1---2name: search-terms-triage3description: >-4 Sorts every search term in a Google Ads or Microsoft Ads export into keep, negative, new keyword or new ad group,5 bid down, or watch, totals the zero-conversion spend by n-gram so recurring waste shows up, and reviews AI Max6 matches in their own section. Every threshold is tied to the company's own target cost per lead, and every negative7 passes a false-positive check before it is listed. Returns ACT, CLEAN, INSUFFICIENT DATA, NEEDS DECISION or BLOCKED.8 Use it weekly on any search account, or before a negative keyword cleanup. Not for setting the cost per lead9 ceiling (use lead-value-math) or for writing the ads of a new ad group (use ad-variants).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Uses a connected ad account or reporting13 connector if the agent has one, otherwise an uploaded CSV export or pasted rows. Python 3 is optional, for the14 n-gram pass.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: decide19 plugin: paid-media20 homepage: https://www.shakeuphq.com/skills/search-terms-triage21---22 23# Search terms triage24 25Finds the words that waste search budget across every term they appear in, and the converting terms the account isn't bidding on yet.26 27## Purpose28 29- One job: label every search term in one export and turn recurring waste into negatives with a match type, a level and a reason.30- Stage: decide. It ends in a verdict for the run, and a label for each term.31- It never adds, removes or uploads a negative, a keyword or a bid. It writes the list and the change log; the reader applies them (Google Ads Editor or Microsoft Advertising Editor, so there is a reviewable diff).32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| Weekly search term review, or a first cleanup of an inherited account | this skill |38| Sizing the waste before asking for budget | this skill (the waste total is the headline figure) |39| You don't know the most a lead may cost | `lead-value-math` first; this skill reads its `max_cpl` |40| A converting term needs its own ads and landing page | this skill labels it; `ad-variants` writes the ads |41| Checking an agent's access before it applies negatives | `agent-guardrails` |42| Choosing a keyword for an organic page | `keyword-selection` |43 44## Inputs45 46| Input | Required | Ways to provide, in order | If missing |47| --- | --- | --- | --- |48| Search terms export: term, match type, added or excluded status, campaign, ad group, clicks, impressions, cost, conversions | yes | a connected ad account or reporting connector (pull the full window in 7-day slices if the connector caps rows, then merge); a CSV export; pasted rows | ask for it; `BLOCKED` |49| Window length | yes | the export's date line; the reader | ask; 90 days is the default request because shorter windows flag words that haven't had time to convert |50| Threshold T: the target cost per lead | yes | `lead-value-math` handoff `max_cpl`; `## Targets` "Target cost per lead"; the account's own non-brand cost per conversion (weaker, labelled) | use the weaker source and say so; with no conversions at all, `INSUFFICIENT DATA` |51| Brand terms and competitor names | yes | `## Company` "Brand terms"; `## Competitors`; the reader | ask once; without brand terms, brand spend hides inside non-brand |52| Core category words and product names | yes | `## Company` "Category"; `## Product`; `## Buying moments` search phrases | ask once; without them the core-category check can't run, coverage `partial` |53| Qualified outcomes per term (SQL or opportunity column from the CRM) | no | a CRM join on click ID; a column the reader adds | judge on platform conversions and say so |54| Pricing (free plan or trial?) | no | `## Company` "Pricing" | treat "free" as phrase-only until confirmed |55| AI Max columns: Source, landing page | no | the Search terms and ad combinations view; the export | review AI Max on match type alone |56 57## Profile read58 59From `company-profile.md`: `## Company` (brand terms, category, pricing, business model), `## Product`, `## Buyers` (ideal customer and bad fit, for the plausible-buyer test), `## Buying moments`, `## Competitors` (names and mention policy), `## Targets` (target cost per lead), `## Accounts and data`, and every `## Learnings` entry for `search-terms-triage` with status `noted`, `fact` or `accepted`.60 61No profile: ask in one message for brand terms, competitor names, the category in the buyer's words, whether there is a free plan, and the most a lead may cost. Say that `company-profile` saves this next time.62 63## Steps64 651. **Apply learnings.** A past negative that cost conversions, or a term the reader protected, overrides the rules below. Name each one that fires.66 672. **Load and merge.** Normalize terms (lowercase, trimmed, single spaces). Merge the same term across campaigns and slices: sum clicks, impressions, cost and conversions; keep the campaigns, match types and the strongest status (added, then none, then excluded). Drop "Total" rows. Report rows in and unique terms out.68 693. **Split the pools.