sales-atypica

Name: sales-atypica
Author: sales-skills

86stars9forks

How to install sales-atypica?

sales-skills/sales/sales-atypica

$npx -y skills add sales-skills/sales --skill sales-atypica

Installs into the current project.

Summary

atypica.AI (atypica.ai) platform help — an AI research-agent platform that simulates consumers: build AI Personas from a four-layer \"subjective world model\", run AI-moderated Deep Interviews and studies against 300K synthetic + ~10K interview-grounded \"real person\" agents, an

Files · 1

View on GitHub

SKILL.md

1	# atypica.AI Platform Help
2
3	atypica.AI (atypica.ai) is an **AI research-agent platform that simulates
4	consumers. You build AI Personas on a four-layer "subjective world
5	model" (Expression → Story → Cognition → Behavior), run AI-moderated
6	interviews and studies** against them, and get an insights report in minutes — a
7	synthetic-research alternative to a traditional agency or focus group. Its cluster
8	edge is that persona construction and a flywheel (validate synthetic personas
9	against real interviews) aim beyond plain LLM roleplay, plus **~10K
10	interview-grounded "real-person" agents** alongside the 300K synthetic ones.
11
12	Its signal is directional, not demand: personas model existing/social/
13	interview/training data, so they skew agreeable, generic, and Western-biased
14	and can be confidently wrong. Treat any synthetic result as a **hypothesis to
15	disconfirm with real behavior**, never a green light.
16
17	## Step 1 — Gather context
18
19	If `references/learnings.md` exists, read it first for accumulated platform knowledge.
20
21	Ask only what you can't infer:
22
23	1. What do you want from atypica?
24	- A) Build a persona / run a study — set up an AI Persona or an AI Interview /
25	study, and read the insights report
26	- B) Embed atypica in your own app (mint an impersonation login URL so a user
27	lands in a study with no separate login)
28	- C) Provision team access via the API (list / create / invite members)
29	- D) Interpret a study/report you already ran, or decide whether to trust it
30	2. What's the research question and who's the audience? A sharp objective + a
31	well-defined persona yields usable answers; a vague one yields generic filler.
32
33	Skip-ahead: if the user wants to compare synthetic-research/persona/idea tools
34	across the market, or the validate-before-building method, that's a
35	`/sales-idea-validation` question — route in Step 2.
36
37	## Step 2 — Route or answer directly
38
39	\| If the user's question is about… \| Route to \|
40	\|---\|---\|
41	\| Comparing synthetic-research/persona/idea tools, or the validate-before-building method \| `/sales-idea-validation {question}` \|
42	\| Running a real demand test (smoke-test page, waitlist, pre-sale) after synthetic signal \| `/sales-idea-validation` or `/sales-funnel` `{question}` \|
43	\| Analyzing real-customer NPS/CSAT/VoC feedback (post-launch) \| `/sales-customer-feedback {question}` \|
44	\| A census-calibrated demographic panel with a free-tier API, or a documented studies REST API \| `/sales-ditto` or `/sales-syntheticusers` `{question}` \|
45
46	When routing, give the exact command: "This is a {domain} question — run: `/sales-idea-validation {original question}`"
47
48	Otherwise, answer atypica-specific questions using Step 3.
49
50	## Step 3 — atypica platform reference
51
52	Read `references/platform-guide.md` for the full reference — the three
53	capabilities + flywheel, the module → automation-surface table (what's API-
54	accessible vs UI-only), best-effort token/enterprise pricing, the data model (JSON
55	shapes for the team/embedding API), and quick-start recipes.
56
57	For raw endpoints, auth, JSON schemas, and error codes, read
58	`references/atypica-api-reference.md`.
59
60	Answer using only the relevant section — don't dump the full reference.
61
62	## Step 4 — Actionable guidance
63
64	- A synthetic "yes" is not demand — say so every time. Whatever the user asks,
65	make explicit that atypica's personas model existing/interview/training data, so
66	they run agreeable, generic, and Western-biased and can be **confidently
67	wrong. Frame every study result as a hypothesis to disconfirm with a real
68	behavior test** (smoke-test click, reply, pre-sale) — keep the *objections,
69	segments, and language* it surfaces (its real value), take the go/no-go from real
70	strangers, and route the r

