Exported functions in state/lib/blog.ts. .md file to compare - side-by-side diff against blog
blog
description: "Triggers on prompt mention of 'blog'."
What it does for you
Turns your meetings and notes into a ready-to-post update.
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/blog/SKILL.md
present
state/lib/blog.ts
present
state/bin/blog/
not present
state/skills/blog/AGENTS.md
present
how it's graded - what counts as a good run 4 criteria · 2 deterministic · 2 judge
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 - ALWAYS run voice.checkTone() against any blog body before publish - em-dashes are dead AI tells in reader-facing prose (program.md §voice)
- Image-prompt frontmatter (layer_, metaphor_rationale, image_prompt) is §4a-exempt - em-dashes there go to DALL-E, not a reader (memory: feedback_image_prompts_not_4a)
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 { listBlogPosts, validateFrontmatter } from "state/lib/blog.ts"
npx tsx -e 'import("/Users/robertboulos/projects/snappy-os/state/lib/blog.ts").then(m => console.log(Object.keys(m)))'
SKILL.md- the skill, written out in plain English
blog
Blog MDX operations for all snappy-* skills.
Ported from kernel snappy-blog in Phase 0.5. See state/lib/blog.ts for the full API surface.
Steps
listBlogPosts()- seestate/lib/blog.tsvalidateFrontmatter()- seestate/lib/blog.ts
Eval
Actor: the exported functions in state/lib/blog.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: blog_ts_exists
kind: deterministic
check: "File 'state/lib/blog.ts' must exist."
- name: list_blog_posts_output_valid
kind: judge
check: "The output of listBlogPosts() accurately represents the blog posts available and their frontmatter data based on 'listBlogPosts_input'."
- name: frontmatter_validation_correct
kind: judge
check: "The validateFrontmatter() function correctly identifies valid and invalid frontmatter based on 'validateFrontmatter_input' and relevant schema definitions for blog posts."
- name: log_entry_created
kind: deterministic
check: "An entry for this skill's execution must be present in 'state/log/pending-eval.ndjson'."AGENTS.md- what the AI loads when this skill comes up
blog - loader
Per-turn rules for the blog skill. Full reference: state/skills/blog/SKILL.md. Do not skip these.
Critical Rules
_(no failures recorded yet - Phase 0.5 mechanical port from kernel snappy-blog. Read state/skills/blog/SKILL.md and state/lib/blog.ts before invoking.)_
- ALWAYS run
voice.checkTone()against any blog body before publish - em-dashes are dead AI tells in reader-facing prose (program.md §voice) - Image-prompt frontmatter (
layer_*,metaphor_rationale,image_prompt) is §4a-exempt - em-dashes there go to DALL-E, not a reader (memory: feedback_image_prompts_not_4a)
Commands
| ui model | live composition via compose_inline, persisted as artifact lang_body, reopened with OpenArtifact | |invoke: import { listBlogPosts, validateFrontmatter } from "state/lib/blog.ts" |verify: npx tsx -e 'import("/Users/robertboulos/projects/snappy-os/state/lib/blog.ts").then(m => console.log(Object.keys(m)))' |eval log: state/log/pending-eval.ndjson (skill: "blog")
Known Pitfalls
- Round-tripped drafts may show
,(space-comma-two-spaces) where em-dashes used to be -voice.tsdoesn't catch this artifact (memory: feedback_skool_emdash_backfill_artifact); scan for the literal string - Phase 0.5 port - kernel SKILL.md at
~/projects/snappy-kernel/skills/snappy-blog/is the long-form reference
Self-Test
An agent reading this should correctly:
- [ ] Run
checkTone()on body, but skip it forimage_promptfrontmatter - [ ] Scan for the
,em-dash backfill artifact - [ ] Use
validateFrontmatter()from the lib
<!-- kernel-ok: Phase 0.5 port pointer - kernel SKILL.md reference is a historical long-form link, not an active dependency -->
Found a gap? Edit this file. <!-- footer-injection-point -->
api.ts- the code it can call
#!/usr/bin/env npx tsx
/**
* snappy-blog/api.ts -- Blog MDX operations for all snappy-* skills.
*
* Usage:
* npx tsx api.ts list # list blog posts in the snappy.ai repo
* npx tsx api.ts validate <path> # validate MDX frontmatter
*
* Or import as module:
* import { listBlogPosts, validateFrontmatter } from "./blog.ts";
*
* Configuration:
* SNAPPY_BLOG_DIR - path to the blog content directory (MDX files).
* Defaults to ~/.snappy-os/blog when unset.