**70 71 | Pool | Rule | Why |72 | --- | --- | --- |73 | Brand | the term contains a brand term (spaces ignored for 5+ letter names) | Brand converts at a different rate and hides non-brand waste |74 | AI Max | match type or Source says AI Max | Reviewed in step 9 with its own rules |75 | Competitor | contains a competitor name | Inside non-brand totals, labelled separately |76 | Non-brand | everything else | The n-gram pool |77 784. **Size the waste.** Waste = cost of non-brand terms with 1+ click and 0 conversions (excluded terms left out). Waste rate = waste / non-brand cost.79 80 | Waste rate | Read |81 | --- | --- |82 | under 15% | healthy |83 | 15% to 25% | watch |84 | over 25% | investigate: the account is buying traffic it can't convert |85 865. **N-gram the non-brand pool.** Split every term into 1, 2 and 3-word phrases (each counted once per term; single stopwords dropped; "what is", "how to" kept). Sum clicks, impressions, cost and conversions per phrase across every term it appears in. Flag, with T the threshold:87 88 | Flag | Rule | Why |89 | --- | --- | --- |90 | negative strong | 0 conversions, cost at least 2 x T | Enough spend to have converted at the target cost twice |91 | negative candidate | 0 conversions, cost at least 1 x T | It has spent what one lead may cost, and produced none |92 | safe category | a jobs, education or consumer word, 0 conversions, any spend | The lowest false-positive categories; they need no threshold |93 | over ceiling | converts, but cost per conversion above T | It converts: bid down, qualify or route to a cheaper offer, never negate |94 | protected core | the phrase is, or sits inside, a core category phrase or product name | A negative on it would block the company's own category |95 | in converting term | a single word that appears in any converting term | Never a broad negative |96 976. **Run the false-positive checks** on every flagged phrase before it becomes a negative. All 4 must pass:98 99 | Test | Question | Fails when |100 | --- | --- | --- |101 | Converting term | Does any converting term contain it? | yes, for a broad negative (a phrase or exact negative on the bad combination may still pass) |102 | Plausible buyer | Could the ideal customer type it while looking to buy? | yes ("template" can be a buyer word; "salary" can't) |103 | Core category | Is it the category or a product name? | yes: never negate; reclassify (step 7) or hold |104 | Sample size | 20+ impressions and 5+ clicks behind it? | no: watch, unless it is a safe category |105 1067. **Classify and place.** Put each passing phrase in one of the 11 categories in `references/negative-categories.md` and take its match type and deployment group from there. Choose the narrowest match that blocks the waste: a single word broad only when it disqualifies on its own and appears in no converting term; otherwise phrase on the 2 or 3-word phrase; exact for one bad query. Add plurals as their own negatives. A phrase that fits no category is either wrong-industry waste (Off-ICP list) or a targeting gap (step 8): say which.107 1088. **Label every term.**109 110 | Label | Rule (first match wins) |111 | --- | --- |112 | already excluded | status excluded: note only |113 | competitor evaluative | competitor plus alternative, vs, pricing, reviews, switch: keep or route to a competitor campaign, if the mention policy allows |114 | competitor navigational | competitor plus login, support, status, careers: negative in competitor campaigns only |115 | negative | 0 conversions, cost at least T, enough sample, and the step 6 checks pass (or covered by a phrase negative from step 7) |116 | bid down | converts above T: lower its bid toward max CPL x its conversion rate, or qualify it |117 | new keyword | not yet a keyword, 2+ conversions at or under T, and the matched ad group's ad and page answer it honestly: add it as exact in that ad group |118 | new ad group | the same, but the matched ad group's ad and page don't answer it (a different promise or buyer): it needs its own ad and page |119 | watch | spend under the thresholds |120 | keep | converts at or under T |121 122 With a qualified-outcome column, judge on cost per qualified lead instead of cost per conversion.123 1249. **Review AI Max separately.** From the AI Max rows (Google: add the Source column to the search terms report and filter match type "AI Max"; the "Search terms and ad combinations" view adds headlines and landing pages):125 126 | Check | Rule |127 | --- | --- |128 | Too early | AI Max on for under 14 days: no negatives yet, only obvious safe-category ones (Google's guidance is to wait at least 2 weeks) |129 | Brand and competitor leakage | AI Max serving brand or competitor terms in non-brand campaigns: set brand exclusions with a brand list before anything else |130 | Landing pages | final URL expansion choosing careers, support, blog or other pages that don't convert: add URL exclusions |131 | Cost per conversion | compare with the non-AI-Max non-brand pool, and read AI Max on cost per opportunity at account level once the judgment window has passed |132 | Negatives | add only for terms that underperform consistently across campaigns, and say they came from AI Max |133 13410. **Run the script.