Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Start, drive and measure the local stack. An agent skill from stella/stella.
Install Dev
$ npx skills add stella/stella --skill dev -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install stella/stella dev --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/stella/stella.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/dev .claude/skills/dev && 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 "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .claude/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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/stella/stella/tree/main/.agents/skills/devType 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 stella/stella --skill dev -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install stella/stella dev --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/dev .agents/skills/dev && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .agents/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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 stella/stella --skill dev -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install stella/stella dev --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/dev .cursor/skills/dev && 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 "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .cursor/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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/stella/stella.git --path .agents/skills/dev--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 stella/stella --skill dev -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install stella/stella dev --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/dev .gemini/skills/dev && 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 "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .gemini/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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 stella/stella devInstalls 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 stella/stella --skill dev -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/dev .github/skills/dev && 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 "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .github/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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 stella/stella --skill dev -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install stella/stella dev --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/stella/stella.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/dev .opencode/skills/dev && 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 "dev" agent skill from https://github.com/stella/stella/tree/main/.agents/skills/dev into .opencode/skills/dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dev", 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.
Facts
- Skill name
dev- GitHub stars
- 258
- Token cost
- ~1.4k tokens
- SKILL.md length
- 746 words
- Files
- 1
- Skills in repo
- 24
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Start, drive and measure the local stack. An agent skill from stella/stella.
- Works in 6 steps: Start → Drive the API → Drive the web app → …
- Development work in your project
- SKILL.md covers 1. Start, 2. Drive the API, 3. Drive the web app and 4. Measure, plus 2 more sections
- Calls bun and gh
What it does
Dev is an agent skill from stella/stella. Start, drive and measure the local stack. bun run agent:up gives a checkout its own seeded, signed-in stack in one blocking command; agent:cli and agent:drive exercise it and write evidence (screenshots, browser errors, failed API calls, timings).
Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: Open-source legal workspace. The licence is Apache-2.0.
When your agent uses it
- Development work in your project
Example prompts
- “/dev”
Requirements
- Docker
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 269655d. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
bungh
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dev loads about 1.4k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 746 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.
Safety
Auto-check passed
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from stella/stella at commit 269655d, republished under its Apache-2.0 licence (© stella). 746 words, ~1,351 tokens.
Download SKILL.mdSave it as
.claude/skills/dev/SKILL.md (or your agent's skills folder).- name
- dev
- description
- Start, drive and measure the local stack. `bun run agent:up` gives a checkout its own seeded, signed-in stack in one blocking command; `agent:cli` and `agent:drive` exercise it and write evidence (screenshots, browser errors, failed API calls, timings).
Local Stack
Use this whenever a change needs to be seen working, not just type-checked: a UI change, an API behaviour, a performance claim.
1. Start
bun run agent:upIt blocks until the stack is ready and prints the web and API URLs. The
first start takes about half a minute (Docker services, migrations, and the
fixture seed while the servers boot; each step logs how long it took);
later runs reuse the running stack instantly. Interrupting up stops the runner it started,
and a retry joins a runner that is still starting. The runner is
packages/scripts/src/dev-runner.ts started detached with --seed:
- Worktrees get their own ports and Docker project automatically
(
--infra-offset auto, the default). The root checkout keeps the default ports. Never reset or repair a database another checkout owns. - The seed signs in
test@stella.dev, owner of the fixture firm, with matters, contacts and documents; the same data every time. - A machine API key for that owner is minted through
/v1/api-keys. - State lives in
.stella-dev/(gitignored):runtime.json,runner.log,agent.env, evidence and saved measurements.
bun run agent:status prints the live URLs; bun run agent:down stops the
stack (volumes and data survive). Leave it running while you iterate; the API
and web servers reload on save. bun run agent:reset recreates a worktree's
database from the seed alone (it refuses the root checkout's stack).
If up fails, read the tail it prints and .stella-dev/runner.log; fix the
cause and rerun. Do not start a second runner by hand in the same checkout.
2. Drive the API
bun run agent:cli -- matter list --json
bun run agent:cli -- document list --matter-id <id>agent:cli runs the stella CLI from this checkout against the stack with
the minted key, so it sees the MCP registry of the code on disk. It is also
the quickest way to find ids: a matter opens at /workspaces/<matter id>.
3. Drive the web app
bun run agent:drive -- snap /workspaces /chat/new
bun run agent:drive -- run path/to/flow.tssnap opens each path signed in, waits until main is visible, loading
placeholders are gone and the API is quiet, then screenshots it. run
imports a script that default-exports
async ({ page, snap, webUrl, apiUrl }) => {} (a Playwright page) for flows
that need clicks or typing. snap("label", { waitFor: "<selector>" })
records a step after the same readiness checks; name the element that
proves the step rendered, since main alone can be a loading screen.
