1---2name: topic-precheck3description: >-4 Decides whether a B2B SaaS article topic is worth researching and writing before any time goes into it. Checks5 whether a page on the site already owns the intent, where the topic sits in the topic clusters, whether anyone6 searches for it, whether the company has first-party evidence to say something new, and whether a real author is7 set, then returns GO, GO (supporting content), STOP or NEEDS DECISION from ordered rules. Use it at the start of8 every new article, or to sanity-check a topic idea. Not for picking the keyword itself (use keyword-selection) or9 for deciding what to do with a published page (use content-triage).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Uses Search Console, an SEO tool or the13 site's sitemap if the agent can reach them, otherwise exports or pasted data. Python 3 is optional, for the verdict14 and the demand split.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: decide19 plugin: content20 homepage: https://www.shakeuphq.com/skills/topic-precheck21---22 23# Topic precheck24 25Stops an article before it starts when a page already owns the intent, nobody searches for it, or the company has nothing new to say.26 27## Purpose28 29- One job: one verdict on one topic, with every reason and figure behind it.30- Stage: decide. It ends in a verdict decided by ordered rules (`scripts/precheck_verdict.py`), never by feel.31- It never invents demand, rankings, evidence or an author. A missing figure is `not available` and lowers coverage.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| A new article topic or keyword, before research | this skill |38| An idea from the team, sales or a content calendar that might become an article | this skill |39| Choosing the exact keyword and intent for the page | `keyword-selection` (this skill reads its handoff) |40| Two published pages already compete | `cannibalization-audit` |41| Deciding what to do with a published page | `content-triage`, then `refresh-audit` |42| A LinkedIn post, not an article | `founder-post` or `content-calendar` |43 44## Inputs45 46| Input | Required | Ways to provide, in order | If missing |47| --- | --- | --- | --- |48| The topic or keyword, in the buyer's words | yes | the reader's request; a `keyword-selection` handoff | ask once; `BLOCKED` without it |49| The site's existing pages on the topic | no | a `cannibalization-audit` handoff; the sitemap or a site search if the agent can browse; URLs and titles the reader pastes | cannibalization `NOT_CHECKED`; coverage `partial` |50| Search Console queries, last 12 months | no | a connected Search Console; a Queries export (CSV); pasted rows | demand from the keyword tool alone |51| Keyword volumes for the topic and its category | no | a `keyword-selection` handoff; a connected SEO tool; an export; figures the reader pastes | demand from Search Console alone; with neither, demand `UNKNOWN` |52| Topic clusters and pillar pages | no | a `cluster-fit` handoff; `## Content` in the profile; the site's page titles | role `standalone`, flagged |53| First-party evidence on the topic | no | `## Claims and proof` in the profile; items the reader pastes (cleared quotes, data, cases) | evidence 0 |54| A named author with a bio page | yes | `## Content` > `Authors` in the profile; the reader's answer | ask once; `STOP` if there is none |55 56## Profile read57 58From `company-profile.md`: `## Company` (website, brand terms), `## Buyers` and `## Buying moments` (for the intent fingerprint), `## Claims and proof` (evidence), `## Content` (authors, topic clusters), and every `## Learnings` entry for `topic-precheck` with status `noted`, `fact` or `accepted`.59 60No profile: ask in one message for the website, who the buyer is, the named author and their bio link, and any first-party proof on this topic. Say that `company-profile` saves this next time.61 62## Steps63 641. **Apply learnings.** Read the learnings first. An accepted learning that changes a rule or threshold (the evidence minimum, the demand floor) overrides the default below; name it in the output when it fires.65 662. **Fix the topic.