Exported functions in state/lib/offer.ts. .md file to compare - side-by-side diff against offer
offer
description: "Triggers on prompt mention of 'offer'."
What it does for you
Keeps your offer, pricing, and business model in one place.
What it produces
A recent result, so you can see the kind of work it returns.
loading…
How to get it
These run inside the Snappy workspace. Want this working in your business? I set skills like this up with you, in one focused week.
For developers how this skill is built, graded, and how it runs
at a glance- the short version
what's inside - the parts that make up a skill 3/4 present
A skill is just a few plain-text files. Only the main one is required. The rest are optional, added as the work needs them. This is what the skill is made of; how it runs is just below.
state/skills/offer/SKILL.md
present
state/lib/offer.ts
present
state/bin/offer/
not present
state/skills/offer/AGENTS.md
present
how it's graded - what counts as a good run 4 criteria · 4 deterministic
Each row is one thing a good run has to get right. deterministic means a quick check decides, pass or fail. judge means the AI reads the result and rates it. Grading each piece on its own (instead of one overall score) shows exactly where a run fell short, so the fix is obvious.
how it runs - the shared frame every skill uses 4/5 present
Every skill runs the same way. One part does the work, a separate part checks it, and a short loader hands the AI exactly what it needs for the job. Anything this skill doesn't use shows a one-line note saying why, on purpose, not by accident.
This skill doesn't fix its own gaps yet.
state/log/pending-eval.ndjson - NEVER frame offers with scarcity hooks - drafts MUST NOT reference "idle hours / leftover budget / limited time / spots left". Robert is system owner; value-first only.
- NEVER use Nx claims ("10x faster", "100x speed") in any offer copy - the voice gate blocks them
- NEVER write hype words (revolutionize, supercharge, unlock, leverage, seamless) in offer copy
- This skill exposes data; any GENERATED copy that consumes it must pass voice.checkTone() before reader exposure
what it has learned - fixes written back in over time sample
When a run hits something this skill didn't handle, the fix gets written back into the skill so it doesn't happen again. FIXED means it was corrected on the spot. LOGGED means it's queued for a bigger rewrite. Either way, the skill gets a little better and never makes the same mistake twice.
- Loading feedback rows…
how the work flows- who makes it, who checks it
import from `state/lib/offer.ts` - `getOffer()`, `getPricing()`, `getIcp()
SKILL.md- the skill, written out in plain English
offer
Business offer, model, and pricing data.
Ported from kernel snappy-offer in Phase 0.5. See state/lib/offer.ts for the full API surface.
Steps
getOffer()- seestate/lib/offer.tsgetPricing()- seestate/lib/offer.tsgetIcp()- seestate/lib/offer.ts
Eval
Actor: the exported functions in state/lib/offer.ts. Auditor: none wired yet - eval is manual (Robert review). File a state/log/pending-eval.ndjson row on each run.
Score convention:
| Outcome | Score |
|---|---|
| Pass on first try | 1.0 |
| Failed first, auto-fix applied, re-check passed | 0.5 |
| Still failing or unrecoverable | 0.0 |
Gotchas
via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)
realpathSync(process.argv[1])CLI guard wrapped in try/catch
- See the kernel SKILL.md for the original long-form guidance if you need it
(read-only reference at the kernel path above).
Graduation
This skill is prose. Graduate by defining a deterministic auditor and flipping eval: auto.
Rubric
criteria:
- name: calls_get_offer
kind: deterministic
check: "The skill execution successfully calls the getOffer() function from state/lib/offer.ts."
- name: calls_get_pricing
kind: deterministic
check: "The skill execution successfully calls the getPricing() function from state/lib/offer.ts."
- name: calls_get_icp
kind: deterministic
check: "The skill execution successfully calls the getIcp() function from state/lib/offer.ts."
- name: writes_pending_eval_log
kind: deterministic
check: "A new row is appended to state/log/pending-eval.ndjson after the skill execution."AGENTS.md- what the AI loads when this skill comes up
offer - loader
Per-turn rules for the offer skill. Full reference: state/skills/offer/SKILL.md. Do not skip these.
Critical Rules
- NEVER frame offers with scarcity hooks - drafts MUST NOT reference "idle hours / leftover budget / limited time / spots left". Robert is system owner; value-first only.
