Run Train (RigorPilot)
Conservative execution of selected training commands — startup/short-run verification, kickoff, resume — with command/config/seed/log/checkpoint evidence in train_outputs/
- What
- Conservative execution of selected training commands — startup/short-run verification, kickoff, resume — with command/config/seed/log/checkpoint evidence in train_outputs/
- Cost
- Free
- Needs
- a deep-learning training setup with compute (GPU/accelerator time) and a pre-selected, runnable training command — the skill executes conservatively; it doesn't pick your training strategy.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the RigorPilot "Rigor Train" skill: conservative execution of a selected training command for deep-learning research repositories. It applies when the training command has already been selected and should be run conservatively — startup verification, short-run verification, full kickoff, or resume — with command, config, seed, log, checkpoint, status and metric evidence written to standardized `train_outputs/` (`SUMMARY.md`, `COMMANDS.md`, `LOG.md`, `SCIENTIFIC_CHANGELOG.md`, `COMPARABILITY_REPORT.md`, `status.json`). The boundaries are clear: it executes a selected training command and normalizes the resulting evidence; it does not choose the research goal on its own, does not own exploratory branching or speculative code adaptation, and records partial, blocked, resumed and kicked-off states explicitly while preserving reproducibility context (configs, seeds, checkpoints, logs, metrics, runtime assumptions). Not for environment setup, asset download, inference-only or evaluation-only execution, speculative exploration, multi-variant sweeps, or autonomous idea implementation. By @lllllllama, listed here with credit to its creator. Honest caveats: it burns real GPU time — budgets, timeouts and cost awareness are entirely your responsibility; the command must be selected before the skill runs, it won't pick your training strategy for you; checkpoint and log evidence is only as good as the repo's own instrumentation. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Run Train is a free RigorPilot skill for conservative execution of a selected training command in deep-learning research repositories. It covers startup verification, short-run verification, full kickoff, or resume, then writes command, config, seed, log, checkpoint, status, and metric evidence into a standardized outputs folder for consistent comparison across runs.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit fb3ccdfStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a deep-learning training setup with compute (GPU/accelerator time) and a pre-selected, runnable training command — the skill executes conservatively; it doesn't pick your training strategy. Install "Run Train (RigorPilot)" for me. The RigorPilot training skill: conservative execution of a selected training command (startup verification, short-run verification, kickoff, resume) with standardized command/config/seed/log/checkpoint evidence in train_outputs/. Repository: https://raw.githubusercontent.com/lllllllama/rigorpilot-skills/fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01/skills/run-train/SKILL.md Pinned version: install the code at commit fb3ccdf5aa64b1fa5b1d0463e666a8bc8bc26e01 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "rigorpilot-run-train". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- fb3ccdf · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.