drop another .md file to compare - side-by-side diff against update

update

Sends progress updates to your client channels.

description: "Triggers on prompt mention of 'update' as a client-comms skill."

personal 2 files 10 recent evals

Export

What it does for you

Sends progress updates to your client channels.

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/update.ts.

auditorNone wired yet - eval is manual (Robert review).

eval modeshape

categoryContent

stages1

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/update/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/update.ts present

code the skill can run

Reusable code this skill can call when it needs to.

Scripts

state/bin/update/ not present

helper scripts

Optional. Added when a skill has a few commands to run.

Loader

state/skills/update/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 · 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.

name

kind

check

recent_commits_fetched

deterministic

The getRecentCommits() function must be called with the provided getRecentCommits_input.

slack_message_sent

deterministic

The sendSlackMessage() function must be called with the provided sendSlackMessage_input.

text_message_sent

deterministic

The sendText() function must be called with the provided sendText_input.

pending_eval_logged

deterministic

A new row must be appended to state/log/pending-eval.ndjson for this skill execution.

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/update.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

ALWAYS run voice.checkTone() over the update body BEFORE sending — em-dashes / hype / personal-story openers HARD-BLOCK on client channels
Default to apply: false — preview the message and channel destination, then require explicit apply to send
Round-trip fetch after send — actor (channel write) ≠ auditor (independent fetch confirms post landed); score: 1.0 only on confirmed delivery
NEVER include author-scoreboard numbers ("shipped 14 commits this week") in client-facing updates (memory: numbers_decoy_rule)
NEVER reference scarcity ("idle hours / leftover budget") in client comms (memory: no_scarcity_offers)

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

actor Exported functions in state/lib/update.ts.

auditor None wired yet - eval is manual (Robert review).

1 data

eval log

`state/log/pending-eval.ndjson` (manual) — graduate to `state/log/evals.ndjson` once auditor is wired

+ eval for this step

SKILL.md- the skill, written out in plain English

update

Dev updates to client channels for all snappy-* skills.

Ported from kernel snappy-update in Phase 0.5. See state/lib/update.ts for the full API surface.

Steps

getRecentCommits() - see state/lib/update.ts
sendSlackMessage() - see state/lib/update.ts
sendText() - see state/lib/update.ts

Eval

Actor: the exported functions in state/lib/update.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: recent_commits_fetched
    kind: deterministic
    check: "The getRecentCommits() function must be called with the provided getRecentCommits_input."
  - name: slack_message_sent
    kind: deterministic
    check: "The sendSlackMessage() function must be called with the provided sendSlackMessage_input."
  - name: text_message_sent
    kind: deterministic
    check: "The sendText() function must be called with the provided sendText_input."
  - name: pending_eval_logged
    kind: deterministic
    check: "A new row must be appended to state/log/pending-eval.ndjson for this skill execution."

AGENTS.md- what the AI loads when this skill comes up

update - loader

Per-turn rules for the update skill. Full reference: state/skills/update/SKILL.md. Do not skip these.

Critical Rules

ALWAYS run voice.checkTone() over the update body BEFORE sending - em-dashes / hype / personal-story openers HARD-BLOCK on client channels
Default to apply: false - preview the message and channel destination, then require explicit apply to send
Round-trip fetch after send - actor (channel write) ≠ auditor (independent fetch confirms post landed); score: 1.0 only on confirmed delivery
NEVER include author-scoreboard numbers ("shipped 14 commits this week") in client-facing updates (memory: numbers_decoy_rule)
NEVER reference scarcity ("idle hours / leftover budget") in client comms (memory: no_scarcity_offers)

Commands

| ui dashboard | state/skills/update/resources/ui.openui | |library: state/lib/update.ts - getRecentCommits(), sendSlackMessage(), sendText() |voice gate: state/lib/voice.ts - checkTone() |eval log: state/log/pending-eval.ndjson (manual) - graduate to state/log/evals.ndjson once auditor is wired

OpenUI Resource

Skill-owned OpenUI Lang resource: state/skills/update/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

"Just sending a quick status" is the exact path that ships voice violations to a client channel; gate every send
Same-session toast / write-call return value is NOT verification - fetch from a separate session

Self-Test

An agent reading this should correctly:

[ ] Always voice-gate the update body before sending?
[ ] Default to scope-only (apply: false) and require explicit confirmation to send?
[ ] Strip author-scoreboard numbers and scarcity framing before they hit a client channel?

