| name | article-research |
| description | First-party topic selection, research, and evidence sourcing for the article factory. Use to turn any material/topic into a vetted topic with a one-page brief and a primary-source evidence ledger — self-sufficient, no external SEO pack required. 选题/挖词/内容缺口/research/topic/keyword/intent/evidence/证据台账 |
| version | 1.0.0 |
| license | Apache-2.0 |
| homepage | https://github.com/weitzu-com/ai-article-factory |
| when_to_use | Use at the start of a piece (pipeline P1–P2) when the user gives a topic, product, or pile of materials and needs: a chosen topic with a defensible angle, a topic brief (intent + ICP + keywords + AI-query terms + competitive gap + one-line differentiator), and an evidence ledger where every checkable claim has a primary source + exact locator. Also when the user says 选题 / 挖词 / 找证据 / research the topic / find keywords / what should I write / classify intent / build evidence. |
| argument-hint | <topic | product | materials path> |
| metadata | {"author":"weitzu-com","tags":["research","topic-selection","keyword","search-intent","serp","content-gap","evidence","claim-ledger","geo","first-party"]} |
Article Research
You select the topic and assemble the evidence before a single sentence is written. This is the factory's intake stage (P1 topic → P2 evidence ledger): it takes any material/topic/product and outputs (a) one chosen topic with a defensible angle, (b) a topic brief, and (c) a claim-ready evidence ledger. It is self-sufficient — built-in web search/fetch plus the user's own materials are enough; no keyword-tool export, no external SEO skill pack.
First principles
- Pick the topic you can prove, not the topic with the most volume. The best topic is where you hold (or can find) first-party evidence competitors lack — that is the only durable edge for both SEO long-tail and AI citation.
- Evidence before sentences. Every checkable claim (number, definition, standard, causal link, comparison) earns a ledger row with a primary source + exact locator before it can be written. No row → no claim.
- Every angle reduces to one differentiating sentence. If you can't state in one line why this beats the top 3 results, the topic isn't ready.
- Competitor blogs are signals, never authority. Read them to find gaps; cite the primary source they (should have) used.
- Degrade loudly, never silently. If the web is unavailable, say so and mark every affected claim
[unverified] — never invent a source.
Inputs
- A topic / seed keyword, or a product, or a materials path (folder/files/URLs). Any one is enough.
- Optional: target market/language, ICP, domain. If absent, infer from the input, echo back in one line, and proceed (silence = continue). Never make the user fill a form.
Output (write into the article folder)
01-选题brief.md — the topic brief (template below).02-证据台账.md — the evidence ledger (discipline in references/evidence-ledger.md).
Both feed P3 angle / P4 outline / P5 draft directly. Drafting must cite ledger rows as [C#].
Workflow
Step 1 — Scope & seed (1 line back to the user)
Name the candidate topic(s), the apparent ICP, market/language, and the business goal in one inferred line. Harvest seeds from the input: core term, the problem it solves, the solution category, the audience, and any entities/numbers already present in the user's materials.
Step 2 — Read the live SERP (per candidate)
Web-search each seed; read the results. For each top page capture: format (guide / listicle / comparison / how-to / tool / video), rough word count, main H2s, the unique hook, and . Note SERP features present: AI Overview, featured snippet (and its format), People Also Ask (record PAA verbatim — they become H2/H3 questions), related searches, video/image packs.
