[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6R8TA295KS6VA5X8633CD2B":3,"skill-same:01M6R8TA295KS6VA5X8633CD2B":78},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":51,"updatedAt":52,"install":53,"resources":66},"01M6R8TA295KS6VA5X8633CD2B","asb-carol-inciting-events",null,"Facilitates the fifth step of a proven ideal-customer (ICP) method: mapping inciting events — the specific trigger moments that move a perfect-fit customer from could-buy-someday to buying-today. Takes a keystones file (K1, K2, … with market segments) and, when available, customer-interview findings; walks the keystones one at a time, harvesting real trigger stories from interview evidence (marked observed) and working backward through brainstorm lenses — crises, seasonal cycles, strategic windows, personal life-changes — for the rest (marked hypothesized), recording each event with the keystone it couples to and how to find prospects in that condition, in INCITING-EVENTS.md (E1, E2, …). Load when the user has keystones and asks what makes customers buy now, what triggers a purchase, or 'run the inciting-events step.' Do NOT load to derive keystones or deal-breakers (previous steps), to write the final ideal-customer definition (next step), or to write the ads themselves.","Nairon-AI\u002Fagentic-starter-pack","Nairon-AI","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F260662138?v=4","01M6R8PZ1Y8CSQGFN61VACZGTH","Nairon AI","01M6R8PZ6184VR3BA88YZFBC3N",4,"MIT","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fbusiness\u002Fasb-carol-inciting-events\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"events","asb carol inciting events","condition","how","when","definition","market segments","purchase","recording","move","now","ads","customer","how to","icp","seasonal","time","next","one at a time","brainstorm","2026-11-10 10:12:30",false,"---\nname: asb-carol-inciting-events\ndescription: \"Facilitates the fifth step of a proven ideal-customer (ICP) method: mapping inciting events — the specific trigger moments that move a perfect-fit customer from could-buy-someday to buying-today. Takes a keystones file (K1, K2, … with market segments) and, when available, customer-interview findings; walks the keystones one at a time, harvesting real trigger stories from interview evidence (marked observed) and working backward through brainstorm lenses — crises, seasonal cycles, strategic windows, personal life-changes — for the rest (marked hypothesized), recording each event with the keystone it couples to and how to find prospects in that condition, in INCITING-EVENTS.md (E1, E2, …). Load when the user has keystones and asks what makes customers buy now, what triggers a purchase, or 'run the inciting-events step.' Do NOT load to derive keystones or deal-breakers (previous steps), to write the final ideal-customer definition (next step), or to write the ads themselves.\"\n---\n\n# Inciting Events: What Makes Them Buy Today\n\nA prospect can agree the product is a great fit, the keystone is\nexactly what they want, there are no deal-breakers, the price is fair —\nand still not buy. Their excuse is genuine: \"we can't implement this\nright now; call back in nine months.\" The person with buying power has\none to three top priorities, and you aren't one of them. What promotes\nyou to the top is an **inciting event**: nobody wakes up randomly\ndeciding today's the day to buy — something happens in their life, a\nmoment of struggle where action *must* be taken. This skill maps those\nmoments, keystone by keystone.\n\n## The mental model\n\n### The inciting event completes the purchase\n\nThree forces, in order: **inciting events are why people buy\nanything** (the struggle that forces action now), **keystones are why\nthey buy from you** (the circumstance that makes your strength\ncritical), and **deal-breakers carve off exclusions**. A keystone\nmeans the customer *could* care about the issue; the inciting event is\nwhat raises it to a top-three priority they want solved today. That is\nwhy every real inciting event couples to a keystone — an event with no\nkeystone attached is a trigger to buy *something else*. The canonical\npairs: the speed keystone's events were \"the SEO consultant said poor\nperformance is blocking our rankings\" and \"we saw the study showing\nfaster sites convert more revenue\"; the scale keystone's event was\n\"the biggest traffic day of the year crashed the site — never again\";\nthe security keystone's was \"we got hacked, it was terrifying, we paid\na consultant $300 an hour and we're still not sure it's fixed\"; the\nsupport keystone's was \"we called for help and were told 'all we do is\nkeep your server powered on.'