How I drew all 11,064 bird species with Claude Code and Codex, and why the reviewer mattered more than the artist
I drew a sticker for every living bird species on Earth. All 11,064 of them, every species in the IOC World Bird List v15.2, and I've put them on GitHub along with structured data for each species: names in up to 43 languages, Wikidata / eBird / GBIF / iNaturalist IDs, range, subspecies, body measurements and IUCN status.
Repo: alchaincyf/huashu-bird-sticker
!Forty bird stickers with white outlines on a dotted cream background
Two things up front. First, I don't write code. Everything here was built by AI agents I directed: Claude Code as the orchestrator, Codex (with GPT-image) as the illustrator. Second, these are AI illustrations, not hand-painted, and not all of them are good. 7,676 meet the quality bar we set; 3,388 don't, and the data says which. I'd rather you hear that from me.
This post is about how a project this size gets done without falling apart, because I think the method transfers to anything with "do this 10,000 times, correctly".
Why birds, and why every species
Last December I spent some time in Sydney. Sulphur-crested cockatoos became my favourite bird almost immediately. There was a tree in the Royal Botanic Garden full of rainbow lorikeets, and an Australian white ibis smacked me on the head while charging at someone's chips. After that I started actually noticing the birds around me.
!Left: my photo of a sulphur-crested cockatoo in a Sydney park holding grass in its foot. Right: the sticker drawn from it
That's my photo on the left, and the cockatoo sticker in the repo is drawn from it (it scored 86, a pass).
A few weeks ago I was testing a design tool and had Claude Code mock up a birding app as a test case. The mock-up was good enough that I decided to build it for real. The idea is a sticker book: every time you identify a bird, you stick it into your own notebook with a date-and-city postmark. That means every species needs a sticker.
We started with China's birds, grew to 5,232 species, and then I said: all of them. The IOC list has 11,227 species; minus 163 extinct ones, that's 11,064.
Why not just use photos?
We did find a reference photo for every species. But by species, only 1,986 had openly licensed photos (CC0, public domain, CC BY, CC BY-SA). Many others were non-commercial, no-derivatives or all rights reserved, and for 2,017 we didn't record the license at the time. And photos shot from every angle, against every background, in every light, don't sit together on one page.
So photos became references only, and every sticker was redrawn.
The pipeline: four steps
Roles first:
- Claude Code (main session): planner and dispatcher. It owned the species list, the job queue and the rules.
- Claude subagents: finding references and reviewing finished stickers.
- Codex with GPT-image: drawing.
The principles that held it together:
1. Start from an authoritative list, and give every species a stable ID that every file hangs off.
2. Don't trust the image model's imagination. Give it a real reference for every single bird.
3. The reviewer must never be the model that drew the picture.
4. Decide in advance what happens to each kind of failure.
Step 1: a reference for every species
An image model drawing a bird from memory gets the bill curve, the eye colour and the number of toes wrong all the time. So every species gets a real photo first, mostly from iNaturalist and Wikimedia Commons. The source page, author and known license are recorded in each record's sticker.reference field.
For 453 obscure species there was no single usable photo (only distant shots, backs, half a bird). For those we built a reference board: 2 to 4 imperfect images tiled together, plus a written description of the field marks that must be right. The rule I set was "done beats perfect".
Step 2: draw nine at a time from the references
!Nine reference photos tiled in a grid, the same nine birds redrawn by GPT-image on grey, then cut out as stickers
Reference photos above, all from Wikimedia Commons, left to right, top to bottom: Blue-throated Bee-eater (Charles J. Sharp, CC BY-SA 4.0), Chinese Crested Tern (Oregon State University, CC BY-SA 2.0), White-throated Dipper (Mark Medcalf, CC BY 2.0), Siberian Sand Plover (Vedant Raju Kasambe, CC BY-SA 4.0), Plaintive Cuckoo (Charles J. Sharp, CC BY-SA 4.0), Pallas's Rosefinch (M.Nishimura, CC BY-SA 3.0), Red-tailed Minla (Shiv's fotografia, CC BY 4.0), Blue-tailed Bee-eater (Tisha Mukherjee, CC BY-SA 4.0), Orange-headed Thrush (JJ Harrison, CC BY-SA 3.0).
