Comunidad Guías…

Ayuda y problemas de academic-research-skills

Pregunta a la comunidad o invita a KiBot con contexto del repositorio.

Publicar un problema

No publiques contraseñas, tokens ni claves privadas. HostingByte aplica una redacción básica de secretos evidentes antes de guardar el texto.

Problemas en HostingByte

Todavía no hay problemas publicados.

Issues abiertas upstream

#1068 citation_compliance_agent: Corrected Draft is still unconditional outside the Phase Boundary block; revision mode undefined · 1 comentarios #1025 Windows: prefer a Python outside WindowsApps so the guard launcher does not start the Install Manager alias at all (follow-up to #1015) · 7 comentarios #1001 Reviewer-recommended references: verify through the existing resolver clients before they reach the decision letter (paper-derived: King & Worthington 2026) · 2 comentarios #993 draft_writer infers a cited source's contribution from its title and method when Key Findings are missing · 1 comentarios #582 Calibrate reviewer and research role count against a matched solo baseline · 1 comentarios #996 Support Perplexity AI · 3 comentarios #991 Socratic exploratory mode: three unscoped rules still auto-advance, auto-end, or use the prohibited closing phrase · 0 comentarios #830 [Gartenberg sub A] Deterministic writing-surface measurement (readability, nominalization, jargon, hedging) as an advisory on drafts and reviewer outputs · 2 comentarios #742 Define research-family workflow profiles and progressive-disclosure usability gates · 2 comentarios #960 Routing fixture 16: Claude Opus 5.5 asks which deliverable on a plugin install instead of entering lit-review mode · 0 comentarios #879 Gemini/Antigravity support? · 6 comentarios #954 ARS scope guard rejects Copilot apply_patch: expects top-level file_path · 1 comentarios #907 Committee-correspondence follow-ups from #854: scope by determination, grade a false committee claim · 0 comentarios #892 Routing discipline lives only in .claude/CLAUDE.md, which plugin and skills-copy installs do not load (static finding) · 0 comentarios #675 Security evaluation: measure indirect prompt-injection behavior on retrieved-content surfaces · 1 comentarios #653 Reviewer calibration: reproducible public-corpus manifest and first measured error profile · 2 comentarios