\"\n\n### Observed beats hypothesized — and both get marked\n\nThe reliable way to identify inciting events is to ask customers what\nprompted them to start looking and why they chose you — ideally right\nafter purchase, while the answer is fresh. So when interview evidence\nexists (a findings report, per-interview debrief files, onboarding\nsurvey answers), harvest it FIRST: real trigger stories, in the\ncustomers' words, marked **observed** with their source. Only then\nwork backward for the gaps, and mark those **hypothesized** — honest\nlabels, because a hypothesized event is a guess wearing a plan, and\nthe next round of customer conversations should test it. Never dress\na brainstorm as evidence.\n\n### The work-backward lenses\n\nWhen hypothesizing, ask: what would compel a customer to act *today*,\nwith urgency, with budget, with pre-approval? Brainstorm through these\nlenses:\n\n- **Crises that force immediate action** — a public breach or data\n  loss; a critical vendor acquired or shut down; a key customer\n  ultimatum; a lawsuit or regulatory investigation; executive\n  turnover; a PR debacle; a competitor announcement that exposes a\n  gap.\n- **Seasonal and recurring cycles** — annual planning, fiscal\n  year-end, tax season, quarterly reviews, compliance audits,\n  conference deadlines, the industry's peak season approaching.\n- **Strategic windows** — a compliance deadline, a required\n  certification, entering a new market, an acquisition closing, IPO\n  prep, legacy-system modernization, new funding creating budget and\n  expectations at once.\n- **Personal life-changes** (for consumer and solo-professional\n  products) — becoming a parent, retiring, a health diagnosis, a\n  death in the family, marriage or divorce, starting a business,\n  changing jobs, graduating, buying a first home.\n\n### Findability makes the file operational\n\nFor each event, answer: **how do you find prospects in this condition?**\nSomeone whose site was just hacked isn't searching \"secure hosting\" —\nthey're searching \"how to tell whether my site is hacked\" and posting\n\"Help! My site is hacked!\" into the void. Findability signals include:\nofficial announcements, executive podcast appearances, product\nlaunches and press tours, changes in job postings, recurring\ncomplaints in reviews or social media, analyst reports, regulatory\nchange notices, leadership changes, funding news — and above all, the\nexact phrases a person in that moment types into a search box. An\nevent you can't detect from outside is still worth recording, but say\nso: it can only be exploited in messaging (\"if this just happened to\nyou…\"), not targeting. Events are often split — the lawsuit half of\nan enforcement event is public record while the audit-notice half is\ninvisible; annotate which parts are targetable and which are\nmessaging-only. If the user asks you to research the triggers — recent\nregulatory changes, funding news, seasonal cycles, competitor moves —\nconfirm them with current results from your search tools; do not rely\non internal (training) knowledge, which is stale and misses this\nyear's real events.\n\n### Vivid or it doesn't advertise\n\nIn advertising, the inciting event often outperforms the keystone,\nbecause it speaks to the customer's current experience — they're\nreacting to their circumstance, not shopping for product attributes.\nThat only works if the event is written vividly: the specific moment,\nthe emotion, the number. \"A hacked website is a personal violation —\nyou pay a consultant $300 an hour and still wonder if it's coming\nback\" advertises; \"customers get frustrated with their host\" doesn't.\nGeneric events (\"realizes they need a better solution\") are not\nrecorded, in any form — there is always a specific moment inside a\ntrue trigger, and finding it is the work.\n\n### Vocabulary\n\n- **Inciting event (E1, E2, …)** — the specific trigger moment that\n  moves a keystone-fit customer to buy now; cites its [K-number].\n- **Observed \u002F hypothesized** — evidence status: harvested from real\n  customer accounts (with source) vs. worked backward (to be\n  validated). Two sanctioned shadings: \"OBSERVED (from memory)\" for\n  the user's recall of a real account — genuine evidence, weaker\n  sourcing, re-confirm at validation; and a composite of repeated\n  sales-call patterns with no single account stays HYPOTHESIZED. A\n  hypothesized event may cite supporting-but-not-triggering evidence\n  (\"plausibility supported — not evidenced — by the June debrief's\n  standing dread\") without gaining a Source line.\n- **Findability** — how prospects in the event's condition can be\n  detected or reached from outside, including their likely search\n  phrases.\n\n## The mapper's posture\n\n### Be clear, not clever\n\nWrite to be understood, not admired. The work here wrestles with hard\nconcepts, and clever metaphors, wordplay, or cute turns of phrase make\nthem harder to grasp, not easier. Say plainly what you mean. If a\nsentence reads more clearly without a flourish, cut the flourish. State\nthe actual point rather than gesturing wittily at it.