1. Tile 9 reference photos into one 3×3 grid (1254×1254 px, 418 px per cell).
2. Ask GPT-image to redraw the same 9 birds in the same cells: realistic texture, bird filling 50–60% of the cell, flat grey background, correct toe count, no watermarks.
3. Slice into 9, cut each out with BiRefNet, add a white outline.
Species with reference boards were drawn one at a time instead.
When a bird failed review, its next batch prompt got an extra "pay attention to" line with the reviewer's note pasted in verbatim, for example "toes must be zygodactyl, two forward and two back" or "the iris is red", and the redraw was checked specifically against it.
The grid route alone ran 2,760 batches and 16,339 bird draws including redraws. At peak, early on 30 October, there were 8 Codex sessions drawing, 8 reviewer subagents reviewing and 10 subagents building reference boards for the last 195 species without photos.
Things broke, of course. BiRefNet's memory crept up to 22 GB and froze the whole Mac. Codex keeps about 7 MB of session log per generated image, which quietly grew to 46 GB.
Step 3: score it, 80 to pass
Every AI sticker goes to a separate reviewer subagent that compares it with the reference and scores it out of 100. 80 or above passes.
The reviewer works through a checklist: iris colour, bill shape and length, every colour patch on the head and body, legs, feet and claws, tail shape, feather texture and the white outline, and whether last round's problems were fixed. Any single error caps the score at 76–78, so it can't pass.
Where something can't be verified (the eye isn't visible in the reference, say), the reviewer has to write that down instead of assuming it's fine. And every bird has to be zoomed in on, because many errors are invisible at thumbnail size.
The reviewer returns JSON, roughly like this (illustrative, not a real record):
{"<species id>": {"name": "Common name", "score": 78, "verdict": "fail",
"plumage": "sex / plumage drawn",
"issues": ["pay-attention item: fixed", "iris: drawn black, reference is red", "..."],
"redoNote": "what to change in the next redraw, and to what colour or shape"}}
A failed sticker's redoNote becomes the next round's "pay attention to" line.
Step 4: review the reviewer
On the evening of 29 October we took 270 stickers that Claude subagents had already reviewed and had Codex re-check them against the same standard. Claude had passed 88 that Codex failed; only 23 went the other way. Claude was too lenient.
The disagreements clustered in a few places: eyes drawn solid black where the reference shows a red, yellow or blue-green iris; toes fused into a lump or a hind toe with no claw; hummingbirds, with their tiny legs, standing like sparrows; elongated central tail feathers drawn as an ordinary tail.
So we rewrote the review instructions, listed those errors one by one, and made zooming in on every bird mandatory. After calibration, Claude agreed with Codex on 13 of 18 samples and was slightly stricter overall.
In the last round, the 852 borderline stickers scoring 80–82 also got a second blind review, and 211 of them failed it and were redrawn.
When a bird just won't come out right
Some birds won't draw well: the reference is too poor, or the model keeps getting one feature wrong. The rule: at most two redraws per species. If it still doesn't pass, keep the highest-scoring version. No falling back to a photo, no blank page.
That gives the honest result:
- 7,676 meet the bar: AI stickers scoring 80+, plus 34 photo cut-outs that passed a blind review against the original photo.
- 3,388 don't: 3,273 score 70–79, 109 score below 70, and 6 scored 80+ but failed the blind second review.
Every sticker's score and pass/fail is in the data (meetsQualityBar), so you can filter to only the ones that pass. The scores come from a model comparing against a reference photo, not from an ornithologist, and these are illustrations, not field-guide plates. For fine identification details, use a field guide.