Self-report

If this loader fell short, append a line:

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

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)] update: <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-update/api.ts -- Dev updates to client channels for all snappy-* skills.
 *
 * Re-exports from slack and telegram for delivery. Adds GitHub commit
 * fetching for dev update generation.
 *
 * Usage:
 *   npx tsx api.ts commits owner/repo          # recent commits (7 days)
 *   npx tsx api.ts commits owner/repo 3        # commits from last 3 days
 *   npx tsx api.ts notify C09DD2D0S07 "text"   # post to slack channel
 *
 * Or import as module:
 *   import { getRecentCommits, slackPost, telegramPost } from "./update.ts";
 */

import { env } from "./env.ts";
import { realpathSync } from "fs";

// --- Re-exports from child skills ---

export { sendSlackMessage as slackPost } from "./slack.ts";
export { sendText as telegramPost } from "./telegram.ts";

// --- GitHub API ---

/**
 * Fetch recent commits from a GitHub repo via the GitHub API.
 * Requires GITHUB_TOKEN in .env.cache.
 */
export async function getRecentCommits(repo: string, days = 7): Promise<Array<{ sha: string; message: string; author: string; date: string }>> {
  const token = env("GITHUB_TOKEN");
  const since = new Date();
  since.setDate(since.getDate() - days);

  const res = await fetch(
    `https://api.github.com/repos/${repo}/commits?since=${since.toISOString()}&per_page=100`,
    {
      headers: {
        Authorization: `Bearer ${token}`,
        Accept: "application/vnd.github+json",
        "X-GitHub-Api-Version": "2022-11-28",
      },
    }
  );

  if (!res.ok) {
    const text = await res.text().catch(() => "");
    throw new Error(`GitHub commits API failed (${res.status}): ${text}`);
  }

  const data = await res.json();
  return data.map((c: { sha: string; commit: { message: string; author: { name: string; date: string } } }) => ({
    sha: c.sha.slice(0, 7),
    message: c.commit.message.split("\n")[0],
    author: c.commit.author.name,
    date: c.commit.author.date,
  }));
}

// --- CLI ---

if ((() => { try { return import.meta.url === `file://${realpathSync(process.argv[1])}`; } catch { return false; } })()) {
  (async () => {
    const { sendSlackMessage } = await import("./slack.ts");

    const [, , cmd, ...args] = process.argv;

    switch (cmd) {
      case "commits": {
        const repo = args[0];
        if (!repo) { console.error("Usage: api.ts commits <owner/repo> [days]"); process.exit(1); }
        const days = args[1] ? parseInt(args[1], 10) : 7;
        const commits = await getRecentCommits(repo, days);
        console.log(`${commits.length} commits in ${repo} (last ${days} days):\n`);
        for (const c of commits) {
          const date = new Date(c.date).toLocaleDateString("en-US", { month: "short", day: "numeric" });
          console.log(`  ${c.sha}  ${date}  ${c.message}`);
        }
        break;
      }
      case "notify": {
        const [channelId, ...textParts] = args;
        if (!channelId || !textParts.length) { console.error("Usage: api.ts notify <channel_id> <text>"); process.exit(1); }
        await sendSlackMessage(channelId, textParts.join(" "));
        console.log("sent");
        break;
      }
      default:
        console.log("Usage: npx tsx api.ts [commits|notify] ...");
    }
  })();
}

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 none declared

timestamp	verb	score	primary_issue	artifact
2026-04-25 04:11Z	-	1.00	-	-
2026-04-21 15:58Z	-	1.00	-	-
2026-04-21 15:57Z	-	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 15:57Z	-	1.00	-	-
2026-04-21 03:53Z	-	1.00	-	-
2026-04-25 04:11Z	-	1.00	-	-
2026-04-21 15:58Z	-	1.00	-	-