\n\n### Restate references; never cite a bare token\n\nWhen you mention a numbered or lettered item to the user — K4, W2,\nO17, H3, and the like — add a few plain words on what it actually is\n(\"K4 — the owner whose career rides on the site\"). A bare token is\nunreadable to a human who saw it defined hours or days ago: the tag is\nfor traceability, the gloss is for comprehension. Keep the tag for\naccuracy; always add the gloss.\n\n### Harvest before you brainstorm\n\nIf interview artifacts exist — a findings report with trigger\nstories, per-interview debrief files, exit or onboarding surveys —\nread them first and pull every trigger story into candidate events\nbefore hypothesizing anything — and record harvested events as they\nconfirm, even when they belong to keystones later in the walk;\nE-numbers run in settle order, not keystone order. The user's memory counts too (\"what\ndid your last three customers say prompted them to look?\"), marked\nobserved-from-memory. Only where the evidence runs out do the lenses\ncome out. If the user has no interview evidence at all, say plainly\nthat everything in this file will be hypothesized until customers are\nasked — and that asking is the validation path.\n\n### Press moments into vividness\n\nWhen the user offers a vague trigger (\"when they get fed up with\ntheir current tool\"), press for the moment: fed up *by what incident*?\nWhat happened that morning? What did it cost? What did they type into\nGoogle that night? A predefined way to press harder: if a\ndevil's-advocate interrogation skill is installed in the environment\n(for example *Rude Q&A* \u002F `asb-rude-qa`, from the same author as this\nmethod), invoke it against the draft with this brief: *attack these\ninciting events — find every one that's a mood rather than a moment,\nevery one no real customer story or plausible circumstance backs,\nevery \"hypothesized\" that's being treated as fact, and every\nfindability note too vague to act on. Don't accept wishful or\nhand-wavy defenses.* If no such skill is available, run that\ninterrogation yourself, visibly — candidates inline, the batch attack\nat the closing sweep.\n\n### Couple every event to a keystone\n\nAn event that couples to no keystone is a flag, not an entry: either\nit's a trigger to buy something you don't sell, or it's pointing at a\nkeystone the earlier steps missed. Say which it looks like; if the\nuser believes a real keystone is missing, that's a finding to take\nback to the keystones file — not a reason to record an orphan event.\n\n### One keystone per exchange\n\nWalk the keystones in order, one per exchange; a keystone may yield\none or several events. Small opening move: what was read, which\nkeystones already have observed trigger material, then the first\nkeystone. Compress ceremony on request, never structure.\n\n## How to use this skill\n\n### Phase A — Ingest\n\nRead the keystones file (default: `KEYSTONES.md` in the current\ndirectory — ideally already honed with deal-breaker qualifiers; if\nthe change log shows no honing, proceed but note the segments may\nstill be over-broad). Ask what customer evidence exists and read\nwhatever is offered: a customer-interview findings report,\nper-interview debrief files, survey exports, or just the user's\nrecall of what recent customers said prompted them. If no keystones\nfile exists, don't map triggers for unknown targets: offer the\non-ramp — run the keystones step first (if a keystones skill from\nthis method's author is installed, for example *Keystones* \u002F\n`asb-carol-keystones`, name it), or capture a minimal keystone list\nin chat with the caveat that unvetted keystones yield unvetted\nevents. If an INCITING-EVENTS.md exists: in-progress header means\nresume — and anything not in the file was never settled; re-derive\nit from the evidence rather than reconstructing the dead session's\nhalf-proposal from anyone's memory. Complete means ask whether to\nrevise. (The presence of per-interview debrief files in the\nquestion-mapped format is itself evidence the interview process is in\nuse — harvest them without asking.)\n\nOutput: `INCITING-EVENTS.md` in the same directory. If the input was pasted and no path is known, ask where the method's files should live before creating anything (default: the current directory) — never scatter files silently.\n\n### Phase B — Walk the keystones\n\nOpen small: what you read, which keystones already carry observed\ntrigger stories in the evidence, then the first keystone. Per\nkeystone:\n\n1. **Harvest observed events** from the evidence — the customers'\n   own words, with source (\"FINAL-REPORT.md F5\" \u002F \"the debrief from\n   the June 12 interview\" \u002F \"user's recall of the Meridian deal\").\n2. **Hypothesize the gaps** through the lenses, marked as such.\n3. **Press each event vivid** — the moment, the emotion, the number.\n4. **Findability** — how to detect or reach someone in that\n   condition, including their likely search phrases; if it can't be\n   detected from outside, say so.\n5. **Record** with [K-number], evidence status, and findability;\n   move to the next keystone.\n\n**Record to the file as you go.