If you want to build something similar
Swap birds for insects, plants or fish and I think it comes down to four things:
1. An authoritative checklist as the full set, with a stable ID per item that every file hangs off.
2. A real reference for every item, with its source and license recorded. Where there isn't one, a board of partial images plus a written description.
3. A reviewer that isn't the generator, with an itemised checklist and score caps; then a second model auditing the reviewer on a sample, and a blind second pass for anything sitting right on the line.
4. A cap on retries, keeping the best attempt and flagging it in the data.
What's in the repo, and how you can use it
!Twenty-four hummingbird stickers in iridescent greens, blues and reds
- 11,064 stickers: transparent WebP with a white outline, about 1,000 px on the long side, organised as stickers/<Order>/<Family>/<Genus_species>.webp.
- data/species.json / species.csv: one record per species: taxonomy, names, cross-database IDs, breeding and non-breeding range, subspecies, AVONET traits (mass, wing, tail, habitat, migration), IUCN and CITES status.
- data/names.csv: names in 43 languages from the IOC multilingual list.
Some ideas: a birding journal or printed sticker sheets, nature-education material and bird cards for kids, multilingual flashcards (the Common Kingfisher is カワセミ in Japanese and Eisvogel in German), or joining eBird/GBIF IDs to observation data for your own visualisations.
The full repo is about 700 MB. If you only want the data and one order (owls, say):
git clone --filter=blob:none --sparse https://github.com/alchaincyf/huashu-bird-sticker
cd huashu-bird-sticker && git sparse-checkout set data stickers/Strigiformes
Licenses. The stickers are under PolyForm Shield 1.0.0: free for almost anything, including commercial use, except using them in a product that competes with our app (another birding, bird-ID or field-guide app or site). Strictly speaking PolyForm Shield isn't an OSI open-source license; it's source-available. Our own data is MIT; third-party parts keep their terms (IOC multilingual names are CC BY 3.0). Whether a drawing made from a photo is bound by that photo's license is legally unsettled; if that matters for your use, you can filter by each sticker's reference source.
If one of the stickers was drawn from your photo and you'd rather it wasn't, open an issue or email me at alchaincyf@gmail.com and I'll replace it within 7 days.
The most useful contribution
Corrections from birders. AI has certainly drawn some of these birds wrong. If you spot one, please open an issue. That's worth more to this project than a star.
The stickers were made for Mingji, the iOS birding notebook I'm building; it's in App Store review now (Chinese interface first). I'll write about that when it's out.
Repo again: alchaincyf/huashu-bird-sticker
[self-promotion] All 11,064 living bird species (IOC 15.2): names in 43 languages, eBird/GBIF/Wikidata/iNat IDs, AVONET traits, IUCN status, plus an illustration for each
Disclosure: I made this, and the illustrations are AI-generated (details below).
I've been building a birding app and ended up assembling a species table for every living bird species in the IOC World Bird List v15.2 (11,064 species, 44 orders, 250 families). I've published it so other people don't have to stitch it together again.
What's in data/:
- species.json / species.csv: one record per species. Taxonomy (IOC sequence, order, family, genus), authority, breeding and non-breeding range, subspecies with ranges, AVONET traits (mass, wing, tail, habitat, migration, trophic niche), IUCN and CITES status, China national protection level
- Cross-database IDs: Wikidata 10,939, GBIF 10,649, eBird 10,052, plus iNaturalist
- names.csv: names in 43 languages from the IOC multilingual list. English is complete; French and Simplified Chinese nearly; Japanese and most European languages over 90%; Korean, Arabic, Thai and Persian only cover a few hundred to ~1,000 species, because that's what the IOC list has
- field-guide.zh-Hans.json: Chinese field-guide notes for 1,596 species (CC BY-SA 4.0)
Each record also points to a sticker (transparent WebP, ~1,000px) and to the reference photo it was drawn from, with author and license. 11,030 stickers are AI illustrations and 34 are photo cut-outs. Every AI sticker was scored against its reference by a separate model; 7,676 meet our bar and 3,388 don't, and that's a field (meetsQualityBar, reviewScore) so you can filter.
