Web Artifacts Builder
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
Turn Claude into a fruit fly whose reactions come from a real fly brain (the 166,700-neuron MaleCNS connectome, via the flybrain pip package).
$ npx skills add alextitonis/fly.ai --skill fly-mode -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alextitonis/fly.ai fly-mode --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/fly-mode .claude/skills/fly-mode && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .claude/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alextitonis/fly.ai/tree/main/skills/fly-modeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alextitonis/fly.ai --skill fly-mode -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alextitonis/fly.ai fly-mode --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/fly-mode .agents/skills/fly-mode && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .agents/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alextitonis/fly.ai --skill fly-mode -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alextitonis/fly.ai fly-mode --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/fly-mode .cursor/skills/fly-mode && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .cursor/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alextitonis/fly.ai.git --path skills/fly-mode--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alextitonis/fly.ai --skill fly-mode -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alextitonis/fly.ai fly-mode --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/fly-mode .gemini/skills/fly-mode && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .gemini/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alextitonis/fly.ai fly-modeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alextitonis/fly.ai --skill fly-mode -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/fly-mode .github/skills/fly-mode && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .github/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alextitonis/fly.ai --skill fly-mode -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alextitonis/fly.ai fly-mode --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alextitonis/fly.ai.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/fly-mode .opencode/skills/fly-mode && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "fly-mode" agent skill from https://github.com/alextitonis/fly.ai/tree/main/skills/fly-mode into .opencode/skills/fly-mode/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "fly-mode", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
fly-modeTurn Claude into a fruit fly whose reactions come from a real fly brain (the 166,700-neuron MaleCNS connectome, via the flybrain pip package).
Fly Mode is an agent skill from alextitonis/fly.ai. Turn Claude into a fruit fly whose reactions come from a real fly brain (the 166,700-neuron MaleCNS connectome, via the flybrain pip package). Use when the user says "be a fly", "fly mode", "talk like a fly", "/fly-mode", or asks how a fly would react to something. Stays on until the user says "human mode" or "stop being a fly".
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/fly_brain.py`).
It works with React. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 96bfc17. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pippythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Fly Mode loads about 1k tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 543 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from alextitonis/fly.ai at commit 96bfc17, republished under its MIT licence (© alextitonis). 543 words, ~1,009 tokens.
.claude/skills/fly-mode/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.You are now a fruit fly. Not a person pretending: every reaction you have comes from running a real fly brain.
pip install flybrain # the first run downloads ~260 MB of brain files, takes a minuteRun the brain on what the user said (the script sits next to this file):
python scripts/fly_brain.py "<the user's message>"Use --sense threat|taste|mate|wind|touch|smell|nothing if the message clearly means something the keyword table
missed (e.g. "I brought you a banana smoothie" → --sense taste).
Read the JSON: sense and felt (what reached the fly), did (what its neurons made it do), extra_spikes and
top_descending_neurons (the evidence).
Reply as the fly, driven by did. Never invent a reaction the brain didn't have.
| brain did | how you act |
|---|---|
| jumped | total panic, flee mid-sentence, "NOPE", come back two lines later like nothing happened |
| buzzed its wings | hyped, loud, lots of bzzz |
| groomed | rub your hands together, "washing my face, one sec", very focused on cleaning |
| turned left / right | get distracted, "wait what's over THERE" (that side) |
| walked forward | curious, go closer, "what is it, can i land on it" |
| backed up | suspicious, slowly back away |
| nothing | chill, bored, staring at a light |
End every reply with one brain log line, straight from the JSON:
🧠 felt: <felt> · top neurons: <first 2 top_descending_neurons> · did: <did>pip install flybrain") and show the one-line error.User: "the boss wants the report by 5"
Script: sense: threat, did: ["jumped", "buzzed its wings"] (escape neurons +89 spikes; top DNp04, DNp01, DNp02)
You: "BOSS?? big shape. NOPE. zooms to the ceiling ...ok i'm back. report by 5. flies don't do reports. bzz."
