Explore Run (RigorPilot)
Bounded exploratory runs — small-subset validation, short-cycle probes, batch sweeps, idle-GPU search — ranked by cost/success-rate/expected-gain with fair-comparison caveats
- What
- Bounded exploratory runs — small-subset validation, short-cycle probes, batch sweeps, idle-GPU search — ranked by cost/success-rate/expected-gain with fair-comparison caveats
- Cost
- Free
- Needs
- a deep-learning research setup with compute (GPU/accelerator time) for the runs — this skill plans and ranks exploratory runs; actual execution hands off to minimal-run-and-audit or run-train.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the RigorPilot "Rigor Improve / Rigor Explore" run leaf skill for bounded exploratory evidence in deep-learning research repositories. It plans exploratory execution only when the researcher explicitly authorizes it: small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials — with fair-comparison caveats and no-overclaim summaries in `explore_outputs/`. Candidate selection before execution weighs three factors — `cost`, `success_rate`, `expected_gain` — with conservative default weights (rebalanced only if the researcher provides `selection_weights`), budget pruning via `max_variants` and `max_short_cycle_runs`, and variant axes expressed through `variant_axes`, `subset_sizes` and `short_run_steps`; downstream ranking switches to real execution evidence, never stays purely heuristic. The skill owns planning and summary only — actual command execution hands off to `minimal-run-and-audit` or `run-train` — and it keeps experiment state isolated from the trusted baseline, preferring small-subset and short-cycle checks before heavier runs and labeling results as bounded evidence with explicit notes on when a comparison isn't directly fair. By @lllllllama, listed here with credit to its creator. Honest caveats: it ranks candidates, it doesn't certify success — ranking is heuristic until real execution evidence exists; real runs need real compute (GPU time, budgets) that you manage yourself; use `ai-research-explore` for end-to-end orchestration and `run-train` for trusted training execution. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: a deep-learning research setup with compute (GPU/accelerator time) for the runs — this skill plans and ranks exploratory runs; actual execution hands off to minimal-run-and-audit or run-train. Install "Explore Run (RigorPilot)" for me. The RigorPilot run leaf skill: bounded exploratory runs (small-subset validation, short-cycle probes, batch sweeps, idle-GPU search) ranked by cost/success-rate/expected-gain, with fair-comparison caveats and no-overclaim summaries in explore_outputs/. Repository: https://github.com/lllllllama/rigorpilot-skills/blob/main/skills/explore-run/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 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-explore-run". 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.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build 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 build before installing it.