Licenses: our own data is MIT, third-party parts keep theirs (IOC names CC BY 3.0 etc., see NOTICE). The stickers are PolyForm Shield 1.0.0.
Repo: alchaincyf/huashu-bird-sticker
If you only want the data (the full repo is ~700MB because of the images):
git clone --filter=blob:none --sparse alchaincyf/huashu-bird-sticker
cd huashu-bird-sticker && git sparse-checkout set data
Happy to hear about mismatches. IOC vs eBird/Clements splits and lumps are where I expect most of the ID errors.
7 points
Mentions
16,339 bird drawings through Codex in about a week: what running 8 parallel image sessions taught me I used Codex (GPT-image) as the illustrator for an open-source sticker set covering all 11,064 living bird species: alchaincyf/huashu-bird-sticker Setup that worked: - 9 birds per call. Tile 9 reference photos into a 1254x1254 3x3 grid (418px cells) and ask for the same 9 birds redrawn in the same cells: realistic texture, bird filling 50-60% of the cell, flat grey background, correct toe count, no watermarks. Then slice, cut out with BiRefNet, add a white outline. - Failures feed the next prompt. When a bird fails review, the reviewer's note (e.g. "toes must be zygodactyl, two forward two back", "iris is red") goes into the next batch prompt as a "pay attention" line, and the redraw is checked specifically against it. - Codex as auditor, too. Re-checking 270 stickers another model had already passed showed that model was too lenient (88 vs 23 disagreements), which made us rewrite the review rubric. Numbers: 2,760 grid batches, 16,339 bird draws including redraws, 8 Codex sessions at peak, about a week. I went through the $200 weekly limit three times. Gotcha: each generated image left about 7MB in the Codex session logs. Ours reached 46GB before I noticed. If your disk is filling up mysteriously, check ~/.codex/sessions. Result: 7,676 of 11,064 pass our bar; the rest are flagged in the data. Happy to share the prompt structure if useful.
I made an illustrated sticker for every living bird species (11,064, IOC list). They're AI-drawn from reference photos, so I'd love birders to tell me which ones are wrong Hi all. Full disclosure first: these were drawn by AI, using a real reference photo for each species, then checked against that photo by a separate AI reviewer. They're not hand-painted and not field-guide plates. What I made: one sticker for every living species in the IOC World Bird List v15.2, with each species' names in up to 43 languages, ranges, subspecies and IUCN status. It's all free to download, for nature-journalling, kids' bird cards, classroom material, and so on. alchaincyf/huashu-bird-sticker Sources: the reference photo behind each sticker (mostly iNaturalist and Wikimedia Commons), with its author and license where known, is listed in the data for that species. Taxonomy and names are from the IOC list. Where it came from: last December in Sydney I fell for sulphur-crested cockatoos (the cockatoo sticker is drawn from one I photographed with a clump of grass in its foot), and since then I've been paying a lot more attention to birds. What I know is imperfect: about 7,700 of them pass our checklist (eye colour, bill, legs and toes, plumage pattern, tail shape), and about 3,400 don't. The data marks which. The commonest errors are iris colour, toe arrangement, and leg proportions on very small birds. So the most valuable thing you could do: if your local species looks wrong, open an issue (or just reply here and I'll file it). And if one was drawn from your photo and you'd rather it wasn't, tell me and I'll replace it within 7 days.
