tsf-run
Streamlines running TSF paperkit experiments and ablations via CLI automation.
Install
mkdir -p .claude/skills/tsf-run && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12595" && unzip -o skill.zip -d .claude/skills/tsf-run && rm skill.zipInstalls to .claude/skills/tsf-run
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when the user wants to create, validate, run, or ablate tsf-paperkit experiment configs from natural-language intent.Key capabilities
- →Inspect or create a YAML config under `configs/`.
- →Prefer toy/smoke settings for experiments.
- →Run `python -m tsf_paperkit.cli run --config <config>`.
- →Run `python -m tsf_paperkit.cli ablate --config <config>` for ablations.
- →Report output directory, resolved config, results CSV, and actionable failures.
How it works
The skill translates natural language intent into `tsf-paperkit` experiment configurations, runs the experiments, and reports the results.
Inputs & outputs
When to use tsf-run
- →Running a smoke test experiment
- →Ablating configuration parameters
- →Validating experiment config files
About this skill
tsf-run
Goal: turn user intent into small reproducible TSF runs.
Workflow:
- Inspect or create a YAML config under
configs/. - Prefer toy/smoke settings unless the user explicitly requests larger runs.
- Run
python -m tsf_paperkit.cli run --config <config>. - For ablations, run
python -m tsf_paperkit.cli ablate --config <config>. - Report output directory, resolved config, results CSV, and any actionable failure.
Rules:
- Do not silently change experiment settings; record resolved config.
- Do not claim toy/smoke results are benchmark results.
When not to use it
- →When the user wants to run experiments outside of `tsf-paperkit`.
- →When the user wants to perform benchmark runs with toy/smoke settings.
Limitations
- →The skill is specific to `tsf-paperkit` experiment configs.
- →The skill does not silently change experiment settings.
- →The skill does not claim toy/smoke results are benchmark results.
How it compares
This skill automates the creation, validation, and execution of `tsf-paperkit` experiments from natural language, unlike manually configuring and running experiments.
Compared to similar skills
tsf-run side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| tsf-run (this skill) | 0 | 2mo | No flags | Intermediate |
| robotics-code-generator | 14 | 7mo | No flags | Advanced |
| modal | 5 | 7mo | Review | Intermediate |
| hugging-face-cli | 3 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
robotics-code-generator
HumaizaNaz
Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics
modal
davila7
Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.
hugging-face-cli
patchy631
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.
computer-use-agents
davila7
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
machine-learning-ops-ml-pipeline
sickn33
Design and implement a complete ML pipeline for: $ARGUMENTS
ray-train
davila7
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.