How Kaleidorabble Works
Kaleidorabble judges Bluesky accounts the way a careful person would: with several independent lines of evidence that are allowed to disagree, and a receipt for every conclusion. Here is the whole mix - including the point values, because a score you can't audit is just an accusation with extra steps.
Three lenses, kept separate
Most tools boil everything down to one mystery number. Kaleidorabble runs three different kinds of analysis, and deliberately does not blur them together, because they have different error rates and deserve different levels of trust:
A transparent point system over observable facts: follow ratios, posting volume, account age, profile completeness, bio phrasing, and the shape of the recent feed. Every point it awards is itemized.
Good at shapes (mass-follow churn, empty shells, firehoses). Ranks a review queue; never acts on its own.
Optional, using your own Gemini key: reads the bio, name, stats, and (for single checks) the avatar, and returns a category with written reasoning - genuine, spam, scam, engagement farm, and more.
Sees what regexes can't - tone, coherence, AI-generated faces. Refines the score; its reasoning appears on the receipt.
The algorithm, with the actual numbers
The structural score is a simple sum of named signals, capped at 100. Nothing hidden, nothing learned-in-the-dark - these are the real values:
Shape signals
| Signal | Fires when | Points |
|---|---|---|
| Mass-follow pattern | follows 2,000+ accounts, fewer than 10% follow back | +30 |
| Very low follow-back | follows 500+, under 5% follow back | +20 |
| Empty shell | zero posts but follows 100+ accounts | +25 |
| Follow-for-follow shape | thousands followed at a near 1:1 ratio with barely any posts - the mature engagement-farm silhouette | +20 |
| Firehose volume | an implausible posts-per-day rate for the account's age | +25 |
| Brand-new and aggressive | under 14 days old, already following 300+ | +20 |
Profile signals
| Signal | Fires when | Points |
|---|---|---|
| Spam bio | crypto/forex, "dm for promo", cashapp, giveaway-for-follow phrasing | +30 |
| Engagement-farming bio | "follow back", f4f, ifb, follow trains, "let's grow together" | +25 |
| Generated-looking handle | the classic word12345 shape | +15 |
| No avatar / empty profile | default avatar; no name and no bio | +10 each |
Feed signals (after a post scan)
| Signal | Fires when | Points |
|---|---|---|
| Repost amplifier | over 90% of the recent feed is reposts | +25 |
| Measured firehose | 100+ feed items per day, actually observed | +25 |
And the evidence that counts for you
| Signal | Effect |
|---|---|
| Established audience & history | score scaled down ×0.3-0.7 |
| Valid Bluesky verification | hard cap at 20 - a verified account can never be pushed into the flagged bands by heuristics |
| Self-declared automation (a labeled bot, labeler, or feed generator) | annotated, never penalized - honest robots are infrastructure, not spam |
The post-mix scan
On demand, Kaleidorabble reads an account's last ~100 feed items from the public API and splits them into original posts, replies, and reposts - drawn on every card as a three-color stripe. A feed that's 95% reposts at 200 items a day tells you more than any bio ever will. If an account hasn't been scanned, the receipt says so plainly: unobserved data is stated, never silently assumed.
The AI second opinion
With your own Gemini API key added (it's optional, and off until you add one), suspicious accounts can get a model's read: a 0-100 assessment, a category - genuine, inactive, promo, spam, bot, scam, or engagement farm - written reasoning, and for single checks, whether the avatar looks like a real photo, an AI-generated face, or ordinary art (which is completely normal on Bluesky and never counts against anyone).
When an AI verdict exists, the card's single score becomes a blend:
fresh verdict → score = 40% algorithm + 60% AI
old verdict (14+ days) → score = 70% algorithm + 30% AI
The receipt always shows the decomposition - algorithm 42 · AI 72 → blended 51 - so you can see exactly who said what.
Every score comes with a receipt
Click any score and you get the itemized evidence: each fired signal with its points, the moderation labels with the name of the service that applied them, the AI's category and reasoning, the exculpatory factors (verification, established history), what was not observed, and the scorer version that produced it. If Kaleidorabble can't show its work, it doesn't show a score - accounts whose profile facts were never fetched simply say not scored.
Your own score
The Overview tab points the same lens at the account being analyzed. You get your structural score, your post mix, and a concrete "improve it" list - each suggestion tagged with the points fixing it would remove. It's the fastest way to see your account the way other people's spam filters see it.
What Kaleidorabble refuses to do
- No automatic punishment. Scores rank a review queue. Every follow, unfollow, and block is a button you press, and bulk actions skip any account you've locked.
- No verdicts without evidence. Unscanned feeds, unfetched profiles, and missing data are stated on the receipt, never counted against anyone.
- No pretending a heuristic is a fact. A high score means "matches patterns worth your review" - the platform's own moderation labels are the only evidence treated as a settled call, and they're always attributed to their source.
- No silent public actions. Blocks on Bluesky are public records, and Kaleidorabble tells you so before you make one.
- No data leaves your browser by default. There's no Kaleidorabble server; analysis and storage are local. Only the optional AI layer sends profile text anywhere (directly from your browser to Google, with your key), and the page tells you what Google's free tier does with it.
The signals, weights, and thresholds are hand-built and honestly imperfect - accounts are scored one at a time, English bio patterns work best, and a clever farm can dodge any fixed rule. That's exactly why the three lenses stay separate, why receipts exist, and why the tool asks you to review before you act.
← Back to Kaleidorabble - sync any handle and click a score to see the receipts yourself.