*/
import { existsSync, readFileSync, readdirSync, realpathSync } from "fs";
import { join } from "path";
import os from "os";
import { env } from "./env.ts";
const BLOG_DIR = process.env.SNAPPY_BLOG_DIR ?? join(os.homedir(), ".snappy-os", "blog");
const REQUIRED_FIELDS = ["title", "description", "date", "author", "authorRole", "category", "featured", "tags"];
const VALID_CATEGORIES = ["Strategy", "Engineering", "AI", "Business", "Case Study"];
interface PostInfo {
slug: string;
path: string;
title: string;
date: string;
category: string;
featured: boolean;
}
interface ValidationResult {
valid: boolean;
errors: string[];
warnings: string[];
}
/** Lists blog posts from the snappy.ai repo. */
export function listBlogPosts(): PostInfo[] {
if (!existsSync(BLOG_DIR)) return [];
const files = readdirSync(BLOG_DIR).filter((f) => f.endsWith(".mdx")).sort();
const posts: PostInfo[] = [];
for (const file of files) {
const content = readFileSync(join(BLOG_DIR, file), "utf-8");
const fm = parseFrontmatter(content);
posts.push({
slug: file.replace(".mdx", ""),
path: join(BLOG_DIR, file),
title: fm.title || "(untitled)",
date: fm.date || "(no date)",
category: fm.category || "(none)",
featured: fm.featured === true || fm.featured === "true",
});
}
return posts;
}
/** Validates MDX frontmatter against snappy-publish schema. */
export function validateFrontmatter(mdxContent: string): ValidationResult {
const errors: string[] = [];
const warnings: string[] = [];
const fm = parseFrontmatter(mdxContent);
if (!fm._found) {
errors.push("No YAML frontmatter found (must start with ---)");
return { valid: false, errors, warnings };
}
for (const field of REQUIRED_FIELDS) {
if (fm[field] === undefined || fm[field] === null || fm[field] === "") {
errors.push(`Missing required field: ${field}`);
}
}
if (fm.category && !VALID_CATEGORIES.includes(fm.category)) {
errors.push(`Invalid category "${fm.category}". Must be one of: ${VALID_CATEGORIES.join(", ")}`);
}
if (fm.tags && !Array.isArray(fm.tags)) {
errors.push("tags must be a YAML array, not a comma string");
}
if (fm.description && String(fm.description).length > 160) {
warnings.push(`description is ${String(fm.description).length} chars (should be < 160)`);
}
// Word count check
const body = mdxContent.split("---").slice(2).join("---").trim();
const wordCount = body.split(/\s+/).filter(Boolean).length;
if (wordCount < 800) warnings.push(`Body is ${wordCount} words (minimum 800)`);
if (wordCount > 1200) warnings.push(`Body is ${wordCount} words (maximum 1200)`);
return { valid: errors.length === 0, errors, warnings };
}
/** Simple YAML frontmatter parser (no dependencies). */
function parseFrontmatter(content: string): Record<string, any> {
const match = content.match(/^---\n([\s\S]*?)\n---/);
if (!match) return { _found: false };
const result: Record<string, any> = { _found: true };
const lines = match[1].split("\n");
let currentKey = "";
let inArray = false;
let arrayValues: string[] = [];
for (const line of lines) {
if (inArray) {
if (line.match(/^\s+-\s+/)) {
arrayValues.push(line.replace(/^\s+-\s+/, "").trim());
continue;
} else {
result[currentKey] = arrayValues;
inArray = false;
arrayValues = [];
}
}
const kvMatch = line.match(/^(\w+):\s*(.*)/);
if (kvMatch) {
const [, key, val] = kvMatch;
currentKey = key;
if (val.trim() === "") {
inArray = true;
arrayValues = [];
} else {
let parsed: any = val.trim().replace(/^["']|["']$/g, "");
if (parsed === "true") parsed = true;
if (parsed === "false") parsed = false;
result[key] = parsed;
}
}
}
if (inArray) result[currentKey] = arrayValues;
return result;
}
// --- CLI ---
if ((() => { try { return import.meta.url === `file://${realpathSync(process.argv[1])}`; } catch { return false; } })()) {
(async () => {
const [, , cmd, ...args] = process.argv;
switch (cmd) {
case "list": {
const posts = listBlogPosts();
console.log(`${posts.length} blog posts:`);
for (const p of posts) {
console.log(` ${p.date}\t${p.slug}\t${p.category}\t${p.featured ? "FEATURED" : ""}`);
}
break;
}
case "validate": {
const [path] = args;
if (!path) { console.error("Usage: api.ts validate <path>"); process.exit(1); }
const absPath = path.startsWith("/") ? path : join(BLOG_DIR, path);
const content = readFileSync(absPath, "utf-8");
const result = validateFrontmatter(content);
console.log(`Valid: ${result.valid}`);
for (const e of result.errors) console.log(` ERROR: ${e}`);
for (const w of result.warnings) console.log(` WARN: ${w}`);
break;
}
default:
console.log("Usage: npx tsx api.ts [list|validate] ...");
}
})();
}
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