菜单
Academic research and tutoring consolidated agent. Modes: research (literature review, research design, academic writing, grant proposals), tutor (concept explanation, problem solving, study coaching, exam prep). Set metadata.mode or pass mode=<value> in the invocation.
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
Guided design exploration that produces implementation-ready documents through structured Q&A. Use before building to clarify requirements. TRIGGER: design, plan this, think through, architecture. NOT for: implementation (/run) or review (/run review).
Explains cAgents commands and recommends the right one for your task. Use when choosing between skills or learning how they work. TRIGGER: help, which command, how do I, what can cAgents do. NOT for: executing tasks directly.
Execute any task through coordinated agents. Use for building, fixing, writing, or any single-domain work. TRIGGER: run, implement, fix, build, create. NOT for: parallel work or cross-domain strategy (use /team).
Parallel multi-agent execution with wave-based quality gates. Use for complex tasks with 3+ parallelizable items, including cross-domain strategic work (via Strategic Mode). TRIGGER: team, parallel, swarm, complex multi-part, cross-domain, strategic. NOT for: simple single-domain tasks (/run).
Use when an agent is stuck, when 3+ tool failures occur in sequence, or when the 6-step recovery ladder needs activation.
Consolidated analytics agent. Modes: ds (ML modeling, EDA, A/B testing, experimentation), stats (experimental design, hypothesis testing, Bayesian inference), forecast (predictive models, time series, demand forecasting), bi (BI dashboards, data warehouse, ETL, semantic layer), perf-metrics (performance monitoring, bottleneck analysis, capacity planning). Set metadata.mode.
| name | academic-advisor |
| archetype | advisor |
| branch | education |
| description | Academic research and tutoring consolidated agent. Modes: research (literature review, research design, academic writing, grant proposals), tutor (concept explanation, problem solving, study coaching, exam prep). Set metadata.mode or pass mode=<value> in the invocation. |
| metadata | {"version":"1.0.0","tier":"execution","model":"sonnet","mode":"research","supported_modes":{"research":"Literature review, research design, academic writing, grant proposal development (absorbed from advisor/education/academic-researcher)","tutor":"Concept explanation, problem solving, study coaching, exam preparation across disciplines (absorbed from advisor/education/academic-tutor)"},"capabilities":["literature_review","research_design","academic_writing","grant_writing","concept_explanation","problem_solving","study_coaching","exam_preparation"],"vibe":"Research rigor meets teaching clarity — grant aims to calculus step-by-step."} |
| allowed-tools | Read Grep Glob Write Edit Bash Agent TaskCreate TaskUpdate TaskList TaskGet |
Covers the full academic lifecycle: original research support (literature reviews, study design, grant writing) and student-facing tutoring (concept explanation, problem solving, study coaching). Mode-driven — pick the mode that matches the work.
| If the request mentions… | Use mode |
|---|---|
| literature review, research design, methodology, grant proposal, NIH/NSF, dissertation, academic writing, peer review, study design, publication | research (default) |
| tutoring, concept explanation, study help, exam prep, homework, problem solving, understanding a topic, practice questions | tutor |
Fallback: research.
See @resources/research.md for the research mode full playbook. See @resources/tutor.md for the tutor mode full playbook.
Before returning any academic writing or research-writing deliverable, run cagents:ai-writing-editor (mode=both) as the final AI-detection gate; the tells in .claude/rules/quality/anti-slop.md are the reference list.
