Analyze Project (RigorPilot)
Read-only audit of deep-learning research repos — maps model structure, training/inference entrypoints, configs and insertion points, flags suspicious patterns as heuristics; modifies nothing, runs no heavy jobs
- What
- Read-only audit of deep-learning research repos — maps model structure, training/inference entrypoints, configs and insertion points, flags suspicious patterns as heuristics; modifies nothing, runs no heavy jobs
- Cost
- Free
- Needs
- none beyond a deep-learning repo to read — this skill is read-only (lightweight static inspection only); it modifies nothing and runs no heavy jobs.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — the RigorPilot "Rigor Analyze / Rigor Audit" skill: a read-only audit for deep-learning research repositories. It applies when you want to understand a repo before touching it — map model structure, training entrypoints, inference entrypoints, config relationships — or get conservative suggestions about likely insertion points and suspicious implementation patterns, explicitly without modifying code or running heavy jobs. The boundaries are strict: the skill is read-mostly, may run lightweight static inspection helpers, never patches repo code, never owns final reproduction outputs, and marks suspicious patterns as heuristics — not confirmed bugs. Output expectations are a small standardized set: `analysis_outputs/SUMMARY.md`, `analysis_outputs/RISKS.md`, `analysis_outputs/status.json`. By @lllllllama, listed here with credit to its creator. Honest caveats: deliberately lightweight — it won't execute training, run sweeps or fix anything (pair it with `safe-debug`, `run-train` or the explore skills for follow-through); suspicious patterns are flagged as possibilities, not verdicts, so a flagged pattern may be intentional design; clear fit matters — use it for repo understanding, not for literature summaries, environment setup or general research help. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Prerequisites: none beyond a deep-learning repo to read — this skill is read-only (lightweight static inspection only); it modifies nothing and runs no heavy jobs. Install "Analyze Project (RigorPilot)" for me. The RigorPilot read-only audit skill for deep-learning research repos: maps model structure, training/inference entrypoints, configs and insertion points, flags suspicious patterns as heuristics, with standardized analysis_outputs/ reports. Repository: https://github.com/lllllllama/rigorpilot-skills/blob/main/skills/analyze-project/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-analyze-project". 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.