** Create `INCITING-EVENTS.md` at the\nfirst settled event; keep the header pointer current (\"Keystones\nwalked: K1; currently on: K2\"). The file is the memory, not the chat.\n\n### Phase C — Sweep and close\n\n- **Coupling check** — every event cites a keystone; every keystone\n  has at least one event or an honest gap note (\"no trigger known\n  yet — ask the next five customers what prompted them\").\n- **Evidence audit** — the batch press (delegated or self-run):\n  no hypothesized event reads as fact; no observed event lacks its\n  source; nothing generic survived.\n- **Validation path** — for the hypothesized events, note the\n  question to ask customers (\"what prompted you to start looking?\")\n  and when (right after purchase, while fresh). If a\n  customer-interview process from this method's author is installed\n  (its goal-setting skill is `asb-interview-goals`), name it as the\n  systematic way to run that validation; otherwise describe it: ask\n  new customers at onboarding, every time, and keep the answers.\n\nFinalize (remove the header) and close with the handoff: the next\nstep synthesizes everything — strengths, keystones, deal-breakers,\nand these events — into the ideal-customer definition; if a\ndefinition skill from this method's author is installed (for example\n*Define Carol* \u002F `asb-carol-define`), name it: \"when you're ready,\nrun `asb-carol-define` on these files.\"\n\n### The file structure\n\n```markdown\n# Inciting events — \u003Ccompany \u002F project name>\n\n> ⚠️ IN PROGRESS — the walk is not complete. Keystones walked:\n> \u003Cwhich>; currently on: \u003CK-number>. If you are resuming, continue\n> there. (This note is removed at finalization.)\n\n\u003CTwo or three lines: which keystones file this maps triggers for\n(name it), what customer evidence was available, and the standing\nrule — observed events carry sources; hypothesized events are\nguesses to validate with customers, not facts.>\n\n## Inciting events\n\n**E1.** \u003CThe specific trigger moment, written vividly — what\nhappened, what it cost, how it felt.>    [K2] — OBSERVED\n    Source: \u003Cwhere this story came from.>\n    Findability: \u003Chow to detect\u002Freach someone in this condition;\n    likely search phrases in quotes.>\n\n**E2.** \u003C…>    [K1] — HYPOTHESIZED (validate: ask new customers what\n    prompted them to look)\n    Findability: \u003C…>\n\n## Gaps\n\n- \u003CK-number> — no trigger known yet; \u003Cthe question to ask the next\n  customers>.\n\n## Next steps\n\n\u003CTwo or three sentences of prose: validate the hypothesized events by\nasking customers — right after purchase, while fresh — what prompted\nthem to start looking; then synthesize strengths, keystones,\ndeal-breakers, and these events into the ideal-customer definition.\nThat's the final step of the method, and it works from all four\nfiles.>\n```\n\nE-numbers are stable once written. Never renumber; an event whose\nstatus changes (hypothesized → observed, once customers confirm it)\nkeeps its number and gains its source.\n\n## Refusal conditions\n\n- **No keystones.** Triggers mapped without targets describe\n  everyone's bad week. Offer the keystones step or the caveated\n  quick capture.\n- **Brainstorms dressed as evidence.** A hypothesized event never\n  loses its label because the user is sure. It converts to observed\n  when a real customer account backs it — that's what the validation\n  path is for.\n- **Generic events, however insisted.** \"When they realize they need\n  something better\" is not recorded in any form; the specific moment\n  behind a true trigger always exists, and pressing for it is the\n  work.\n- **Orphan events.** An event coupled to no keystone is a flag —\n  either off-target or a missing keystone worth taking back to that\n  file — never an entry.\n- **Writing the ads.** The events are the raw material for\n  advertising and positioning; writing the copy is downstream work\n  with its own craft. Findability notes point at where and to whom;\n  the words come later.\n- **Inventing customer quotes.** Observed means a real account from\n  a real customer with a source. Fabricated color poisons the file's\n  one advantage over guessing.\n","# Inciting Events: What Makes Them Buy Today\n\nA prospect can agree the product is a great fit, the keystone is\nexactly what they want, there are no deal-breakers, the price is fair —\nand still not buy. Their excuse is genuine: \"we can't implement this\nright now; call back in nine months.\" The person with buying power has\none to three top priorities, and you aren't one of them. What promotes\nyou to the top is an **inciting event**: nobody wakes up randomly\ndeciding today's the day to buy — something happens in their life, a\nmoment of struggle where action *must* be taken. This skill maps those\nmoments, keystone by keystone.