- NEVER use Nx claims ("10x faster", "100x speed") in any offer copy - the voice gate blocks them
- NEVER write hype words (revolutionize, supercharge, unlock, leverage, seamless) in offer copy
- This skill exposes data; any GENERATED copy that consumes it must pass
voice.checkTone()before reader exposure
Commands
| ui model | live composition via compose_inline, persisted as artifact lang_body, reopened with OpenArtifact | |invoke: import from state/lib/offer.ts - getOffer(), getPricing(), getIcp() |tone gate downstream: import { checkTone } from "../lib/voice.ts" and run on any draft that uses this data |eval log: state/log/pending-eval.ndjson (manual review until shape gate added)
Known Pitfalls
- Phase 0.5 port from
snappy-offer- the lib surface is mechanical, but downstream copy generation has the hard-won voice constraints (no scarcity, no hype, no Nx) - Skill frontmatter says
eval: shapebut no auditor wired - log topending-eval.ndjson
Self-Test
An agent reading this should correctly:
- [ ] Reject a generated offer draft that says "limited spots" or "before this fills up"?
- [ ] Run
voice.checkTone()on any reader-facing copy that consumes offer data? - [ ] Find the data accessors in
state/lib/offer.ts?
Found a gap? Edit this file. <!-- footer-injection-point -->
api.ts- the code it can call
#!/usr/bin/env npx tsx
/**
* snappy-offer/api.ts -- Business offer, model, and pricing data.
*
* Reads from local SKILL.md and sibling files. Pure data skill -- no external APIs.
*
* Usage:
* npx tsx api.ts offer # canonical offer definition
* npx tsx api.ts pricing # pricing tiers
*
* Or import as module:
* import { getOffer, getPricing } from "./offer.ts";
*/
import { existsSync, readFileSync, realpathSync } from "fs";
import { join, dirname } from "path";
import { fileURLToPath } from "url";
import { env } from "./env.ts";
const SKILL_DIR = dirname(fileURLToPath(import.meta.url));
function readSkillFile(filename: string): string {
const path = join(SKILL_DIR, filename);
if (!existsSync(path)) {
throw new Error(`[snappy-offer] ${filename} not found at ${path}`);
}
return readFileSync(path, "utf-8");
}
function extractSection(content: string, heading: string): string {
const pattern = new RegExp(`^##\\s+${heading}[^\\n]*\\n`, "m");
const match = content.search(pattern);
if (match === -1) return "";
const rest = content.slice(match);
const nextH2 = rest.indexOf("\n## ", 1);
return nextH2 === -1 ? rest.trim() : rest.slice(0, nextH2).trim();
}
// --- Public API ---
export function getOffer(): {
businessModel: string;
transformationStatement: string;
offerStack: string;
full: string;
} {
const skill = readSkillFile("SKILL.md");
return {
businessModel: extractSection(skill, "Business Model"),
transformationStatement: extractSection(skill, "Transformation Statement"),
offerStack: extractSection(skill, "Offer Stack"),
full: skill,
};
}
export function getPricing(): string {
if (existsSync(join(SKILL_DIR, "pricing.md"))) {
return readSkillFile("pricing.md");
}
const skill = readSkillFile("SKILL.md");
const section = extractSection(skill, "Pricing") || extractSection(skill, "Tier");
return section || "[snappy-offer] No pricing section found. Check SKILL.md.";
}
export function getIcp(): string {
if (existsSync(join(SKILL_DIR, "icp.md"))) {
return readSkillFile("icp.md");
}
const skill = readSkillFile("SKILL.md");
return extractSection(skill, "Ideal Client") || "[snappy-offer] No ICP section found.";
}
// --- CLI ---
if ((() => { try { return import.meta.url === `file://${realpathSync(process.argv[1])}`; } catch { return false; } })()) {
(async () => {
const [, , cmd] = process.argv;
switch (cmd) {
case "offer": {
const offer = getOffer();
console.log(offer.businessModel || offer.full.slice(0, 2000));
break;
}
case "pricing": {
console.log(getPricing());
break;
}
case "icp": {
console.log(getIcp());
break;
}
default:
console.log("Usage: npx tsx api.ts [offer|pricing|icp]");
}
})();
}
scripts- helper scripts it can run
prose-only skill - 1 inline code block live in SKILL.md above (no state/bin/ sidecar yet).
how we check it- the checks, plus the last 10 runs
no recent runs logged - the eval contract is declared but nothing has been graded yet