** Write the intent fingerprint: "This page targets <audience from `## Buyers`> who want to <do, understand or decide> <specific thing> at the <stage> stage." If a `keyword-selection` handoff exists, use its primary keyword and intent. Without one, use the reader's phrasing and mark intent `unconfirmed`.67 683. **Run the 3 checks.** Use each skill's handoff when it exists; otherwise run the inline method in `references/precheck-rules.md` and say which you did.69 70 | Check | From | Result |71 | --- | --- | --- |72 | Cannibalization | `cannibalization-audit`, else rules section 2 | PROCEED, DIFFERENTIATE, REFRESH, BLOCK or NOT_CHECKED, plus the page and the rule that fired |73 | Cluster fit | `cluster-fit`, else rules section 3 | role (pillar, supporting, standalone), pillar URL, the gap in one sentence |74 | Demand | `keyword-selection` and its demand split, else rules section 4 | GO, SUPPORTING, STOP or UNKNOWN, with problem-intent and category figures reported apart |75 76 Upstream verdicts map as in rules section 1. A `NEEDS DECISION` from `keyword-selection` stays a decision: carry its reason, don't decide it again.77 784. **Count usable evidence.** Apply the 3 tests in rules section 5 (relevant, cleared, first-party). List every counted item and every near miss with the test it failed.79 805. **Check the author.** A real person, named, with a bio page the reader can link. A job title alone ("our head of content") is not an author until it has a name. Never invent a name or a credential.81 826. **Decide.** Run the script with the results:83 84 ```85 python3 scripts/precheck_verdict.py --cannibalization DIFFERENTIATE \86 --gsc-csv queries.csv --keyword "<topic keyword>" --category "<broad term>" \87 --tool-volume 0 --tool-category-volume 1300 --evidence 1 --pillar "<pillar URL>"88 ```89 90 Pass `--demand` and `--problem-intent` instead of the CSV when `keyword-selection` already split demand, and `--no-author` when step 5 failed. Without Python, apply the verdict table below in order and stop at the first match; say which way you ran it. Report crawler rows dropped from the Search Console data, with their impressions.91 927. **Write the reasons.** Every verdict carries: the rule that fired, the figures behind it, the evidence list, and the flags (overlap not checked, thin evidence, standalone page, pillar missing). A bare verdict is a failure.93 94## Check and verdict95 96| Verdict | Condition (first match wins) |97| --- | --- |98| `BLOCKED` | No topic after asking once, or the input is a published page's URL (this skill decides new topics; run `content-triage` on the page) |99| `STOP` | No real, named author (a byline is never invented) |100| `STOP` | Cannibalization is BLOCK: a healthy page already owns the intent |101| `STOP` | Auto-stop: (cannibalization DIFFERENTIATE, or demand SUPPORTING) and problem intent is 0 and usable evidence is under the minimum (default 2). The page would repeat an existing page or sit under a category nobody searches by its own name, with too little to say. Stop without asking |102| `STOP` | Demand STOP and 0 usable evidence |103| `NEEDS DECISION` | Cannibalization DIFFERENTIATE or REFRESH (a person confirms the angle, or chooses the refresh) |104| `NEEDS DECISION` | Demand STOP with 1 or more usable evidence items |105| `NEEDS DECISION` | Demand UNKNOWN: no data from any source |106| `NEEDS DECISION` | Demand SUPPORTING and no pillar page exists to support |107| `GO` | Demand GO, cannibalization PROCEED or NOT_CHECKED, author set |108| `GO (supporting content)` | Demand SUPPORTING with a named pillar: the pillar becomes a required internal link |109 110Problem intent counts as 0 only when every source that covers the topic's own phrasing says 0. When it is unknown, the auto-stop never fires.111 112Named stops: `BLOCKED` and the `STOP` for a missing author ask for the input. `NEEDS DECISION` stops and shows the options, each with what it costs and what it unlocks (for example: "differentiate on <angle> and link to <page>", or "refresh <page> with `refresh-audit` instead"). Every other verdict runs on: `GO` goes to `article-research`; `STOP` ends the run with the reasons on file and no question.113 114## Learn115 116Append to `## Learnings` in the