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...

npx skills add https://github.com/lllllllama/rigorpilot-skills --skill explore-code

explore-code

Use this as the Rigor Improve implementation leaf skill. The installed slug remains explore-code for compatibility.

Use the shared operating principles in ../../references/agent-operating-principles.md; this skill should guide bounded candidate code work without over-prescribing implementation details.

When to apply

  • When the researcher explicitly authorizes exploratory code changes on an isolated branch or worktree.
  • When the task is source-anchored module transplant, backbone adaptation, LoRA or adapter insertion, or low-risk module combination.
  • When summary-level recording is sufficient and the result is a candidate, not a trusted conclusion.

When not to apply

  • When the request is for trusted baseline work, conservative debugging, or normal training execution.
  • When the user did not explicitly authorize exploratory modifications.
  • When the task is a broad refactor or a from-scratch idea implementation.

Clear boundaries

  • This skill owns exploratory code modifications only.
  • It must keep work isolated from the trusted baseline.
  • Use ai-research-explore instead when the task spans both current_research coordination and exploratory runs.
  • It may hand off execution to minimal-run-and-audit or run-train.
  • It should favor source-anchored copying and minimal adaptation over freeform rewrites.
  • It should record why a candidate change is meaningful, how to roll it back, and why it remains a candidate rather than a verified contribution.

Output expectations

  • explore_outputs/CHANGESET.md
  • explore_outputs/SCIENTIFIC_CHANGELOG.md
  • explore_outputs/COMPARABILITY_REPORT.md
  • explore_outputs/TOP_RUNS.md
  • explore_outputs/status.json

Notes

Use references/explore-policy.md, ../../references/research-rigor-principles.md, scripts/plan_code_changes.py, and scripts/write_outputs.py.

Mais skills de lllllllama

ai-research-explore
lllllllama
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding,...
researchdata-analysisapi
analyze-project
lllllllama
Habilidade somente leitura do Rigor Analyze / Rigor Audit para repositórios de pesquisa em deep learning. Use quando o usuário quiser ler e entender um repositório, inspecionar a estrutura do modelo e pontos de entrada de treinamento ou inferência, revisar configurações e pontos de inserção, ou sinalizar padrões de implementação suspeitos sem modificar código ou executar tarefas pesadas. Não use para execução ativa de comandos, refatoração ampla, adaptação especulativa de código ou correção automática de bugs.
developmentcode-reviewresearch
ai-research-reproduction
lllllllama
Orquestrador do modo de reprodução do RigorPilot para reprodução de repositórios de aprendizado profundo com foco em README. Use quando o usuário desejar um fluxo completo e de confiança mínima que primeiro leia o repositório, selecione o menor alvo de inferência ou avaliação documentado, coordene a ingestão, configuração, execução confiável, treinamento confiável opcional, análise opcional do repositório e resolução opcional de lacunas do artigo, aplique regras conservadoras de correção, registre evidências, suposições, desvios e pontos de decisão humana,...
researchdevelopmentdocument
minimal-run-and-audit
lllllllama
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
developmenttestingcode-review
env-and-assets-bootstrap
lllllllama
Habilidade de configuração rigorosa para reprodução de repositório de deep learning com foco em README. Use quando a tarefa for especificamente preparar um ambiente conservador baseado em conda, suposições de caminhos de checkpoint e dataset, dicas de localização de cache e notas de configuração antes de qualquer execução em um repositório documentado por README. Não use para varredura de repositório, orquestração completa, interpretação de artigo, relatório final de execução ou configuração genérica de ambiente que não esteja vinculada a um alvo de reprodução específico.
developmentdevops
explore-run
lllllllama
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as 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/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline...
researchdevelopmentdata-analysis
safe-debug
lllllllama
Habilidade de Debug Rigoroso / Auditoria Rigorosa para trabalhos de pesquisa em aprendizado profundo. Use quando o usuário colar um traceback, erro de terminal, CUDA OOM, falha ao carregar checkpoint, incompatibilidade de forma, sintoma de perda NaN ou falha de treinamento e quiser um diagnóstico conservador antes de qualquer correção, com correções de debug claramente separadas das contribuições de pesquisa. Não use para refatoração ampla, adaptação especulativa, correção exploratória automática ou familiarização geral com o repositório.
developmenttestingcode-review
paper-context-resolver
lllllllama
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or...
researchdocumentdata-analysis