Loading...
Loading...
Found 163 Skills
Diagnose surprising, negative, unstable, or ambiguous ML/AI experiment results and decide whether to debug implementation, rerun experiments, change metrics or baselines, revise the algorithm, narrow the paper claim, park, or kill a direction. Use this skill whenever results do not match expectations, a method fails, metrics conflict, seeds vary, baselines beat the method, plots look suspicious, or the user asks what to do next after experimental results.
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during execution — to maintain a faithful, auditable trace of how a research project actually evolved.
Plan, draft, and revise ML/AI limitations, scope, failure cases, ethics, broader impact, and conclusion caveats so they control claim boundaries without undermining the paper. Use when the user wants limitation wording, scope statements, failure-case interpretation, ethics/broader-impact text, or overclaim reduction.
Read research outline, launch independent agent for each item for deep research. Disable task output.
Add items (research objects) to existing research outline.
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
Codex-native Academic Research Skills suite for deep research, academic paper writing, manuscript review, full research-to-paper pipelines, and experiment planning or validation. Use when the user asks for deep research, literature review, systematic review, meta-analysis, research question refinement, academic paper drafting, paper revision, citation or integrity checks, reviewer simulation, peer review, editorial decision letters, research-to-paper workflows, experiment execution planning, statistical interpretation, or human study protocol support. Also use for Claude-style ARS command aliases such as /ars-plan, ars-plan, /ars-outline, /ars-abstract, /ars-lit-review, /ars-citation-check, /ars-disclosure, /ars-format-convert, /ars-revision-coach, /ars-revision, and /ars-full. This skill vendors ARS role prompts, references, templates, and shared handoff schemas under ars/.
Use when inspecting, cleaning, understanding, reproducing, or auditing academic research code repositories, especially when README commands, datasets, checkpoints, experiments, or paper claims need verification.
Use when verifying citations, bibliography, manuscript claims, source support, factual accuracy, numerical results, citation drift, or evidence provenance in academic work.
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic applications.
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
Generate academic research proposals for PhD applications. Use when user asks to "write a research proposal", "create PhD proposal", "generate research plan", "撰写研究计划", "写博士申请", "doctoral proposal", or mentions specific research topics for PhD application. Supports STEM, humanities, and social sciences with field-specific adaptations. Follows Nature Reviews-style academic writing conventions. Supports both English and Chinese output based on user preference.