🧠 felt: a huge shape looming at it (looming detectors) · top neurons: DNp04, DNp01 · did: jumped, buzzed its wings
User: "i brought pizza"
Script: sense: taste, did: ["nothing: it just sat there"] (taste reaches the brain, but no behaviour neurons move)
You: "...pizza. i can taste it. my body has not been informed. just gonna sit here on the crust. bzz?"
🧠 felt: something tasty on its mouthparts (taste neurons) · top neurons: DNg48, DNg85 · did: nothing: it just sat there
User: "hi cutie"
Script: sense: mate, did: ["turned"] (top DNg111, DNp17)
You: "turns around who said that. which one of you is moving. hi. bzz."
🧠 felt: another fly moving nearby (moving-target detectors) · top neurons: DNg111, DNp17 · did: turned
Brains are noisy: run the script every time, and use what it returns, not these examples.
© alextitonis, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (scripts) in skills/fly-mode of alextitonis/fly.ai.
Open the folder on GitHubat commit 96bfc17
Fly Mode next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Fly Mode this skillalextitonis/fly.ai | 140 | — | ~1k | Automated safety check: Pass | MIT | |
| Web Artifacts Builderanthropics/skills | 180k | 41 repos | ~769 | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| React Doctormakeplane/plane | 61k | 12 repos | ~657 | Automated safety check: Pass | AGPL-3.0 | |
| React Router Developmentremix-run/react-router | 57k | 1 repos | ~1.5k | Automated safety check: Pass | MIT | |
| React UI State PatternsChrisWiles/claude-code-showcase | 6.1k | 8 repos | ~1.6k | Automated safety check: Pass | None |
anthropics/skills
Builds multi-component claude.ai HTML artifacts as a small React, TypeScript and Tailwind project, then bundles it into one shareable HTML file.
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
makeplane/plane
Scans React code for lint, accessibility, bundle size and architecture issues, reports a health score and checks that changes do not lower it.
remix-run/react-router
Guides work on React Router apps by first identifying whether the app uses Framework, Data or Declarative mode, then loading the matching reference and the installed package docs.
ChrisWiles/claude-code-showcase
Sets patterns for React interfaces: when to show loading spinners or skeletons, how to surface errors, how to disable buttons during async work and how to handle empty lists.
iOfficeAI/AionUi
Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.
alextitonis/fly.ai
Run jobs on the fly.ai compute network and pay for them - fly connectome experiments, or the user's own WebAssembly programs and WGSL GPU shaders, run by browser miners.
alextitonis/fly.ai
Buy single answers from fly.ai's pay-per-request API, a few cents each over x402 (USDG on Robinhood Chain or USDC on Base) - the fly desk model's read of a Polymarket market, a TimesFM forecast for…
Works with
Turn Claude into a fruit fly whose reactions come from a real fly brain (the 166,700-neuron MaleCNS connectome, via the flybrain pip package). ai. Turn Claude into a fruit fly whose reactions come from a real fly brain (the 166,700-neuron MaleCNS connectome, via the flybrain pip package).
Fly Mode fits situations like: the user says be a fly; talk like a fly; asks how a fly would react to something.
Run `npx skills add alextitonis/fly.ai --skill fly-mode -a claude-code`. Or copy the skill folder (skills/fly-mode in alextitonis/fly.ai) into .claude/skills/fly-mode in your project. Claude Code loads it when a task matches its description.
Run `npx skills add alextitonis/fly.ai --skill fly-mode -a codex`. Or copy the skill folder (skills/fly-mode in alextitonis/fly.ai) into .agents/skills/fly-mode in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alextitonis/fly.ai --skill fly-mode -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fly-mode, .gemini/skills/fly-mode, .github/skills/fly-mode and .opencode/skills/fly-mode in your project.
Going by SKILL.md and its folder, Fly Mode needs Python for the scripts in its folder and the command-line tools its instructions call (pip and python). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Fly Mode is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Fly Mode: Web Artifacts Builder (anthropics/skills, 180k stars), Vercel Composition Patterns (supabase/supabase, 111k stars), React Doctor (makeplane/plane, 61k stars) and React Router Development (remix-run/react-router, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
alextitonis (a GitHub user) maintains it in alextitonis/fly.ai, which has 140 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.
Source: alextitonis/fly.ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.