profile when:117 118- the reader overrides a verdict, such as writing a STOP topic anyway (a `proposal` with their reason);119- a result comes back for a past GO, such as the page's impressions, rankings or demos after 90 days (a `fact`, with its source);120- a STOP topic later shows demand (a `fact`, and a `proposal` if it suggests a lower floor or a different evidence minimum).121 122Example: `- 2026-10-24 | topic-precheck | proposal | Count a recorded sales call that names the problem as usable evidence | Why: 3 STOP topics from sales calls drew demos once written (reader's CRM, Q3 2026) | Status: proposed`123 124## Output125 126```127Verdict: <GO | GO (supporting content) | STOP | NEEDS DECISION | BLOCKED> · Rule: <rule id> · Coverage: <complete | partial (what's missing) | blocked>128Topic: <topic> · Intent: <fingerprint> (<confirmed | unconfirmed>)129 130| Check | Result | Source | Detail |131| Cannibalization | <verdict> | <handoff | inline | not checked> | <page and rule, or "none found"> |132| Cluster fit | <role> | <handoff | profile | inline> | <cluster, pillar URL, the gap> |133| Demand | <GO | SUPPORTING | STOP | UNKNOWN> | <Search Console | tool | handoff> | problem intent <n>, category <n>, crawler rows dropped <n> (<impressions>) |134| Evidence | <n> usable (minimum <n>) | profile, reader | <items counted; near misses and why> |135| Author | <name, bio link | missing> | profile | |136 137Reasons: <the rule's reason, then the figures>138Flags: <list, or none>139Decision needed (NEEDS DECISION only): <option A, what it costs, what it unlocks> · <option B, ...>140Verdict decided by: <script | the table, by reading>141Learnings applied: <list, or none>142```143 144Then the handoff block.145 146## Hand off147 148```handoff149skill: topic-precheck150version: 1.0.0151verdict: GO (supporting content)152coverage: partial (no Search Console export; keyword tool figures pasted)153for: <topic>154outputs:155 topic: salesforce attribution reports156 intent: decide how to report pipeline by channel in Salesforce157 role: supporting158 pillar: <pillar URL, required internal link>159 evidence: [<claim or item ids counted>]160 author: <name, bio URL>161 avoid_overlap_with: <page URL and the sub-topics not to repeat, or none>162next: [article-research]163open: [confirm the angle differs from <page>]164```165 166`next` is `[article-research]` for GO and GO (supporting content), `[refresh-audit]` when the reader picks the refresh, and `[]` for STOP.167 168## Failure modes169 170| Problem | Do this |171| --- | --- |172| The sitemap or site search can't be read | Ask for page URLs and titles once; without them, `NOT_CHECKED` and say so. Never treat it as a clean pass in the reasons |173| Search Console shows 0 for a topic the site has never written about | That only means no page ranks yet. Use keyword tool data for problem intent; if there is none, problem intent is `unknown`, not 0 |174| The keyword tool and Search Console disagree | Report both; either one showing demand is enough for GO |175| The reader's evidence is a public study, not their own | It doesn't count toward the minimum. Keep it for `article-research` |176| A quote is from a customer but not cleared | Near miss on "cleared". Ask the reader to confirm, don't count it until they do |177| The reader changes the topic or angle at a NEEDS DECISION | Rerun the cannibalization and cluster checks on the new topic; the old results don't hold |178| A handoff names a page or evidence id that doesn't exist | Stop and say which; never fill it in |179| The input is a URL of a published page | `BLOCKED`, with `next: [content-triage]`: refresh, consolidate or retire is that skill's call |180 181## Influenced by182 183- SHAKEUP's content engine: the precheck verdict decided by ordered rules in code, the "stop instead of asking" rule, and demand split into problem intent and category so a big category figure can't stand in for a topic nobody searches.184- Google's guidance on helpful, people-first content, which warns against pages made mainly to attract search visits and against many near-duplicate pages: https://developers.google.com/search/docs/fundamentals/creating-helpful-content