\n\n## The mental model\n\n### The inciting event completes the purchase\n\nThree forces, in order: **inciting events are why people buy\nanything** (the struggle that forces action now), **keystones are why\nthey buy from you** (the circumstance that makes your strength\ncritical), and **deal-breakers carve off exclusions**. A keystone\nmeans the customer *could* care about the issue; the inciting event is\nwhat raises it to a top-three priority they want solved today. That is\nwhy every real inciting event couples to a keystone — an event with no\nkeystone attached is a trigger to buy *something else*. The canonical\npairs: the speed keystone's events were \"the SEO consultant said poor\nperformance is blocking our rankings\" and \"we saw the study showing\nfaster sites convert more revenue\"; the scale keystone's event was\n\"the biggest traffic day of the year crashed the site — never again\";\nthe security keystone's was \"we got hacked, it was terrifying, we paid\na consultant $300 an hour and we're still not sure it's fixed\"; the\nsupport keystone's was \"we called for help and were told 'all we do is\nkeep your server powered on.'\"\n\n### Observed beats hypothesized — and both get marked\n\nThe reliable way to identify inciting events is to ask customers what\nprompted them to start looking and why they chose you — ideally right\nafter purchase, while the answer is fresh. So when interview evidence\nexists (a findings report, per-interview debrief files, onboarding\nsurvey answers), harvest it FIRST: real trigger stories, in the\ncustomers' words, marked **observed** with their source. Only then\nwork backward for the gaps, and mark those **hypothesized** — honest\nlabels, because a hypothesized event is a guess wearing a plan, and\nthe next round of customer conversations should test it. Never dress\na brainstorm as evidence.\n\n### The work-backward lenses\n\nWhen hypothesizing, ask: what would compel a customer to act *today*,\nwith urgency, with budget, with pre-approval? Brainstorm through these\nlenses:\n\n- **Crises that force immediate action** — a public breach or data\n  loss; a critical vendor acquired or shut down; a key customer\n  ultimatum; a lawsuit or regulatory investigation; executive\n  turnover; a PR debacle; a competitor announcement that exposes a\n  gap.\n- **Seasonal and recurring cycles** — annual planning, fiscal\n  year-end, tax season, quarterly reviews, compliance audits,\n  conference deadlines, the industry's peak season approaching.\n- **Strategic windows** — a compliance deadline, a required\n  certification, entering a new market, an acquisition closing, IPO\n  prep, legacy-system modernization, new funding creating budget and\n  expectations at once.\n- **Personal life-changes** (for consumer and solo-professional\n  products) — becoming a parent, retiring, a health diagnosis, a\n  death in the family, marriage or divorce, starting a business,\n  changing jobs, graduating, buying a first home.\n\n### Findability makes the file operational\n\nFor each event, answer: **how do you find prospects in this condition?**\nSomeone whose site was just hacked isn't searching \"secure hosting\" —\nthey're searching \"how to tell whether my site is hacked\" and posting\n\"Help! My site is hacked!\" into the void. Findability signals include:\nofficial announcements, executive podcast appearances, product\nlaunches and press tours, changes in job postings, recurring\ncomplaints in reviews or social media, analyst reports, regulatory\nchange notices, leadership changes, funding news — and above all, the\nexact phrases a person in that moment types into a search box. An\nevent you can't detect from outside is still worth recording, but say\nso: it can only be exploited in messaging (\"if this just happened to\nyou…\"), not targeting. Events are often split — the lawsuit half of\nan enforcement event is public record while the audit-notice half is\ninvisible; annotate which parts are targetable and which are\nmessaging-only. If the user asks you to research the triggers — recent\nregulatory changes, funding news, seasonal cycles, competitor moves —\nconfirm them with current results from your search tools; do not rely\non internal (training) knowledge, which is stale and misses this\nyear's real events.\n\n### Vivid or it doesn't advertise\n\nIn advertising, the inciting event often outperforms the keystone,\nbecause it speaks to the customer's current experience — they're\nreacting to their circumstance, not shopping for product attributes.\nThat only works if the event is written vividly: the specific moment,\nthe emotion, the number. \"A hacked website is a personal violation —\nyou pay a consultant $300 an hour and still wonder if it's coming\nback\" advertises; \"customers get frustrated with their host\" doesn't.\nGeneric events (\"realizes they need a better solution\") are not\nrecorded, in any form — there is always a specific moment inside a\ntrue trigger, and finding it is the work.\n\n### Vocabulary\n\n- **Inciting event (E1, E2, …)** — the specific trigger moment that\n  moves a keystone-fit customer to buy now; cites its [K-number].