OR Key
drop another .md file to compare - side-by-side diff against skool-daily-post

skool-daily-post

Posts a daily tip or discussion prompt to your Skool community.
description: "Triggers on prompt mention of 'skool-daily-post'."
personal 2 files 10 recent evals
Export

What it does for you

Posts a daily tip or discussion prompt to your Skool community.

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

eval modeauto
categoryContent
stages2
dependscommunity

what's inside - the parts that make up a skill 2/4 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/skool-daily-post.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/skool-daily-post.ts not present
code the skill can run
Optional. Many skills are just words and need no code at all.
Scripts
state/bin/skool-daily-post/ not present
helper scripts
Optional. Added when a skill has a few commands to run.
Loader
state/skills/skool-daily-post.agents.md present
what the AI loads on the fly
Loaded automatically the moment this skill is needed. Kept short on purpose.

how it runs - the shared frame every skill uses 3/5 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
inferred
prose skill — from the run command
No worker is named directly, so the command this skill runs is treated as the worker.
checks the work The reviewer
not present

No separate check found. Without one, the part that makes the work could end up approving its own work, worth a closer look.

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/evals.ndjson unknown runs
Every run is written down here, so the next time this skill is used it already knows how the last runs went.
Critical rules the things this skill must not get wrong
  1. NEVER post the same topic twice in a 7-day window — read recent posts via state/lib/skool-fetcher.ts and dedupe BEFORE drafting
  2. ALWAYS run voice.checkTone() before posting — no post ships without passing the gate; em-dashes / hype words / personal-story openers HARD-BLOCK
  3. Every post MUST end with a question to invite replies — engagement-bait closers ("Agree?", "Thoughts?") still violate voice; phrase the question as genuine curiosity
  4. NEVER post personal stories ("I was…", "Last week I…") — Skool community is technical-report territory same as LinkedIn (memory: no_personal_stories)
  5. NEVER reference scarcity hooks ("idle hours", "leftover budget") — value-first only (memory: no_scarcity_offers)
  6. Serialize the upload — no parallel browser writes against the Skool session (memory: no_parallel_browser_writes)

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- step by step

inputs community
1 generator
invoke
prose skill — follow steps in `state/skills/skool-daily-post.md`
+ eval for this step
→
2 data
eval log
`state/log/evals.ndjson` (skill: "skool-daily-post")
+ eval for this step

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

skool-daily-post

Cron job (daily 9 AM). Creates a community post in the Skool group.

Steps

  1. Read recent Skool posts via state/lib/skool-fetcher.ts to avoid duplicates.
  2. Pick a topic from recent course content, student questions, or industry news.
  3. Draft a short post (2-4 paragraphs) that invites discussion.
  4. Run through state/lib/voice.ts check before posting.
  5. Post via agent-browser with Skool auth state.

Hard rules

  • Never post the same topic twice in a 7-day window.
  • Every post must end with a question to invite replies.
  • Run voice gate - no post ships without passing.

Eval

Score 1.0 if posted and voice-checked. Score 0.5 if drafted but not posted (scope-only). Score 0.0 if no topic could be selected.

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

skool-daily-post - loader

Per-turn rules for the skool-daily-post skill. Full reference: state/skills/skool-daily-post.md. Do not skip these.

Critical Rules

  • NEVER post the same topic twice in a 7-day window - read recent posts via state/lib/skool-fetcher.ts and dedupe BEFORE drafting
  • ALWAYS run voice.checkTone() before posting - no post ships without passing the gate; em-dashes / hype words / personal-story openers HARD-BLOCK
  • Every post MUST end with a question to invite replies - engagement-bait closers ("Agree?", "Thoughts?") still violate voice; phrase the question as genuine curiosity
  • NEVER post personal stories ("I was…", "Last week I…") - Skool community is technical-report territory same as LinkedIn (memory: no_personal_stories)
  • NEVER reference scarcity hooks ("idle hours", "leftover budget") - value-first only (memory: no_scarcity_offers)
  • Serialize the upload - no parallel browser writes against the Skool session (memory: no_parallel_browser_writes)

Commands

|invoke: prose skill - follow steps in state/skills/skool-daily-post.md |fetcher: state/lib/skool-fetcher.ts |voice gate: state/lib/voice.ts - checkTone() |upload: agent-browser with Skool auth state |eval log: state/log/evals.ndjson (skill: "skool-daily-post")

Known Pitfalls

  • Drafting a topic without first fetching the last 7 days of posts produces a duplicate that the eval catches AFTER the post lands
  • Skipping the voice gate for "just one short post" is the exact path that ships em-dashes
  • Closing with Thoughts? to satisfy the question rule still trips the voice gate's engagement-bait check

Self-Test

An agent reading this should correctly:

  1. [ ] Dedupe against the last 7 days of Skool posts before drafting?
  2. [ ] Run voice.checkTone() and refuse to post if it fails?
  3. [ ] End with a genuine question, not an engagement-bait closer?
  4. [ ] Serialize the post (no parallel browser writes against the same session)?

Self-report

If this loader fell short, append a line:

echo "[$(date -u +%FT%TZ)] skool-daily-post: <what was missing>" >> ~/.claude/logs/snappy-os-loader-feedback.log

api.ts- the code it can call

⚠ no api.ts - this skill has no typed action surface

scripts- helper scripts it can run

prose-only skill - no sidecar under state/bin/ yet. Steps, if any, are described in SKILL.md.

how we check it- the checks, plus the last 10 runs

rubric auto no rubric declared
recent mean 0.75 · 10 runs actor/auditor: unverifiable
deps community
timestamp verb score primary_issue artifact
2026-04-26 06:57Z - 0.50 - -
2026-04-25 04:11Z - 1.00 - -
2026-04-24 13:04Z - 0.50 - -
2026-04-23 13:14Z - 1.00 - -
2026-04-22 13:04Z - 0.50 - -
2026-04-21 15:58Z - 1.00 - -
2026-04-21 15:57Z - 1.00 - -
2026-04-21 13:04Z - 0.50 - -
2026-04-21 03:53Z - 1.00 - -
2026-04-20 13:02Z - 0.50 - -