1---2name: message-mining3description: >-4 Reads reviews, sales call notes, support tickets and survey answers line by line, pulls the phrases buyers5 repeat, tags each as a pain, outcome, objection or trigger, and counts how many different buyers said it. Returns6 a phrase bank in the buyers' own words with anonymous quotes, the alternatives they name, and the gap between7 their words and the company's messaging. Use it before building a messaging house, rewriting a landing page or8 briefing ads. Not for scoring a finished page (use landing-page-critic) or testing a message with buyers (use9 message-test).10license: MIT11compatibility: >-12 Works in Claude, ChatGPT, Codex, Cursor and any agent that reads SKILL.md. Uses a connected review site, CRM,13 call recorder or help desk if the agent has one, otherwise exports or pasted text. Python 3 is optional, for14 counting phrases.15metadata:16 author: SHAKEUP17 version: "1.0.0"18 stage: get19 plugin: creative-conversion20 homepage: https://www.shakeuphq.com/skills/message-mining21---22 23# Message mining24 25Finds the words buyers already use for their problem, counted per buyer, so pages and ads can say it back to them.26 27## Purpose28 29- One job: turn raw buyer text into a counted, tagged phrase bank.30- Stage: get. It reads data in and structures it, and ends in a coverage verdict, not a recommendation.31- It never writes headlines or messaging (that is `messaging-house` and the skills after it), never invents or paraphrases a quote, and never names a reviewer or their company unless the profile records the quote as cleared.32 33## Use when / not34 35| Situation | Use |36| --- | --- |37| Before building or rewriting the messaging house | this skill, then `messaging-house` |38| A landing page or ad set needs the buyer's words | this skill, then `landing-page-critic` or `creative-brief` |39| A pile of reviews, call notes or tickets and a question about what buyers say | this skill |40| Checking whether a finished message lands with real buyers | `message-test` |41| Finding the situations that start a search | `buying-moments` (it reads this skill's trigger phrases) |42| Scoring a published page | `landing-page-critic` |43 44## Inputs45 46An item is one review, one call, one ticket, one survey answer or one interview. Every count in this skill is items, never mentions.47 48| Input | Required | Ways to provide, in order | If missing |49| --- | --- | --- | --- |50| Buyer text: reviews, call notes or transcripts, tickets, survey or interview answers | yes | a connected tool (review site, CRM notes, call recorder, help desk); an export the reader uploads (CSV or text); text pasted into the chat | ask once; with none, `BLOCKED` |51| Per item: source, and if known the role and deal stage (won, lost, open, customer) | no | columns in the export; a header line per item; the reader's note | treat all items as one source; coverage `partial` |52| Competitor reviews | no | the review site; pasted text | mine own sources only; say so in open items |53| The company's current messaging | no | `## Messaging house` and `### Words to use` in the profile; the homepage text | skip the language gap (step 8); coverage `partial` |54 55## Profile read56 57From `company-profile.md`: `## Company` (brand terms, to keep brand mentions out of the phrases), `### Buying group` (roles to tag items with), `## Messaging house`, `### Words to use`, `## Claims and proof` (a customer quote is cleared only when a `Claim:` line holds it with a source), `## Competitors` (names to catch as alternatives), and every `## Learnings` entry for `message-mining` with status `noted`, `fact` or `accepted`.58 59No profile: ask for the brand name and the product category in one message, so brand mentions can be removed and off-topic items spotted. Say that `company-profile` saves this step next time. Treat every quote as not cleared.60 61## Steps62 631. **Apply learnings.** A learning that changes a rule (a source to down-weight, a threshold) overrides the default below. Name it in the output when it fires.64 652. **Strip personal data first.** Before reading for meaning, remove names, emails, phone numbers, handles, signatures and the reviewer's company name from every item. Keep the role. Drop role details that identify one person together (role plus company plus city). Count what you removed.66 673. **Check that it is buyer language.**68 69 | Material | Do this |70 | --- | --- |71 | Reviews, call transcripts, buyer emails, tickets, survey or interview answers | mine it |72 | A sales rep's summary of a call ("prospect worried about price") | mine it, source `rep summary`; the words are the rep's, so never quote them as the buyer's |73 | Competitor reviews | mine as their own group: they show pains with the alternatives |74 | The company's own site, deck, ads, emails or an AI summary of buyers | don't mine: it is the company's words. If nothing else was given, `BLOCKED` |75 764. **List the items.