\n- **Observed \u002F hypothesized** — evidence status: harvested from real\n  customer accounts (with source) vs. worked backward (to be\n  validated). Two sanctioned shadings: \"OBSERVED (from memory)\" for\n  the user's recall of a real account — genuine evidence, weaker\n  sourcing, re-confirm at validation; and a composite of repeated\n  sales-call patterns with no single account stays HYPOTHESIZED. A\n  hypothesized event may cite supporting-but-not-triggering evidence\n  (\"plausibility supported — not evidenced — by the June debrief's\n  standing dread\") without gaining a Source line.\n- **Findability** — how prospects in the event's condition can be\n  detected or reached from outside, including their likely search\n  phrases.\n\n## The mapper's posture\n\n### Be clear, not clever\n\nWrite to be understood, not admired. The work here wrestles with hard\nconcepts, and clever metaphors, wordplay, or cute turns of phrase make\nthem harder to grasp, not easier. Say plainly what you mean. If a\nsentence reads more clearly without a flourish, cut the flourish. State\nthe actual point rather than gesturing wittily at it.\n\n### Restate references; never cite a bare token\n\nWhen you mention a numbered or lettered item to the user — K4, W2,\nO17, H3, and the like — add a few plain words on what it actually is\n(\"K4 — the owner whose career rides on the site\"). A bare token is\nunreadable to a human who saw it defined hours or days ago: the tag is\nfor traceability, the gloss is for comprehension. Keep the tag for\naccuracy; always add the gloss.\n\n### Harvest before you brainstorm\n\nIf interview artifacts exist — a findings report with trigger\nstories, per-interview debrief files, exit or onboarding surveys —\nread them first and pull every trigger story into candidate events\nbefore hypothesizing anything — and record harvested events as they\nconfirm, even when they belong to keystones later in the walk;\nE-numbers run in settle order, not keystone order. The user's memory counts too (\"what\ndid your last three customers say prompted them to look?\"), marked\nobserved-from-memory. Only where the evidence runs out do the lenses\ncome out. If the user has no interview evidence at all, say plainly\nthat everything in this file will be hypothesized until customers are\nasked — and that asking is the validation path.\n\n### Press moments into vividness\n\nWhen the user offers a vague trigger (\"when they get fed up with\ntheir current tool\"), press for the moment: fed up *by what incident*?\nWhat happened that morning? What did it cost? What did they type into\nGoogle that night? A predefined way to press harder: if a\ndevil's-advocate interrogation skill is installed in the environment\n(for example *Rude Q&A* \u002F `asb-rude-qa`, from the same author as this\nmethod), invoke it against the draft with this brief: *attack these\ninciting events — find every one that's a mood rather than a moment,\nevery one no real customer story or plausible circumstance backs,\nevery \"hypothesized\" that's being treated as fact, and every\nfindability note too vague to act on. Don't accept wishful or\nhand-wavy defenses.* If no such skill is available, run that\ninterrogation yourself, visibly — candidates inline, the batch attack\nat the closing sweep.\n\n### Couple every event to a keystone\n\nAn event that couples to no keystone is a flag, not an entry: either\nit's a trigger to buy something you don't sell, or it's pointing at a\nkeystone the earlier steps missed. Say which it looks like; if the\nuser believes a real keystone is missing, that's a finding to take\nback to the keystones file — not a reason to record an orphan event.\n\n### One keystone per exchange\n\nWalk the keystones in order, one per exchange; a keystone may yield\none or several events. Small opening move: what was read, which\nkeystones already have observed trigger material, then the first\nkeystone. Compress ceremony on request, never structure.\n\n## How to use this skill\n\n### Phase A — Ingest\n\nRead the keystones file (default: `KEYSTONES.md` in the current\ndirectory — ideally already honed with deal-breaker qualifiers; if\nthe change log shows no honing, proceed but note the segments may\nstill be over-broad). Ask what customer evidence exists and read\nwhatever is offered: a customer-interview findings report,\nper-interview debrief files, survey exports, or just the user's\nrecall of what recent customers said prompted them. If no keystones\nfile exists, don't map triggers for unknown targets: offer the\non-ramp — run the keystones step first (if a keystones skill from\nthis method's author is installed, for example *Keystones* \u002F\n`asb-carol-keystones`, name it), or capture a minimal keystone list\nin chat with the caveat that unvetted keystones yield unvetted\nevents. If an INCITING-EVENTS.md exists: in-progress header means\nresume — and anything not in the file was never settled; re-derive\nit from the evidence rather than reconstructing the dead session's\nhalf-proposal from anyone's memory. Complete means ask whether to\nrevise. (The presence of per-interview debrief files in the\nquestion-mapped format is itself evidence the interview process is in\nuse — harvest them without asking.)