huashu-bird-sticker: a sticker for each of the 11,064 living bird species, with names in 43 languages and structured data (AI-drawn from reference photos, quality-scored)
How I drew all 11,064 bird species with Claude Code and Codex, and why the reviewer mattered more than the artist I drew a sticker for every living bird species on Earth. All 11,064 of them, every species in the IOC World Bird List v15.2, and I've put them on GitHub along with structured data for each species: names in up to 43 languages, Wikidata / eBird / GBIF / iNaturalist IDs, range, subspecies, body measurements and IUCN status. Repo: alchaincyf/huashu-bird-sticker !Forty bird stickers with white outlines on a dotted cream background Two things up front. First, I don't write code. Everything here was built by AI agents I directed: Claude Code as the orchestrator, Codex (with GPT-image) as the illustrator. Second, these are AI illustrations, not hand-painted, and not all of them are good. 7,676 meet the quality bar we set; 3,388 don't, and the data says which. I'd rather you hear that from me. This post is about how a project this size gets done without falling apart, because I think the method transfers to anything with "do this 10,000 times, correctly". Why birds, and why every species Last December I spent some time in Sydney. Sulphur-crested cockatoos became my favourite bird almost immediately. There was a tree in the Royal Botanic Garden full of rainbow lorikeets, and an Australian white ibis smacked me on the head while charging at someone's chips. After that I started actually noticing the birds around me. !Left: my photo of a sulphur-crested cockatoo in a Sydney park holding grass in its foot. Right: the sticker drawn from it That's my photo on the left, and the cockatoo sticker in the repo is drawn from it (it scored 86, a pass). A few weeks ago I was testing a design tool and had Claude Code mock up a birding app as a test case. The mock-up was good enough that I decided to build it for real. The idea is a sticker book: every time you identify a bird, you stick it into your own notebook with a date-and-city postmark. That means every species needs a sticker. We started with China's birds, grew to 5,232 species, and then I said: all of them. The IOC list has 11,227 species; minus 163 extinct ones, that's 11,064. Why not just use photos? We did find a reference photo for every species. But by species, only 1,986 had openly licensed photos (CC0, public domain, CC BY, CC BY-SA). Many others were non-commercial, no-derivatives or all rights reserved, and for 2,017 we didn't record the license at the time. And photos shot from every angle, against every background, in every light, don't sit together on one page. So photos became references only, and every sticker was redrawn. The pipeline: four steps Roles first: - Claude Code (main session): planner and dispatcher. It owned the species list, the job queue and the rules. - Claude subagents: finding references and reviewing finished stickers. - Codex with GPT-image: drawing. The principles that held it together: 1. Start from an authoritative list, and give every species a stable ID that every file hangs off. 2. Don't trust the image model's imagination. Give it a real reference for every single bird. 3. The reviewer must never be the model that drew the picture. 4. Decide in advance what happens to each kind of failure. Step 1: a reference for every species An image model drawing a bird from memory gets the bill curve, the eye colour and the number of toes wrong all the time. So every species gets a real photo first, mostly from iNaturalist and Wikimedia Commons. The source page, author and known license are recorded in each record's sticker.reference field. For 453 obscure species there was no single usable photo (only distant shots, backs, half a bird). For those we built a reference board: 2 to 4 imperfect images tiled together, plus a written description of the field marks that must be right. The rule I set was "done beats perfect". Step 2: draw nine at a time from the references !Nine reference photos tiled in a grid, the same nine birds redrawn by GPT-image on grey, then cut out as stickers Reference photos above, all from Wikimedia Commons, left to right, top to bottom: Blue-throated Bee-eater (Charles J. Sharp, CC BY-SA 4.0), Chinese Crested Tern (Oregon State University, CC BY-SA 2.0), White-throated Dipper (Mark Medcalf, CC BY 2.0), Siberian Sand Plover (Vedant Raju Kasambe, CC BY-SA 4.0), Plaintive Cuckoo (Charles J. Sharp, CC BY-SA 4.0), Pallas's Rosefinch (M.Nishimura, CC BY-SA 3.0), Red-tailed Minla (Shiv's fotografia, CC BY 4.0), Blue-tailed Bee-eater (Tisha Mukherjee, CC BY-SA 4.0), Orange-headed Thrush (JJ Harrison, CC BY-SA 3.0). 