Each command prints a Markdown report and exits 1 when the page showed a problem: a browser error, a 5xx API response, a sign-in redirect, the route error boundary, content that never finished loading, or API calls still running after 20 s. Look at the screenshots; a clean report with the wrong content is still wrong.
Show full SKILL.md (324 more words)Show less
4. Measure
bun run agent:drive -- measure /workspaces --save before
# change the code; the dev servers reload
bun run agent:drive -- measure /workspaces --compare beforeReports the median of several samples after a warm-up: settle time,
DOMContentLoaded, largest contentful paint, API request count, waterfall
depth, DB queries and API payload. Timing deltas inside the sample spread are
marked as noise; do not claim them, and repeat a pair before claiming one
outside the spread. Request, query and payload counts are page totals, so a
repeated call shows up. It is a dev build, so compare runs with
each other, never with production numbers. Committed CI budgets stay with
the route-smoke suite (/conventions-perf).
5. Report evidence
When handing work back, say what you ran and what it showed: the command, the report's findings, and the screenshot or measurement paths. A before and after pair is the evidence for a performance claim.
6. Screenshots in pull requests
bun run agent:attach <pr number> <screenshot.png>... is the only way to add
images to a pull request; the command guard blocks gh ... --attach. It
accepts an image only when it is an unaltered agent:drive capture taken while
the stack held nothing but seeded content: after seeding, the runner
fingerprints every table, and agent:drive checks the fingerprint before and
after each run. Anything created since (an upload, a new matter, a typed name,
a chat message) makes that run's captures unattachable, and the driver says so.
So does typing, pasting or dropping anything into the page in a run script,
even unsaved. A stack restarted while it held such content is not resealed
until bun run agent:reset.
- Take "before" shots before editing an existing screen.
- To show a change that needed new content, verify it for yourself, then run
bun run agent:resetand capture a state reachable without creating anything (for example the empty dialog). - The driver blocks requests to non-local sites, so pictures fetched from the web (avatars) are missing from screenshots.
agent:attachappends the images to the pull request body; if an upload fails it exits non-zero, so run it again.
© stella, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/dev of stella/stella.
Open the folder on GitHubat commit 269655d
Compare with similar skills
Dev 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 |
|---|---|---|---|---|---|---|
| Dev this skillstella/stella | 258 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from stella/stella
All 24 skills in this repoPlan
stella/stella
Create a concise, evidence-backed implementation plan in the repository planning area when the user explicitly asks for a plan.
Answer From Sources
stella/stella
Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim.
Check Against Rules
stella/stella
Reviews a non-disclosure agreement against the firm's NDA checklist and reports findings with citations.
Intake To Draft
stella/stella
Collects the facts of an unpaid invoice, then drafts a payment demand letter.
Conventions Perf
stella/stella
Apply when a performance-guard check (network baseline, bundle baseline, DB query count, loader-prefetch lint, RC bailouts) fails or when touching a hot route/endpoint.
Conventions Use Effect
stella/stella
Apply when writing or reviewing React effects in apps/web. An agent skill from stella/stella.
Related
Categories
Questions about Dev
What does Dev do?
Start, drive and measure the local stack. An agent skill from stella/stella. Dev is an agent skill from stella/stella. Start, drive and measure the local stack.
When should I use Dev?
Dev fits situations like: development work in your project.
How do I install Dev in Claude Code?
Run `npx skills add stella/stella --skill dev -a claude-code`. Or copy the skill folder (.agents/skills/dev in stella/stella) into .claude/skills/dev in your project. Claude Code loads it when a task matches its description.
How do I install Dev in Codex?
Run `npx skills add stella/stella --skill dev -a codex`. Or copy the skill folder (.agents/skills/dev in stella/stella) into .agents/skills/dev in your project. Codex loads it when a task matches its description.
Can I use Dev in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add stella/stella --skill dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dev, .gemini/skills/dev, .github/skills/dev and .opencode/skills/dev in your project.
What does Dev need to run?
Going by SKILL.md and its folder, Dev needs the command-line tools its instructions call (bun and gh). Our summary lists: Docker.
Does Dev access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Dev safe to install?
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. Review the folder before installing.
What licence does Dev use?
Dev is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dev use?
About 1.4k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Dev?
Skills that share tags, products or a category with Dev: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dev?
stella (a GitHub organization) maintains it in stella/stella, which has 258 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 8, 2026.
Source: stella/stella on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.