菜单
Compact Codex-Scientist router for codexscientist-paper-reliability-verifier; use for its research stage while keeping Codex-native operations outside the plugin runtime.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | codexscientist-paper-reliability-verifier |
| description | Compact Codex-Scientist router for codexscientist-paper-reliability-verifier; use for its research stage while keeping Codex-native operations outside the plugin runtime. |
| version | 2.0.0 |
This active skill is intentionally compact. The historical long playbook was moved to references/legacy-playbook.md and is reference-only.
copilot; do not invent, improve, or expand ideas automatically unless the user or project manifest explicitly enables autonomous idea improvement.cs_* tools only when visible in the selected profile; prefer public families for root-bound research state, memory, artifacts, baselines, experiments, analysis, literature, paper, method/frontier, claim gates, checkpoint/resume, and compact evidence.cs_* tool calls.Use the relevant bounded MCP cs_* tools exposed by tools/list and cs_tool_schema for this stage. Hidden admin/debug CLI examples live only in docs/ADMIN_CLI.md.
CodexScientist/research.yaml and CodexScientist/summaries/context_pack.md when present.references/legacy-playbook.md and translate it to the current MCP cs_* tool surface.cs_* tools and keep ordinary code edits in Codex-native operations.references/legacy-playbook.md preserves the pre-upgrade detailed playbook for audit and migration. It may contain old names and long procedures. Treat it as source material, not executable instructions.
Write CodexScientist-aware implementation, experiment-roadmap, code-only, and formal-command plans with TDD and durable quest outputs.
Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.
Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.
Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.
Execute CodexScientist project experiment command documents with durable cs_* logging, manifest validation, and cautious baseline-gate handling.
Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.