bug. Edge cases: binary-valued input (e.g. step functions normalizing to exactly 0/1) and series ending at the exact min-max boundary are out-of-distribution for the training data.
For architecture details, weight mapping, and debugging guidance, read references/architecture.md.
© oaustegard, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in forecasting-reverso of oaustegard/claude-skills.
- SKILL.md
- README.md
- references/architecture.md
- scripts/load_checkpoint.py
- scripts/reverso.py
Open the folder on GitHubat commit 90b0f1b
Compare with similar skills
Forecasting Reverso 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 |
|---|---|---|---|---|---|---|
| Forecasting Reverso this skilloaustegard/claude-skills | 150 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Senior Data ScientistRaidriar7170/hermes-skilleval | 125 | 5 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Quant Statistical MethodsHKUDS/Vibe-Trading | 35k | — | ~4k | Automated safety check: Pass | MIT | |
| TimesFM Forecastinggoogle-research/timesfm | 34k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| StatsmodelszLanqing/codex-claude-academic-skills | 4.7k | 15 repos | ~4.9k | Automated safety check: Pass | BSD-3-Clause | |
| Timesfm ForecastingzLanqing/codex-claude-academic-skills | 4.7k | 3 repos | ~7.5k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Quant Statistical Methods
HKUDS/Vibe-Trading
Guides your agent through unit-root, cointegration, GARCH, bootstrap and regression-diagnostic tests on financial time series, using a tested helper module.
TimesFM Forecasting
google-research/timesfm
Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.
Statsmodels
zLanqing/codex-claude-academic-skills
Statistical models library for Python. An agent skill from zLanqing/codex-claude-academic-skills.
Timesfm Forecasting
zLanqing/codex-claude-academic-skills
Zero-shot time series forecasting with Google's TimesFM foundation model.
Exploratory Data Analysis
Oleafly/Oleafly
Perform bounded, local exploratory analysis of explicitly supported scientific files.
More from oaustegard/claude-skills
All 67 skills in this repoVega-Lite Interactive Charts
oaustegard/claude-skills
Builds interactive Vega-Lite charts from uploaded data: analyzes the fields, picks five to ten fitting chart types, and produces a React artifact with the data embedded inline.
Single-File HTML Composer
oaustegard/claude-skills
Builds self-contained single-file HTML pages such as reports, decks, postmortems, flowcharts and prototypes from a small spec using a bundled Python composer and templates.
Deciding With Confidence
oaustegard/claude-skills
Routes, triages, flags and rates a piece of text with a probability for every option: which department or queue a ticket goes to, which intent a message expresses, whether a yes/no condition holds…
Declauding
oaustegard/claude-skills
Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.
Preact Developer
oaustegard/claude-skills
Guides building standards-based Preact apps with native-first choices, HTM syntax, import maps and vendored ESM, from single-file demos to larger builds.
Bluesky Zeitgeist Sampler
oaustegard/claude-skills
Deprecated sampler that captures short windows of the Bluesky firehose, clusters trending terms and builds an HTML report; replaced by the browsing-bluesky skill.
Related
Works with
Categories
Questions about Forecasting Reverso
What does Forecasting Reverso do?
Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference). Forecasting Reverso is an agent skill from oaustegard/claude-skills. Zero-shot univariate time series forecasting using the Reverso foundation model (NumPy/Numba CPU-only inference).
When should I use Forecasting Reverso?
Forecasting Reverso fits situations like: S provide time series data and request forecasts; tabular data with a temporal dimension needs future-value estimation.
How do I install Forecasting Reverso in Claude Code?
Run `npx skills add oaustegard/claude-skills --skill forecasting-reverso -a claude-code`. Or copy the skill folder (forecasting-reverso in oaustegard/claude-skills) into .claude/skills/forecasting-reverso in your project. Claude Code loads it when a task matches its description.
How do I install Forecasting Reverso in Codex?
Run `npx skills add oaustegard/claude-skills --skill forecasting-reverso -a codex`. Or copy the skill folder (forecasting-reverso in oaustegard/claude-skills) into .agents/skills/forecasting-reverso in your project. Codex loads it when a task matches its description.
Can I use Forecasting Reverso 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 oaustegard/claude-skills --skill forecasting-reverso -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/forecasting-reverso, .gemini/skills/forecasting-reverso, .github/skills/forecasting-reverso and .opencode/skills/forecasting-reverso in your project.
What does Forecasting Reverso need to run?
Going by SKILL.md and its folder, Forecasting Reverso needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.
Does Forecasting Reverso access the network?
SKILL.md names 1 domain. In commands or code: huggingface.co; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Forecasting Reverso 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Forecasting Reverso use?
Forecasting Reverso 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 Forecasting Reverso use?
About 1.5k tokens (SKILL.md is roughly 5.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.
What are the alternatives to Forecasting Reverso?
Skills that share tags, products or a category with Forecasting Reverso: Senior Data Scientist (Raidriar7170/hermes-skilleval, 125 stars), Quant Statistical Methods (HKUDS/Vibe-Trading, 35k stars), TimesFM Forecasting (google-research/timesfm, 34k stars) and Statsmodels (zLanqing/codex-claude-academic-skills, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Forecasting Reverso?
oaustegard (a GitHub user) maintains it in oaustegard/claude-skills, which has 150 GitHub stars. The repository holds 67 skills in this directory. The repository was last updated on October 9, 2026.
Source: oaustegard/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.