analyst-research
installsforks
How to install analyst-research?
genli-ai/market-research-skills/analyst-research
$npx -y skills add genli-ai/market-research-skills --skill analyst-researchEnd-to-end research workflow skill for investment analysts and policy researchers. Three scope modes the user picks at trigger time — light (4-5 page decision memo, ~15 min, 0 charts), medium (12-15 page topic brief, ~1 h, 6-10 charts), heavy (flagship report 30-40 pages / 15k+ w
SKILL.md
| 1 | <!-- Bilingual skill: this SKILL.md is the English primary; the Chinese mirror is SKILL.zh.md. |
| 2 | Each references/*.md has a Chinese mirror references/*.zh.md (same content, two languages). |
| 3 | The .md files are authoritative for the agent; the .zh.md files are for human readers. --> |
| 4 | |
| 5 | # analyst-research · investment research workflow skill |
| 6 | |
| 7 | A field-validated AI-assisted research workflow for investment analysts and policy researchers, packaged as a reusable Claude skill. Built on the methodology that produced the Saudi Vision 2030 deep-dive (35 figures, 15k+ words). Three scope modes; user picks at trigger time. |
| 8 | |
| 9 | > **License**: MIT. Copyright © 2026 Ligen <ligen.thu@gmail.com>. See `LICENSE`. |
| 10 | |
| 11 | ## Step 0 — pick a mode (REQUIRED before loading references) |
| 12 | |
| 13 | When this skill is triggered, **before** loading any reference file, ask the user to pick a scope. Present these three options verbatim: |
| 14 | |
| 15 | ``` |
| 16 | This skill has three scope modes. Pick one based on your project size: |
| 17 | |
| 18 | light 4-5 page decision memo, 0 charts, ~15 min budget |
| 19 | Single LLM session. Pure markdown footnote citations. |
| 20 | Use for: exec brief, internal memo, quick decision support. |
| 21 | |
| 22 | medium 12-15 page topic analysis, 6-10 charts, ~1 h budget |
| 23 | Single LLM. PDF + Word derivations. Sign-off checkpoint after draft. |
| 24 | Use for: topic deep-dive, board memo with data, same-day analysis. |
| 25 | |
| 26 | heavy Flagship report 30-40 pages / 15k+ words, 25-35+ charts, ~2-3 h budget |
| 27 | Single or multi-LLM. PDF + Word + WeChat md + HTML publication. |
| 28 | Runs the full 11-step staged workflow (framing → sourcing → |
| 29 | analysis → drafting → review), with 3 sign-off checkpoints. |
| 30 | Use for: industry deep-dive, macro thesis, policy assessment, |
| 31 | flagship investor publication. |
| 32 | |
| 33 | Which mode fits your project? (reply with light, medium, or heavy) |
| 34 | ``` |
| 35 | |
| 36 | If the user's trigger message already contains explicit scope hints (page count, chart count, time budget), infer the mode and ask one-line confirmation instead of presenting the full menu: |
| 37 | |
| 38 | > "Sounds like ~10 pages with a few charts — medium mode. Going with that?" |
| 39 | |
| 40 | After the mode is confirmed, ask one short language question: **"Report language — English (default), or another language?"** (see Language policy below). Then load the reference files for that mode. |
| 41 | |
| 42 | ## Loading order per mode |
| 43 | |
| 44 | First **always** read `references/workflow.md` (≈40 lines, mode router). It points you to the mode-specific workflow file. (Each reference also has a `.zh.md` Chinese mirror; the agent reads the English `.md`.) |
| 45 | |
| 46 | ### light mode |
| 47 | |
| 48 | 1. **Required** `references/workflow.md` — overview + mode router |
| 49 | 2. **Required** `references/workflow_light.md` — 6-step skeleton, soft stops only, BLUF executive summary, grep self-check |
| 50 | 3. **Required** `references/_quarto-light.yml` — Quarto template optimized for a 4-5 page memo (no TOC, no number sections, footnote citations, 11pt body) |
| 51 | 4. No charts. No bibliography. No HTML/WeChat derivation. Skip `report_style_spec.md` and `chart_template.py`. |
| 52 | |
| 53 | Then proceed to `workflow_light.md §1 hypothesis lock` to start the 6-step flow. |
| 54 | |
| 55 | ### medium mode |
| 56 | |
| 57 | 1. **Required** `references/workflow.md` — overview + mode router |
| 58 | 2. **Required** `references/workflow_medium.md` — 8-step skeleton, single LLM, one sign-off checkpoint after draft |
| 59 | 3. **Required** `references/report_style_spec.md` — visual spec for the 6-10 charts (chart_template interface contract, color palette, font policy) |
| 60 | 4. **Required** `references/_quarto-medium.yml` — Quarto template (footnote citations, no .bib, 11pt body, Songti SC CJK) |
| 61 | 5. **On demand** `scripts/chart_template.py` — chart styling implementation |
| 62 | |
| 63 | Then proceed to `workflow_medium.md §1 onboarding` to scaffold the project and start. |
| 64 | |
| 65 | ### heavy mode |
| 66 | |
| 67 | 1. **Required** `references/workflow.md` — overview + mode router |
| 68 | 2. **Required** `references/workflow_heavy.md` — full 11-step skeleton, multi-LLM optional, 3 sign-off checkpoints (outline / draft / final) |
| 69 | 3. **Required** `references/report_style_spe |
People who liked this also viewed
6 picksType
- grill-with-docsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.SkillsJul 2026
- lark-minutes飞书妙记：搜索妙记、查看妙记基础信息、下载/上传音视频、读取或编辑妙记的产物内容、改标题、替换说话人/关键词、申请妙记查看/编辑权限。当给出minute_token、本地音视频文件，要查/改/转妙记产物，或用户明确要主动申请妙记权限时使用；本地音视频转纪要/逐字稿优先走本 skill，不要用 ffmpeg/whisper 本地转写。不负责：获取会议关联妙记，或仅按自然语言标题定位纪要SkillsJul 2026
- lark-markdown飞书 Markdown：查看、创建、上传、编辑和比较 Markdown 文件。当用户需要创建或编辑 Markdown 文件、读取、修改、局部 patch 或比较差异时使用。不负责将 Markdown 导入为飞书在线文档，也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。SkillsJul 2026
- docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', SkillsJul 2026
- edit-articleSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- lark-note飞书会议纪要（Note）直查：已知 note_id 时查询纪要详情、展示类型、关联文档 token，并读取 unified 原始逐字记录。当用户已持有 note_id，或从文档显式 vc-node-id 获得 note_id 时使用。不负责会议/日程/妙记定位、文档标题搜索或 Docx 正文读取。SkillsJul 2026