1. Tile 9 reference photos into one 3×3 grid (1254×1254 px, 418 px per cell). 2. Ask GPT-image to redraw the same 9 birds in the same cells: realistic texture, bird filling 50–60% of the cell, flat grey background, correct toe count, no watermarks. 3. Slice into 9, cut each out with BiRefNet, add a white outline. Species with reference boards were drawn one at a time instead. When a bird failed review, its next batch prompt got an extra "pay attention to" line with the reviewer's note pasted in verbatim, for example "toes must be zygodactyl, two forward and two back" or "the iris is red", and the redraw was checked specifically against it. The grid route alone ran 2,760 batches and 16,339 bird draws including redraws. At peak, early on 30 October, there were 8 Codex sessions drawing, 8 reviewer subagents reviewing and 10 subagents building reference boards for the last 195 species without photos. Things broke, of course. BiRefNet's memory crept up to 22 GB and froze the whole Mac. Codex keeps about 7 MB of session log per generated image, which quietly grew to 46 GB. Step 3: score it, 80 to pass Every AI sticker goes to a separate reviewer subagent that compares it with the reference and scores it out of 100. 80 or above passes. The reviewer works through a checklist: iris colour, bill shape and length, every colour patch on the head and body, legs, feet and claws, tail shape, feather texture and the white outline, and whether last round's problems were fixed. Any single error caps the score at 76–78, so it can't pass. Where something can't be verified (the eye isn't visible in the reference, say), the reviewer has to write that down instead of assuming it's fine. And every bird has to be zoomed in on, because many errors are invisible at thumbnail size. The reviewer returns JSON, roughly like this (illustrative, not a real record): {"<species id>": {"name": "Common name", "score": 78, "verdict": "fail", "plumage": "sex / plumage drawn", "issues": ["pay-attention item: fixed", "iris: drawn black, reference is red", "..."], "redoNote": "what to change in the next redraw, and to what colour or shape"}} A failed sticker's redoNote becomes the next round's "pay attention to" line. Step 4: review the reviewer On the evening of 29 October we took 270 stickers that Claude subagents had already reviewed and had Codex re-check them against the same standard. Claude had passed 88 that Codex failed; only 23 went the other way. Claude was too lenient. The disagreements clustered in a few places: eyes drawn solid black where the reference shows a red, yellow or blue-green iris; toes fused into a lump or a hind toe with no claw; hummingbirds, with their tiny legs, standing like sparrows; elongated central tail feathers drawn as an ordinary tail. So we rewrote the review instructions, listed those errors one by one, and made zooming in on every bird mandatory. After calibration, Claude agreed with Codex on 13 of 18 samples and was slightly stricter overall. In the last round, the 852 borderline stickers scoring 80–82 also got a second blind review, and 211 of them failed it and were redrawn. When a bird just won't come out right Some birds won't draw well: the reference is too poor, or the model keeps getting one feature wrong. The rule: at most two redraws per species. If it still doesn't pass, keep the highest-scoring version. No falling back to a photo, no blank page. That gives the honest result: - 7,676 meet the bar: AI stickers scoring 80+, plus 34 photo cut-outs that passed a blind review against the original photo. - 3,388 don't: 3,273 score 70–79, 109 score below 70, and 6 scored 80+ but failed the blind second review. Every sticker's score and pass/fail is in the data (meetsQualityBar), so you can filter to only the ones that pass. The scores come from a model comparing against a reference photo, not from an ornithologist, and these are illustrations, not field-guide plates. For fine identification details, use a field guide. If you want to build something similar Swap birds for insects, plants or fish and I think it comes down to four things: 1. An authoritative checklist as the full set, with a stable ID per item that every file hangs off. 2. A real reference for every item, with its source and license recorded. Where there isn't one, a board of partial images plus a written description. 