** `python3 scripts/ngram_triage.py --csv terms.csv --brand ... --competitor ... --protect "<core phrase>" --threshold <T> --days <window>`. It returns totals, the flagged n-grams with a suggested match, term labels, brand navigational terms, the AI Max section and a first verdict. Then apply steps 6 to 9 to its candidates. The script can't see the reader's requests: a negative the reader asks for that fails a step 6 test turns the verdict to `NEEDS DECISION`. Without Python, do steps 2 to 5 by hand on the top 200 terms by cost (say so, and say what share of cost they cover), then steps 6 to 9.135 13611. **Write the change log.** One row per negative or keyword: date, level (account, list name, campaign), match type, the phrase, the source terms and their cost, the reason (flag and category), and how to reverse it.137 138## Check and verdict139 140| Verdict | Condition (first match wins) |141| --- | --- |142| `BLOCKED` | No export with terms and cost |143| `INSUFFICIENT DATA` | Window under 30 days, or 0 non-brand conversions: only safe-category negatives are listed, everything else is watch |144| `NEEDS DECISION` | A flagged phrase fails the core-category check, or the reader asks for a negative that fails a step 6 test |145| `ACT` | At least 1 negative, new keyword or new ad group clears the rules |146| `CLEAN` | Nothing clears the rules and the waste rate is under 15% |147 148Named stops: `BLOCKED` asks for the export. `NEEDS DECISION` stops on the conflicting phrase only, showing its spend, the converting terms that contain it and 2 or 3 options (phrase negatives on the bad pairs, the informational list on mid and bottom of funnel only, a cheaper offer such as a guide for that intent). Every negative that passed is still listed as ready. No other stops.149 150## Learn151 152Append to `## Learnings` when:153 154- the reader rejects a negative ("we sell to schools"): a `fact` that protects the word for this company;155- a past negative is found to block converting traffic (impressions on a converting keyword fell after it): a `fact` naming the negative, and a `proposal` to loosen the rule that produced it;156- a promoted term or new ad group reports cost per opportunity after the judgment window: a `fact`;157- the reader sets a different threshold: a `proposal` with their reason.158 159Example: `- 2026-10-24 | search-terms-triage | fact | Never negate "template": buyers search "attribution report template" before demos | Why: 3 opportunities from that term in Q3 (reader's CRM) | Status: noted`160 161## Output162 163```164Verdict: <ACT | CLEAN | INSUFFICIENT DATA | NEEDS DECISION | BLOCKED> · Coverage: <complete | partial (what's weak)> · N-gram pass: <script | by hand, top n terms, x% of cost>165Window: <dates, days> · Threshold T: <value> (<source>)166 167Waste: <amount> of <non-brand cost> non-brand spend (<rate>, <band>) across <n> terms168Brand: <cost>, <conversions> · Competitor: <cost> · AI Max: <cost>, <conversions>169 170Negatives ready171| Phrase | Match | Level or list | Category | Cost | Terms | Reason |172 173Held for a decision174| Phrase | Cost | Converting terms that contain it | Options |175 176New keywords and new ad groups177| Term | Conversions | Cost per conversion | Label | Why |178 179Bid down180| Term | Cost per conversion | Max CPC at its rate |181 182AI Max183<checks from step 9, each with what it found>184 185Change log186| Date | Level | Match | Phrase | Source terms | Reason | Reverse by |187 188Learnings applied: <list, or none>189```190 191Then the handoff block.192 193## Hand off194 195```handoff196skill: search-terms-triage197version: 1.0.0198verdict: ACT199coverage: complete200for: <account, window>201outputs:202 waste: 6830203 waste_rate: 0.21204 negatives_ready: 14205 held: [marketing attribution]206 new_ad_groups: [attribution software for hubspot]207 ai_max: brand exclusions missing208next: [ad-variants, lead-value-math]209open: [reader applies negatives in Editor and logs them]210```211 212`ad-variants` reads `new_ad_groups`. `lead-value-math` reads `waste` for the recovered-pipeline estimate.213 214## Failure modes215 216| Problem | Do this |217| --- | --- |218| The export has no conversions column | `BLOCKED` for negatives; list the waste candidates by cost only and ask for the column |219| Conversions are form fills on a long sales cycle | Say so; prefer a qualified-outcome column; never promote on a single form fill |220| Low-volume terms are hidden by the platform | Block patterns (phrases) rather than single queries: suppressed queries are covered by the phrase |221| A brand term is also a common word | Ask the reader for the brand terms that are unambiguous; match the rest only with the category word next to them |222| The reader asks to push the negatives live | Recommend the Editor upload with the change log; this skill never applies changes |223| Lead volume and sales-accepted leads both fall after a cleanup | Over-negated: list the negatives added in the window and test removing the newest first |224 225## Influenced by226 227- SHAKEUP's B2B Google Ads playbook: waste sized on 90 days of zero-conversion spend, the cost-weighted n-gram pass, the 11 negative categories and their deployment, and the false-positive checks.228- Google's guidance on AI Max reporting (the Source column, the search terms and ad combinations view, brand lists, waiting 2 weeks before adding negatives): https://support.google.com/google-ads/answer/16470459?hl=en