OR Key
drop another .md file to compare - side-by-side diff against blog

blog

Turns your meetings and notes into a ready-to-post update.
description: "Triggers on prompt mention of 'blog'."
personal 2 files 10 recent evals

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.

Work with me
For developers how this skill is built, graded, and how it runs

at a glance- the short version

actorExported functions in state/lib/blog.ts.
auditorNone wired yet - eval is manual (Robert review).
eval modeshape
categoryContent
stages3
dependspublish, settings

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.

The skill
state/skills/blog/SKILL.md present
the skill itself, in plain text
The main file. It says what the skill is and lays out the steps in plain English.
Code
state/lib/blog.ts present
code the skill can run
Reusable code this skill can call when it needs to.
Scripts
state/bin/blog/ not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/blog/AGENTS.md present
what the AI loads on the fly
Loaded automatically the moment this skill is needed. Kept short on purpose.

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.

name
kind
check
blog_ts_exists
deterministic
File 'state/lib/blog.ts' must exist.
list_blog_posts_output_valid
judge
The output of listBlogPosts() accurately represents the blog posts available and their frontmatter data based on 'listBlogPosts_input'.
frontmatter_validation_correct
judge
The validateFrontmatter() function correctly identifies valid and invalid frontmatter based on 'validateFrontmatter_input' and relevant schema definitions for blog posts.
log_entry_created
deterministic
An entry for this skill's execution must be present in 'state/log/pending-eval.ndjson'.

how it runs - the shared frame every skill uses 5/5 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.

makes the work The worker
present
Exported functions in state/lib/blog.ts. the worker
Does the actual work. Whatever it produces is what gets checked next.
checks the work The reviewer
present
None wired yet - eval is manual (Robert review). the checker
A separate checker grades the work, so the part that made it can't approve its own work.
frame
learns Self-correction
present
fixes itself learns from gaps
When a run hits a gap, the skill gets edited on the spot [FIXED] or queued for a bigger rewrite [LOGGED], so it keeps getting better.
tidies up Background fixes
present
queued for rewrite runs in the background
Bigger fixes that can't be made on the spot get queued and rewritten in the background later.
remembers Run history
present
state/log/pending-eval.ndjson pending runs
Every run is written down here, then reviewed by hand each week.
Critical rules the things this skill must not get wrong
  1. ALWAYS run voice.checkTone() against any blog body before publish — em-dashes are dead AI tells in reader-facing prose (program.md §voice)
  2. 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.

  1. Loading feedback rows…

how the work flows- who makes it, who checks it

inputs publishsettings
actor Exported functions in state/lib/blog.ts.
1 generator
invoke
actor = Exported functions in state/lib/blog.ts.
import { listBlogPosts, validateFrontmatter } from "state/lib/blog.ts"
auditor None wired yet - eval is manual (Robert review).
2 auditor
inspect
auditor = None wired yet - eval is manual (Robert review).
npx tsx -e 'import("/Users/robertboulos/projects/snappy-os/state/lib/blog.ts").then(m => console.log(Object.keys(m)))'
3 data
eval log
`state/log/pending-eval.ndjson` (skill: "blog")

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() - see state/lib/blog.ts
  • validateFrontmatter() - see state/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:

OutcomeScore
Pass on first try1.0
Failed first, auto-fix applied, re-check passed0.5
Still failing or unrecoverable0.0

Gotchas

via the Phase 0.5 driver. Only these rewrites were applied: already in state/lib/)

  1. 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 dashboard | state/skills/blog/resources/ui.openui | |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")

OpenUI Resource

  • Skill-owned OpenUI Lang resource: state/skills/blog/resources/ui.openui. Read it before rendering or editing this skill's generated component surface.
  • Treat this resource as a first-class artifact of the skill, not a generic chat response. Improve it when the skill's user-facing output needs to become richer.
  • System resources compose OpenUI primitives and inherit SnappyChat tokens. Use ui_contract: branded in SKILL.md only for deliberate platform or client visuals.

Known Pitfalls

  • Round-tripped drafts may show , (space-comma-two-spaces) where em-dashes used to be - voice.ts doesn'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:

  1. [ ] Run checkTone() on body, but skip it for image_prompt frontmatter
  2. [ ] Scan for the , em-dash backfill artifact
  3. [ ] Use validateFrontmatter() from the lib

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] blog: <what was missing>" >> state/log/loader-feedback.log

<!-- kernel-ok: Phase 0.5 port pointer - kernel SKILL.md reference is a historical long-form link, not an active dependency -->


<!-- kernel-ok: historical attribution for the PID-loader pattern. -->

Self-correcting loader (PID feedback)

This is the rule that makes loaders learn. Ported from snappy-kernel, where it demonstrably worked: the snappy-dom-cartographer skill mapped Skool admin UI once, every later ship-agent inherited the full map for free.

Before you finish, do two things:

1. Fix gaps (P - proportional). MANDATORY. If this loader didn't cover your case - if you had to read another file, run an undocumented command, work around a wrong selector, or discover a quirk - you MUST attempt an Edit to this AGENTS.md before you log.

  • Default action: edit this file. Surgical. Add the missing line, table

row, or code example where it belongs. No restructuring.

  • Only LOGGED is allowed when: the fix needs >10 lines, spans multiple

files, or requires a structural rewrite. In that case the state/regen/drain.sh queue picks it up asynchronously.

  • "I didn't have time" / "it's minor" / "the next agent will figure it out"

are NOT valid reasons. Minor gaps compound - that's the whole point of this loop.

  • Concrete example of a valid P-fix: discover agent-browser screenshot

takes path positionally not as --output <path>. One line in a table. Edit it in. Do not just log it.

  • The goal: the next agent never has to leave the loader.

2. Log the result.

echo "[$(date -u +%FT%TZ)] blog: <what was missing or fixed> [FIXED|LOGGED]" >> state/log/loader-feedback.log
  • FIXED = you patched this loader inline (P-fix).
  • LOGGED = too large for inline; the PostToolUse enqueue + Stop-hook drain

will rewrite the loader from scratch on next session-end.

Do not skip this. Every agent run must leave the system better than it found it. The loader is the setpoint; you are the sensor; the gap is the error signal; closing the gap is the correction.

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";
 */

import { existsSync, readFileSync, readdirSync, realpathSync } from "fs";
import { join } from "path";
import { env } from "./env.ts";

const BLOG_DIR = "/Users/robertboulos/.openclaw/workspace/projects/snappy-website-claude/content/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

rubric shape schema-shape check (no inline rubric)
recent mean 1.00 · 10 runs actor/auditor: unverifiable
deps publish settings
timestamp verb score primary_issue artifact
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:58Z - 1.00 - -
2026-04-21 15:56Z - 1.00 - -
2026-04-21 03:53Z - 1.00 - -
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:58Z - 1.00 - -
2026-04-21 15:56Z - 1.00 - -
2026-04-21 03:53Z - 1.00 - -
2026-04-25 04:11Z - 1.00 - -
2026-04-21 15:58Z - 1.00 - -