People who liked this also viewed

6 picks

Type

sales-atypica

86stars9forks

View on GitHub

How to install sales-atypica?

sales-skills/sales/sales-atypica

$npx -y skills add sales-skills/sales --skill sales-atypica

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# atypica.AI Platform Help
2
3	atypica.AI (atypica.ai) is an **AI research-agent platform that simulates
4	consumers. You build AI Personas on a four-layer "subjective world
5	model" (Expression → Story → Cognition → Behavior), run AI-moderated
6	interviews and studies** against them, and get an insights report in minutes — a
7	synthetic-research alternative to a traditional agency or focus group. Its cluster
8	edge is that persona construction and a flywheel (validate synthetic personas
9	against real interviews) aim beyond plain LLM roleplay, plus **~10K
10	interview-grounded "real-person" agents** alongside the 300K synthetic ones.
11
12	Its signal is directional, not demand: personas model existing/social/
13	interview/training data, so they skew agreeable, generic, and Western-biased
14	and can be confidently wrong. Treat any synthetic result as a **hypothesis to
15	disconfirm with real behavior**, never a green light.
16
17	## Step 1 — Gather context
18
19	If `references/learnings.md` exists, read it first for accumulated platform knowledge.
20
21	Ask only what you can't infer:
22
23	1. What do you want from atypica?
24	- A) Build a persona / run a study — set up an AI Persona or an AI Interview /
25	study, and read the insights report
26	- B) Embed atypica in your own app (mint an impersonation login URL so a user
27	lands in a study with no separate login)
28	- C) Provision team access via the API (list / create / invite members)
29	- D) Interpret a study/report you already ran, or decide whether to trust it
30	2. What's the research question and who's the audience? A sharp objective + a
31	well-defined persona yields usable answers; a vague one yields generic filler.
32
33	Skip-ahead: if the user wants to compare synthetic-research/persona/idea tools
34	across the market, or the validate-before-building method, that's a
35	`/sales-idea-validation` question — route in Step 2.
36
37	## Step 2 — Route or answer directly
38
39	\| If the user's question is about… \| Route to \|
40	\|---\|---\|
41	\| Comparing synthetic-research/persona/idea tools, or the validate-before-building method \| `/sales-idea-validation {question}` \|
42	\| Running a real demand test (smoke-test page, waitlist, pre-sale) after synthetic signal \| `/sales-idea-validation` or `/sales-funnel` `{question}` \|
43	\| Analyzing real-customer NPS/CSAT/VoC feedback (post-launch) \| `/sales-customer-feedback {question}` \|
44	\| A census-calibrated demographic panel with a free-tier API, or a documented studies REST API \| `/sales-ditto` or `/sales-syntheticusers` `{question}` \|
45
46	When routing, give the exact command: "This is a {domain} question — run: `/sales-idea-validation {original question}`"
47
48	Otherwise, answer atypica-specific questions using Step 3.
49
50	## Step 3 — atypica platform reference
51
52	Read `references/platform-guide.md` for the full reference — the three
53	capabilities + flywheel, the module → automation-surface table (what's API-
54	accessible vs UI-only), best-effort token/enterprise pricing, the data model (JSON
55	shapes for the team/embedding API), and quick-start recipes.
56
57	For raw endpoints, auth, JSON schemas, and error codes, read
58	`references/atypica-api-reference.md`.
59
60	Answer using only the relevant section — don't dump the full reference.
61
62	## Step 4 — Actionable guidance
63
64	- A synthetic "yes" is not demand — say so every time. Whatever the user asks,
65	make explicit that atypica's personas model existing/interview/training data, so
66	they run agreeable, generic, and Western-biased and can be **confidently
67	wrong. Frame every study result as a hypothesis to disconfirm with a real
68	behavior test** (smoke-test click, reply, pre-sale) — keep the *objections,
69	segments, and language* it surfaces (its real value), take the go/no-go from real
70	strangers, and route the r

People who liked this also viewed

6 picks

Type