3. A reviewer that isn't the generator, with an itemised checklist and score caps; then a second model auditing the reviewer on a sample, and a blind second pass for anything sitting right on the line. 4. A cap on retries, keeping the best attempt and flagging it in the data. What's in the repo, and how you can use it !Twenty-four hummingbird stickers in iridescent greens, blues and reds - 11,064 stickers: transparent WebP with a white outline, about 1,000 px on the long side, organised as stickers/<Order>/<Family>/<Genus_species>.webp. - data/species.json / species.csv: one record per species: taxonomy, names, cross-database IDs, breeding and non-breeding range, subspecies, AVONET traits (mass, wing, tail, habitat, migration), IUCN and CITES status. - data/names.csv: names in 43 languages from the IOC multilingual list. Some ideas: a birding journal or printed sticker sheets, nature-education material and bird cards for kids, multilingual flashcards (the Common Kingfisher is カワセミ in Japanese and Eisvogel in German), or joining eBird/GBIF IDs to observation data for your own visualisations. The full repo is about 700 MB. If you only want the data and one order (owls, say): git clone --filter=blob:none --sparse https://github.com/alchaincyf/huashu-bird-sticker cd huashu-bird-sticker && git sparse-checkout set data stickers/Strigiformes Licenses. The stickers are under PolyForm Shield 1.0.0: free for almost anything, including commercial use, except using them in a product that competes with our app (another birding, bird-ID or field-guide app or site). Strictly speaking PolyForm Shield isn't an OSI open-source license; it's source-available. Our own data is MIT; third-party parts keep their terms (IOC multilingual names are CC BY 3.0). Whether a drawing made from a photo is bound by that photo's license is legally unsettled; if that matters for your use, you can filter by each sticker's reference source. If one of the stickers was drawn from your photo and you'd rather it wasn't, open an issue or email me at alchaincyf@gmail.com and I'll replace it within 7 days. The most useful contribution Corrections from birders. AI has certainly drawn some of these birds wrong. If you spot one, please open an issue. That's worth more to this project than a star. The stickers were made for Mingji, the iOS birding notebook I'm building; it's in App Store review now (Chinese interface first). I'll write about that when it's out. Repo again: alchaincyf/huashu-bird-sticker
I made a sticker for every living bird species: all 11,064 on the IOC list, with names in 43 languages and open data. Up front: they're AI-drawn from reference photos, and about a third miss our own quality bar (the data flags which). Corrections welcome. alchaincyf/huashu-bird-sticker
[self-promotion] All 11,064 living bird species (IOC 15.2): names in 43 languages, eBird/GBIF/Wikidata/iNat IDs, AVONET traits, IUCN status, plus an illustration for each Disclosure: I made this, and the illustrations are AI-generated (details below). I've been building a birding app and ended up assembling a species table for every living bird species in the IOC World Bird List v15.2 (11,064 species, 44 orders, 250 families). I've published it so other people don't have to stitch it together again. What's in data/: - species.json / species.csv: one record per species. Taxonomy (IOC sequence, order, family, genus), authority, breeding and non-breeding range, subspecies with ranges, AVONET traits (mass, wing, tail, habitat, migration, trophic niche), IUCN and CITES status, China national protection level - Cross-database IDs: Wikidata 10,939, GBIF 10,649, eBird 10,052, plus iNaturalist - names.csv: names in 43 languages from the IOC multilingual list. English is complete; French and Simplified Chinese nearly; Japanese and most European languages over 90%; Korean, Arabic, Thai and Persian only cover a few hundred to ~1,000 species, because that's what the IOC list has - field-guide.zh-Hans.json: Chinese field-guide notes for 1,596 species (CC BY-SA 4.0) Each record also points to a sticker (transparent WebP, ~1,000px) and to the reference photo it was drawn from, with author and license. 11,030 stickers are AI illustrations and 34 are photo cut-outs. Every AI sticker was scored against its reference by a separate model; 7,676 meet our bar and 3,388 don't, and that's a field (meetsQualityBar, reviewScore) so you can filter. Licenses: our own data is MIT, third-party parts keep theirs (IOC names CC BY 3.0 etc., see NOTICE). The stickers are PolyForm Shield 1.0.0. Repo: alchaincyf/huashu-bird-sticker If you only want the data (the full repo is ~700MB because of the images): git clone --filter=blob:none --sparse alchaincyf/huashu-bird-sticker cd huashu-bird-sticker && git sparse-checkout set data Happy to hear about mismatches. IOC vs eBird/Clements splits and lumps are where I expect most of the ID errors.
