zi-yue-1129
- 10 skills
- 0 followers
- 1 day ago last updated
- ▌ Agent State · zi-yue-1129 bundleRecords what the agent does as it drives other skills -- Questions worked on, Runs executed, Results produced, Claims asserted -- in .research/state (canonical, low-frequency) and .research/events (canonical, append-only). Also models the research itself as Project/Hypothesis/Experiment/Source/Evidence, layered above Question/Run, with write-time referential integrity checks. Use when a skill wants to track its own execution history instead of writing one file per run, or when a user wants to see what the agent has been doing. Triggers on phrases like "what have you been running", "log this run", "show agent activity".
- ▌ Research Log · zi-yue-1129 bundleRecord, manage, and query research experiment logs. Use when the user wants to log an experiment result, amend an existing entry, view recent logs, rebuild the index, or plan, execute, repeat, or diagnose research in a project containing docs/research_log/. Triggers on phrases like "log this experiment", "record results", "add a log entry", "show recent experiments", "amend log", "try this method", "change these experiment parameters", and "why did this run fail?". Each entry creates a structured Markdown file in docs/research_log/. Suggest running this before /report-slides when new results have not been logged yet.
- ▌ Deep Research · zi-yue-1129 bundleUniversal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.
- ▌ Report Slides · zi-yue-1129 bundleUse when creating presentations and research reports, especially diagram-heavy decks with architecture, flowcharts, timelines, charts, conceptual illustrations, or editable PPTX output.
- ▌ Research Mode · zi-yue-1129 bundleWork mode dispatcher for research workflows. 5 modes: exp (running experiments), daily (reading/notes), explore (deep-research exploration), report (slide generation), publish (academic-pipeline). Commands: /mode exp|daily|explore|report|publish|status|end. All output in English. Triggers: /mode, switch mode, start experiment, begin research session, mode status, end session.
- ▌ Academic Paper · zi-yue-1129 bundle12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.
- ▌ Academic Pipeline · zi-yue-1129 bundleOrchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.
- ▌ Resource Resolver · zi-yue-1129 bundleMaps logical resource roles (research log, experiment config, results, slides, paper, bibliography) to actual project paths, without assuming any folder naming convention. Use when a skill needs to know where to read or write a project resource, or when the user wants to set up or change where these resources live. Triggers on phrases like "set up my workspace", "where should slides go", "change the research log location", "resolve workspace".
- ▌ Research Project Init · zi-yue-1129 bundleTurn a preliminary research idea into a scoped, reviewable, trackable project. Runs a lightweight guided dialogue covering problem statement, scope, exclusions, expected contributions, initial research questions, constraints, resources, milestones, success criteria, stop conditions, risks, and ethics considerations -- tagging every captured item as confirmed, assumption, suggestion, or open. Writes a project charter to .research/projects/<project_id>/charter.md and registers a Project plus its initial Questions in agent-state. Does not perform literature research or run experiments -- deep-research remains the place a research question gets sharpened. Use when the user has a rough idea and wants to formalize it into a project before research begins. Trigger directly with /research-init, or natural-language phrases like "start a new research project", "formalize this idea", "define project scope", "scope out this project", "建立研究專案", "把這個構想變成正式專案", "幫我把研究範圍定義清楚".
- ▌ Academic Paper Reviewer · zi-yue-1129 bundleMulti-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.