\n\nOutput: `INCITING-EVENTS.md` in the same directory. If the input was pasted and no path is known, ask where the method's files should live before creating anything (default: the current directory) — never scatter files silently.\n\n### Phase B — Walk the keystones\n\nOpen small: what you read, which keystones already carry observed\ntrigger stories in the evidence, then the first keystone. Per\nkeystone:\n\n1. **Harvest observed events** from the evidence — the customers'\n   own words, with source (\"FINAL-REPORT.md F5\" \u002F \"the debrief from\n   the June 12 interview\" \u002F \"user's recall of the Meridian deal\").\n2. **Hypothesize the gaps** through the lenses, marked as such.\n3. **Press each event vivid** — the moment, the emotion, the number.\n4. **Findability** — how to detect or reach someone in that\n   condition, including their likely search phrases; if it can't be\n   detected from outside, say so.\n5. **Record** with [K-number], evidence status, and findability;\n   move to the next keystone.\n\n**Record to the file as you go.** Create `INCITING-EVENTS.md` at the\nfirst settled event; keep the header pointer current (\"Keystones\nwalked: K1; currently on: K2\"). The file is the memory, not the chat.\n\n### Phase C — Sweep and close\n\n- **Coupling check** — every event cites a keystone; every keystone\n  has at least one event or an honest gap note (\"no trigger known\n  yet — ask the next five customers what prompted them\").\n- **Evidence audit** — the batch press (delegated or self-run):\n  no hypothesized event reads as fact; no observed event lacks its\n  source; nothing generic survived.\n- **Validation path** — for the hypothesized events, note the\n  question to ask customers (\"what prompted you to start looking?\")\n  and when (right after purchase, while fresh). If a\n  customer-interview process from this method's author is installed\n  (its goal-setting skill is `asb-interview-goals`), name it as the\n  systematic way to run that validation; otherwise describe it: ask\n  new customers at onboarding, every time, and keep the answers.\n\nFinalize (remove the header) and close with the handoff: the next\nstep synthesizes everything — strengths, keystones, deal-breakers,\nand these events — into the ideal-customer definition; if a\ndefinition skill from this method's author is installed (for example\n*Define Carol* \u002F `asb-carol-define`), name it: \"when you're ready,\nrun `asb-carol-define` on these files.\"\n\n### The file structure\n\n```markdown\n# Inciting events — \u003Ccompany \u002F project name>\n\n> ⚠️ IN PROGRESS — the walk is not complete. Keystones walked:\n> \u003Cwhich>; currently on: \u003CK-number>. If you are resuming, continue\n> there. (This note is removed at finalization.)\n\n\u003CTwo or three lines: which keystones file this maps triggers for\n(name it), what customer evidence was available, and the standing\nrule — observed events carry sources; hypothesized events are\nguesses to validate with customers, not facts.>\n\n## Inciting events\n\n**E1.** \u003CThe specific trigger moment, written vividly — what\nhappened, what it cost, how it felt.>    [K2] — OBSERVED\n    Source: \u003Cwhere this story came from.>\n    Findability: \u003Chow to detect\u002Freach someone in this condition;\n    likely search phrases in quotes.>\n\n**E2.** \u003C…>    [K1] — HYPOTHESIZED (validate: ask new customers what\n    prompted them to look)\n    Findability: \u003C…>\n\n## Gaps\n\n- \u003CK-number> — no trigger known yet; \u003Cthe question to ask the next\n  customers>.\n\n## Next steps\n\n\u003CTwo or three sentences of prose: validate the hypothesized events by\nasking customers — right after purchase, while fresh — what prompted\nthem to start looking; then synthesize strengths, keystones,\ndeal-breakers, and these events into the ideal-customer definition.\nThat's the final step of the method, and it works from all four\nfiles.>\n```\n\nE-numbers are stable once written. Never renumber; an event whose\nstatus changes (hypothesized → observed, once customers confirm it)\nkeeps its number and gains its source.\n\n## Refusal conditions\n\n- **No keystones.** Triggers mapped without targets describe\n  everyone's bad week. Offer the keystones step or the caveated\n  quick capture.\n- **Brainstorms dressed as evidence.** A hypothesized event never\n  loses its label because the user is sure. It converts to observed\n  when a real customer account backs it — that's what the validation\n  path is for.\n- **Generic events, however insisted.** \"When they realize they need\n  something better\" is not recorded in any form; the specific moment\n  behind a true trigger always exists, and pressing for it is the\n  work.\n- **Orphan events.** An event coupled to no keystone is a flag —\n  either off-target or a missing keystone worth taking back to that\n  file — never an entry.