** One row per item: id, source, role, stage group, date. Stage groups: `pre-sale` (reviews, sales calls, lost-deal notes, prospect surveys) and `post-sale` (tickets, churn notes, customer interviews). Drop items under 5 words (too short to hold a phrase and its context) and exact duplicates (a review posted twice is 1 buyer). Put items older than 24 months in an `older` group and keep them out of the counts (the product and the market have moved; an old pain may be solved).77 785. **Count repeated phrases.** Minimum items for a phrase to count as repeated: 2 when there are under 50 items; 3% of items, at least 3, from 50 up (a large pile throws up incidental pairs, so the bar scales with it). Run:79 80 ```81 python3 scripts/phrase_counts.py --file items.txt --brand "<brand term>" [--brand "<product name>"]82 ```83 84 Items in the file are separated by a line with only `---`; an item can open with `[source: review; role: CMO; stage: won]`. Without Python, do it by hand: in each item, mark phrases of 2 to 5 words inside one sentence that carry a problem, a result, a doubt or an event; tally 1 per item, not per mention; drop phrases with the brand name; keep phrases at or above the minimum. Say which way you counted.85 866. **Read line by line for what counting misses.** Buyers say the same thing in different words. Read every item without summarizing, group paraphrases into themes, label each theme with its most common verbatim phrase, and count items per theme. Keep up to 5 `standout` lines: said once, but vivid and specific (a picture, a number, a moment). A standout is never presented as a pattern.87 887. **Tag each phrase or theme.** First match wins:89 90 | The phrase says | Tag |91 | --- | --- |92 | what happened that started the search (an event, a person asking, a date, a change) | `trigger` |93 | a doubt, a risk, a cost or a reason to wait or say no | `objection` |94 | what is better after (a result, time saved, something they can now do) | `outcome` |95 | what was wrong before (the problem, the workaround, the feeling) | `pain` |96 | none of these | untagged: keep in the appendix only |97 98 Triggers and objections win ties because they are rarer and decide more: "after the board asked for pipeline by channel" is a trigger even though it implies a pain. When the same words carry opposite meanings in different items ("we finally trust the report" and "we don't trust the report"), split them into 2 phrases by the meaning of each sentence and tag each; never let a pain count toward an outcome. The script's `tag_hint` is a hint, not the tag. Also list every `alternative` buyers name (a competitor, a spreadsheet, the CRM's own reports, doing nothing) with its item count.99 1008. **Weigh each phrase.**101 102 | Condition | Strength |103 | --- | --- |104 | At or above the minimum, in 2 or more source types | `strong` |105 | At or above the minimum, in 1 source type | `medium` |106 | Below the minimum, or a standout | `weak` (keep, labelled) |107 108 Then apply, in order:109 - A phrase found only in `post-sale` items is labelled `post-sale`: use it for onboarding, retention and expansion copy, not for acquisition headlines, unless it also appears pre-sale (tickets describe using the product, not choosing it).110 - A phrase found only in rep summaries drops one strength level (the rep chose the words).111 - Learnings that down-weight a source apply here.112 1139. **Find the language gap.** Compare the strong and medium phrases with `## Messaging house` and `### Words to use`:114 115 | Status | When |116 | --- | --- |117 | `match` | the company already says it in the buyer's words |118 | `different words` | the company says the same thing in its own words (show both) |119 | `missing` | buyers say it in 3 or more items and no pillar covers it |120 | `unused` | a pillar no buyer phrase supports: it may matter only to the company |121 12210. **Pick quotes.** For each strong or medium phrase, pick 1 or 2 verbatim lines. Format: `"<quote>" (<role or buyer>, <source>, <month>)`. Cut with `...