skills
Marketplace

lllllllama/rigorpilot-skills

explore-code

Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.

All-time installs310.6KObserved Sep 16, 2026
Trending · 24hNo observation in this view
Hot · last hourNo observation in this view

What you’re adding

This skill may reference tools or services you need to set up separately. The package check shows the exact files; it does not install dependencies or run scripts.

5 files in the provider snapshot
  • agents/openai.yaml326 B
  • references/explore-policy.md652 B
  • scripts/plan_code_changes.py14.5K B
  • scripts/write_outputs.py1,186 B
  • SKILL.md2,592 B

Snapshot inspected Sep 14, 2026. Adding uses a fresh GitHub revision and checks it separately.

Your vault, your checks

  1. 01
    Inspect the source

    Review the exact revision, files and available capacity.

  2. 02
    Save a private Draft

    Run your vault’s security scan and complete any required review.

  3. 03
    Use the approved version

    Make it available through your existing agent connection.

Observed activity

All-time installs reported by skills.sh. Daily observations start when this catalog is first synchronized.

DateInstallsRank
Sep 9, 2026310,622#179
Sep 10, 2026310,624#179
Sep 11, 2026310,627#179
Sep 13, 2026310,633#179
Sep 14, 2026310,639#179
Sep 15, 2026310,641#179
Sep 16, 2026310,645#182