\n- **Writing the ads.** The events are the raw material for\n  advertising and positioning; writing the copy is downstream work\n  with its own craft. Findability notes point at where and to whom;\n  the words come later.\n- **Inventing customer quotes.** Observed means a real account from\n  a real customer with a source. Fabricated color poisons the file's\n  one advantage over guessing.\n",{"name":5,"description":7},"main","c9d0c408715983e993b2f9ebffdbfa7f10153bcb","business\u002Fasb-carol-inciting-events",0,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack","https:\u002F\u002Fgithub.com\u002FNairon-AI","https:\u002F\u002Fwww.naironai.com\u002F","Building the future of Work","2026-09-20 17:40:05",{"source":8,"skillName":5,"commands":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add Nairon-AI\u002Fagentic-starter-pack --skill asb-carol-inciting-events",{"tool":59,"command":60},"bunx","bunx skills add Nairon-AI\u002Fagentic-starter-pack --skill asb-carol-inciting-events",{"tool":62,"command":63},"pnpm","pnpm dlx skills add Nairon-AI\u002Fagentic-starter-pack --skill asb-carol-inciting-events","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fbusiness\u002Fasb-carol-inciting-events\u002FSKILL.md",true,[67,72],{"path":68,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},"LICENSE","许可证",18657,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fbusiness\u002Fasb-carol-inciting-events\u002FLICENSE",{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"NOTICE.md","REFERENCE","参考文档",454,"https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fbusiness\u002Fasb-carol-inciting-events\u002FNOTICE.md",[79,115,137,157,177,199],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":95,"publishedAt":39},"01M6RBCG630Y8X99XWR9Q4GYNY","writing-shape","Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-shape\u002FSKILL.md",[85,90],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,23],"writing","writing shape","shape","notes","help","file","markdown","format","session","use","take","draft","article","material","it","about","quotes","at","candidate",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":123,"publishedAt":39},"01M6RBCCCB1KMF01P5SYGFWBSW","writing-fragments","Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions \"fragments\", \"ideate\", or \"raw material\" for writing.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-fragments\u002FSKILL.md",[121,122],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[96,124,125,126,127,128,104,105,129,130,131,108,132,109,133,134,135,136,23],"writing fragments","grilling","ideate","develop","user","document","structure","ideas","as","sharp","claims","for","single",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":145,"publishedAt":39},"01M6RBC8V7NHHKMTAZB4BPXVYQ","writing-beats","Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fwriting-beats\u002FSKILL.md",[143,144],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[96,146,147,148,105,149,150,98,151,36,152,108,153,132,154,109,155,156,135,23],"writing beats","choose","write","assemble","only","journey","options","end","style","narrative","argument",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":165,"publishedAt":39},"01M6RBC58SG5Y5SC4ZV4ZNEFHC","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fstop-slop\u002FSKILL.md",[163,164],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[166,167,168,96,169,170,171,172,173,105,174,175,176,135,23],"stop","stop slop","slop","content","https","text","editing","remove","prose","patterns","drafts",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":185,"publishedAt":39},"01M6RBBJTTCJ7KZCP16G9JDFZH","humanizer","Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, passive\nvoice, negative parallelisms, and filler phrases.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Fhumanizer\u002FSKILL.md",[183,184],{"categoryNo":86,"categoryName":87,"taxonomyType":88,"taxonomyTypeDesc":89},{"categoryNo":91,"categoryName":92,"taxonomyType":93,"taxonomyTypeDesc":94},[179,96,186,187,171,188,148,189,190,173,191,192,175,193,194,195,196,197,198,23],"code","em dash","read","edit","generated","guide","opencode","three","human","make","wikipedia","vague","dash",{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":203,"categories":204,"keywords":205,"publishedAt":39},"01M6RBBEQKJ5HRH8AV9J85QB1T","feedback","Prepare, deliver, and debrief timely interpersonal feedback using a question-first coaching flow, observable behavior, owned experience, and concrete impact. Use when drafting feedback, coaching managers, rehearsing a feedback conversation, praising specific behavior, or reviewing whether feedback landed.","https:\u002F\u002Fgithub.com\u002FNairon-AI\u002Fagentic-starter-pack\u002Fblob\u002Fmain\u002Fwriting\u002Ffeedback\u002FSKILL.md",[],[201,206,207,208,209,210,105,211,212,213,214,215,23,216],"prepare","flow","first","question","behavior","conversation","coaching","debrief","impact","managers","deliver"]