Timesfm Forecasting

What it does

When your agent uses it

• Tasks that involve Forecasting and time series

Example prompts

• “Use the timesfm-forecasting skill to perform zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation…”
• “/timesfm-forecasting”

Requirements

• Python 3
• A Bash shell
• Compatibility (from SKILL.md): Requires Python 3.10+ and timesfm 3.0.2 with PyTorch; CSV tooling also needs NumPy and pandas. Network access and cache space are needed for initial Hugging Face checkpoint download. Optional XReg needs JAX and scikit-learn; current JAX requires Python 3.12+.
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash

Workflow steps

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

1. 1Establish cadence, units, forecast origin, horizon, known-at-origin covariates,
2. 2Validate a sorted, unique, regular time grid. Do not dropna() internal gaps
3. 3Run python scripts/check_system.py before downloading/loading weights.
4. 4Load the chosen checkpoint with a recorded immutable revision. For 2.5,
5. 5Forecast, validate shapes/finite values/quantile ordering and export the
6. 6Evaluate across rolling origins with preprocessing fitted independently per

What it can do on your machine

Read from SKILL.md and the folder at commit 92ace75. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/ (Python and Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python
  • uv

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

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • huggingface.co
  • pytorch.org
  • pypi.org

  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.

• Compatibility

  Requires Python 3.10+ and timesfm 3.0.2 with PyTorch; CSV tooling also needs NumPy and pandas. Network access and cache space are needed for initial Hugging Face checkpoint download. Optional XReg needs JAX and scikit-learn; current JAX requires Python 3.12+.

  From compatibility in the SKILL.md frontmatter.

Context cost

Timesfm Forecasting loads about 2.4k tokens when it runs, and up to ~9.2k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 822 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~84

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~9.2k

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

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash

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 K-Dense-AI/scientific-agent-skills at commit 92ace75, republished under its Apache-2.0 licence (© K-Dense-AI). 822 words, ~2,380 tokens.

name

timesfm-forecasting

description

Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and held-out evaluation. Uses the Apache-licensed TimesFM 2.5 checkpoint by default and documents the distinct TimesFM 3.0 multivariate API and weight-license requirements.

allowed-tools

Read, Write, Edit, Bash

compatibility

Requires Python 3.10+ and timesfm 3.0.2 with PyTorch; CSV tooling also needs NumPy and pandas. Network access and cache space are needed for initial Hugging Face checkpoint download. Optional XReg needs JAX and scikit-learn; current JAX requires Python 3.12+.

license

Apache-2.0 license

metadata.version

3.0

metadata.skill-author

Clayton Young / Superior Byte Works, LLC (@borealBytes)

metadata.last-reviewed

2026-10-01

metadata.tested-package

timesfm 3.0.2

uv venv .venv-timesfm
uv pip install --python .venv-timesfm/bin/python "timesfm[torch]==3.0.2" numpy pandas
.venv-timesfm/bin/python scripts/check_system.py

from importlib.metadata import version
import timesfm
print(version("timesfm"))  # package has no guaranteed timesfm.__version__
assert hasattr(timesfm, "TimesFM_2p5_200M_torch")

import numpy as np
import timesfm

model = timesfm.TimesFM_2p5_200M_torch.from_pretrained(
    "google/timesfm-2.5-200m-pytorch",
    revision="1d952420fba87f3c6dee4f240de0f1a0fbc790e3",
    torch_compile=False,  # avoid compilation startup during an initial smoke run
)
model.compile(timesfm.ForecastConfig(
    max_context=512, max_horizon=128, per_core_batch_size=1,
    normalize_inputs=True, use_continuous_quantile_head=True,
    force_flip_invariance=True, infer_is_positive=False,
    fix_quantile_crossing=True,
))
histories = [np.sin(np.linspace(0, 20, 200)).astype(np.float32)]
# 2.5 may append dummy series to its input list during batching; pass a fresh list.
point, q = model.forecast(horizon=24, inputs=list(histories))
assert point.shape == (1, 24) and q.shape == (1, 24, 10)
assert np.isfinite(q).all() and np.all(np.diff(q[..., 1:], axis=-1) >= 0)
assert np.allclose(point, q[..., 5])
lower_80, upper_80 = q[..., 1], q[..., 9]  # q10-q90: nominal 80% PI
lower_60, upper_60 = q[..., 2], q[..., 8]  # q20-q80: nominal 60% PI

python scripts/forecast_csv.py monthly_sales.csv \
  --date-col date --freq MS --value-cols sales,revenue \
  --horizon 12 --batch-size 1 --nonnegative --output forecasts.csv

© K-Dense-AI, Apache-2.0. 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 21 other files (scripts, references) in skills/timesfm-forecasting of K-Dense-AI/scientific-agent-skills.

• SKILL.md
• examples/anomaly-detection/detect_anomalies.py
• examples/covariates-forecasting/demo_covariates.py
• examples/global-temperature/README.md
• examples/global-temperature/generate_animation_data.py
• examples/global-temperature/generate_gif.py
• examples/global-temperature/generate_html.py
• examples/global-temperature/run_example.sh
• examples/global-temperature/run_forecast.py
• examples/global-temperature/temperature_anomaly.csv
• examples/global-temperature/visualize_forecast.py
• references/api_reference.md
• references/data_preparation.md
• references/examples_and_validation.md
• references/output_and_config.md
• references/performance_tuning.md
• … and 6 more

Open the folder on GitHubat commit 92ace75

Used in 1 other repository

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 K-Dense-AI/scientific-agent-skills, which our catalogue first saw on October 7, 2026.

• lingxling/awesome-skills-cnclaude-scientific-skills/skills/timesfm-forecasting