` and remove names; change nothing else inside quotation marks. Name a person or company only when the quote is a cleared claim in `## Claims and proof`, and then cite that claim's source. If the reader asks for names on uncleared quotes, keep them anonymous and list the quotes to clear in open items.123 124## Check and verdict125 126| Verdict | Condition (first match wins) |127| --- | --- |128| `BLOCKED` | No buyer text, or the only material is the company's own words |129| `THIN` | Fewer than 20 items after step 4, or fewer than 3 phrases reach the minimum. Under 20 items, 2 matching phrases can be chance; the bank is a list of quotes to read, not a pattern to build on |130| `MINED` | 20 or more items and 3 or more phrases at or above the minimum |131 132Before the verdict, check: every count is items, not mentions; no name, email or reviewer company is left in a quote; no quote was reworded; every phrase has a tag and a strength. Fix and recheck once.133 134Named stop: `BLOCKED` asks for buyer text and lists the sources that would work. No other stops. A tag with no phrases (often objections, when only happy reviews were given) is an open item that names the source to add (lost-deal notes, churn notes).135 136## Learn137 138Append to `## Learnings` in the profile:139 140- A phrase from the bank was used in a headline or ad and a result came back (a test, a click-through change, demo rate from the reader's data): a `fact` with the result and its source.141- The reader says a source misleads (tickets dominated by one large customer, reviews gathered by an incentive): a `proposal` to exclude or down-weight that source.142- The reader moves a phrase to another tag or merges 2 themes: a `fact` for this company's bank.143- A quote is cleared for named use: ask the reader to add it to `## Claims and proof` with `company-profile`, and record a `fact`.144 145Example: `- 2026-10-24 | message-mining | proposal | Down-weight tickets from accounts over 1,000 seats | Why: 40% of tickets came from 2 accounts (reader's help desk export, Oct 2026) | Status: proposed`146 147## Output148 149```150Verdict: <MINED | THIN | BLOCKED> · Coverage: <complete | partial (what's missing) | blocked> · Counting: <script | by hand>151Items read: <n> (<n> per source) · Dropped: <n> (<reasons>) · Older than 24 months: <n> · Personal data removed: <counts>152Minimum items for a repeat: <n> · Learnings applied: <list or none>153 154Phrase bank155| Tag | Buyer phrase | Items | Share of items | Sources | Roles | Strength | Example (anonymous) |156(grouped: trigger, pain, objection, outcome; strongest first in each)157 158Alternatives named159| Alternative | Items | What buyers say about it (verbatim) |160 161Language gap162| Pillar or word we use | Buyer phrase | Status |163 164Standout lines (each said once)165Open: <tags with no phrases and the source to add; quotes to clear; sources not mined>166```167 168Then the handoff block.169 170## Hand off171 172```handoff173skill: message-mining174version: 1.0.0175verdict: MINED176coverage: partial (no lost-deal notes, so objections are thin)177for: <product, segment or page the mining was for>178outputs:179 items: <n>180 top_trigger: "<phrase>" (<n> items)181 top_pain: "<phrase>" (<n> items)182 top_objection: "<phrase>" (<n> items)183 top_outcome: "<phrase>" (<n> items)184 alternatives: [<alternative> (<n>), <alternative> (<n>)]185 language_gap: ["buyers say '<phrase>', we say '<phrase>'"]186next: [messaging-house, landing-page-critic, creative-brief]187open: [lost-deal notes for objections]188```189 190`messaging-house` reads the phrases and the gap; `landing-page-critic` reads `top_pain`, `top_objection` and `top_outcome` to check the page speaks to them; `creative-brief` and `ad-themes` read the triggers as hooks. For `THIN`, `next` still lists them, and `open` says the bank is directional.191 192## Failure modes193 194| Problem | Do this |195| --- | --- |196| Every review is 5 stars and short | Mine them, but say objections are missing; ask for lost-deal notes or churn notes |197| One buyer wrote a third of the material (a long transcript) | Count that buyer once per phrase, as with any item; say their share of the words |198| Text in another language | Mine it in that language; give the phrase and a plain translation; never merge across languages |199| The export has no source column | Treat all items as one source; strength can't be `strong`; coverage `partial` |200| The reader wants quotes with names for a page | Keep them anonymous; list the quotes and ask the reader to clear them through `company-profile` |201| A phrase is the product's own feature name repeated by buyers | Keep it out of pains; it can be an outcome only with a result next to it |202 203## Influenced by204 205- Joanna Wiebe's message mining (Copyhackers): read buyer text line by line, without summarizing, and write from the phrases that repeat. Described here: https://wistia.com/learn/marketing/joanna-wiebe-conversion-copywriting206- What we changed: counts are per buyer with a repeat bar that scales with the pile, phrases carry a fixed 4-tag table and a strength, pre-sale and post-sale text are kept apart, the bank is compared with the company's own messaging, and quotes stay anonymous unless cleared.