卧槽！！我真的把这个超大工程的项目搞定了！！！ 我花了10亿+的token，把全球现存的11064种鸟，全部变成了风格统一，设计出色的贴纸！！！主要目的是为了做我那个观鸟记录和了解鸟类的app。 但是what the hell，既然都做完了！！我就干脆把这全部素材都开源好了：alchaincyf/huashu-bird-sticker 我有一种预感，这个仓库会对全世界的鸟类爱好者和鸟类学习者产生长期有价值的影响，可能会是鸟类资源最有价值的资源库之一。
记一个 claude 被封号的经历 看到很多帖子讨论被封号与不被封号，以及 KYC 等的问题。 账号大约使用了 7 个月，一直都是 pro ，今天被要求 KYC ，看到很多人都说用护照可以通过，所以用了护照，然后没有通过，被封了。 所以看了一下这篇文章，zhangxuefeng-skill#63 关于如何用护照通过 KYC 的，逻辑上可行。可能会有用。 现在注册了第二个账号。 这里遇到了一个问题，原来的 pro 账号是用的苹果商店订阅，申请退款还没通过，但是现在说苹果商店已经绑定了原来的账号，不能再开通另外一个。——这个问题现在还没有解决。如果找代充的话，可能再被封号是无法退款的。所以今天的工作暂停，先来发帖交流一下。 网络是 vps 的机房环境，不算特别好，但是也不是最差。 pro 的用量经常用满，有时候还不够，但是现在也找不到好的解决办法处理用量用满之后的问题。MAX 又用不到那么多，pro 的话，如果能有 2 倍或者 1.5 倍 pro 的用量就非常合适，目前似乎没有。 比较认可前面那篇文章提到的关于封号的核心问题，因为他们针对的是中国大陆地区在使用的问题，当然被封的理由是国家地区。 所以，从逻辑上来说，它肯定是发现了可能在中国，并通过 KYC 确定了真的大概率在中国。
AI가 만든 티, 스킬 하나로 지운다 (GitHub 별 9만 개) | 에이전트-001 AI 코딩 도구로 만든 웹페이지, 왜 다 비슷해 보일까요? AI 티를 잡아 주는 디자인 스킬 4개를 골랐습니다. impeccable, hallmark, ai-design-skills, huashu-design. 숫자는 2026년 10월 28일 GitHub 기준이에요. ━━━━━━━━━━━━━━━━━━━━ 📌 오늘 소개한 디자인 스킬 링크 1) impeccable — 명령어 24개 + AI 티 탐지 규칙 62개 pbakaus/impeccable 2) hallmark — 테마 50개 중 3개 추천, 브라우저로 AI 티 검사 Nutlope/hallmark 3) ai-design-skills — 랜딩페이지 전용 스킬 elayadesign/ai-design-skills 4) huashu-design — 한 문장으로 웹·앱 시안·PPT·영상 alchaincyf/huashu-design ━━━━━━━━━━━━━━━━━━━━ 화면 출처: 각 GitHub 저장소(README 스크린샷·출시 영상·소개 그림) #ai #ClaudeCode #바이브코딩 #웹디자인 #GitHub
found one, haven't translated it though github.com/alchaincyf/nuwa-skill/tree/7c7edfeb9d9…