Runs deep learning research repositories from their README with bounded execution and auditable evidence, covering setup, analysis, reproduction and candidate exploration. Candidate exploration needs explicit authorization.
Claude Code
$ npx -y skills add lllllllama/rigorpilot-skills --agent claude-code
Codex
$ npx skills add lllllllama/rigorpilot-skills -a codex
Cursor
$ npx skills add lllllllama/rigorpilot-skills -a cursor
Gemini CLI
$ npx skills add lllllllama/rigorpilot-skills -a gemini-cli
GitHub Copilot
$ npx skills add lllllllama/rigorpilot-skills -a github-copilot
OpenCode
$ npx skills add lllllllama/rigorpilot-skills -a opencode
Windsurf
$ npx skills add lllllllama/rigorpilot-skills -a windsurf
Run research repositories from their README, with bounded execution and auditable evidence. RigorPilot adds section-level results without rewriting the original README. Trusted reproduction is the default; candidate exploration requires explicit authorization.
Real examples · Install & use · Skill index · Validation · Engineering roadmap
Original commands, prose, badges, images, videos and HTML stay in the source file. RigorPilot splits that file into sections and inserts one evidence-linked card per section. Removing its insertion blocks restores the retained original README byte for byte.
Each card below opens a full annotated README beside the original README in a retained repository checkout. Supporting repository files are kept so relative links and media retain their original context.
🟢 selected checks passed · 🔵 not executed · ⚪ read only · 🟡 partial · 🔴 blocked · 🟣 decision needed. Green does not automatically mean paper-result reproduction; blue is not an execution failure.
micrograd · correctness checks 🟢 2 tests passed in 7.62 s8 headings = 8 annotations · original bytes preserved Open full RigorPilot README →
minGPT · selection boundary 🔵 Test selected, not executed · no model download11 headings = 11 annotations · original bytes preserved Open full RigorPilot README →
PyTorch MNIST · bounded startup 🟡 Partial training · observed loss 0.0388931 heading = 1 annotation · original bytes preserved Open full RigorPilot README →
nanoGPT Shakespeare · bounded training 🟡 Partial · train loss 4.1676 · validation loss 4.164911 headings = 11 annotations · original bytes preserved Open full RigorPilot README →
All four cases and upstream links · Recorded suite · Case definitions · Methodology
These are historical, commit-pinned deterministic runs: 4/4 case protocols
passed in 251.0 s, with a peak workspace of 98.67 MiB and 0 model API calls.
The zero-API count applies only to that suite. Selection-only and partial cases
are not completed evaluations, converged training or reproduced paper scores.
New: installed-skill micrograd trial, with before/after command reports, a retained failed attempt and independent checks—not a model-quality comparison.
Current acceptance: explicit named-skill and fresh-client natural-language AUTO both pass end to end; earlier failures remain retained and A/B/model uplift remain unrun. Compact status · real-client evidence
The installer needs Node.js/npm. Tested with skills@1.5.26 and Node 22.20.0;
that installer requires Node ≥22.20.0. If you see EBADENGINE, check the requested version.
Install the self-contained reproduction skill:
npx skills add lllllllama/RigorPilot-Skills --skill ai-research-reproduction
Install all skills for the companion research entrypoints:
npx skills add lllllllama/RigorPilot-Skills --all
These commands use the current GitHub repository name.
Open the target repository in a Skills-capable agent, then ask:
Use ai-research-reproduction: run the smallest README-documented evaluation, preserve the source and write evidence to repro_outputs/, plus an annotated copy beside the original README. Ask before large downloads or long training.
The main skill works alone; choose all skills for companion and leaf entrypoints. Your existing agent loads the skill. The standalone model runner is optional. Client compatibility
Recommended first run:
| Step | What it does | What it does not do |
|---|---|---|
| Plan | Lists README-backed cmd-XX candidates, selects the smallest trusted target, and returns a selection fingerprint | No target execution, installs, downloads, source edits or evidence writes |
| Run | Executes a reviewed command-id bound to that plan fingerprint and writes evidence under the target repo by default | Setup/download commands cannot be selected; a changed plan fails before target execution |
| Verify | Rechecks the retained evidence, README round trip, runtime state and current source snapshot | Does not rerun the target command |
Start with the RIGORPILOT_README.md reported in source_adjacent_readme.path,
then follow its command and log links. If a conflicting file blocks the extra
copy, that file stays intact; inspect repro_outputs/SUMMARY.md for the outcome
and next action.
README → documented target → reviewed setup → bounded execution → verification → evidence.
This is local execution, not an OS sandbox. Approved commands can access the host and network; use trusted repositories. Resource admission and between-action budget checks are not hard OS quotas or subscription-balance monitoring.
The optional model loop currently supports Anthropic Messages and reviewed command IDs, not unrestricted source repair. This standalone runner has no successful live-model acceptance recorded yet: three provider attempts returned HTTP 502. Other model profiles are metadata, not proof of working transports or equivalent model performance. Runner and recovery contract · Implementation evidence and limits
| Task | Skill |
|---|---|
| Reproduce from README commands | ai-research-reproduction |
| Read-only repository analysis | analyze-project |
| Prepare environment, data and weights | env-and-assets-bootstrap |
| Run documented inference or evaluation | minimal-run-and-audit |
| Start or verify training conservatively | run-train |
| Diagnose before proposing a patch | safe-debug |
| Coordinate authorized candidate exploration | ai-research-explore |
| Implement a candidate change on an isolated branch | explore-code |
| Execute a bounded candidate experiment | explore-run |
Two helpers support orchestration: repo-intake-and-plan and paper-context-resolver.
Exploration requires a durable current_research anchor and a frozen comparison
contract. Candidate results never become trusted baseline results by declaration.
Routing · Research loop ·
Campaign inputs
| Artifact | What to inspect |
|---|---|
repro_outputs/ANNOTATED_README.md | Original README with inserted section verdicts |
SUMMARY.md, COMMANDS.md, LOG.md, status.json | Outcome, exact commands, reviewed selection provenance, stable error.code, observations and machine-readable status |
invocation.json, evidence_manifest.json | Invocation/source-integrity summary plus retained file sizes and SHA-256 hashes for local consistency checks |
PATCHES.md, SCIENTIFIC_CHANGELOG.md, COMPARABILITY_REPORT.md | Changes, scientific meaning and comparison boundaries |
_runtime/<run_id>/ | Process state, events, resource samples and stdout/stderr |
.repro_job/ | Optional short-call supervisor: frozen request, reusable receipt, phase logs and completion-time verification |
Stars on GitHub
View @lllllllama’s profileRuns deep learning research repositories from their README with bounded execution and auditable evidence. Also offers analysis, environment setup, and optional exploratory code changes, which need explicit authorization.
@lllllllamaA development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookInstall it with the command on its page. It includes ai-research-explore, ai-research-reproduction, analyze-project. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it