By marcusrbrown
Profile a shop's engineering culture from public sources and generate develop-like-<target> skills. /dev-like Every
Executables (bin/) — files in this plugin's bin/directory are added to the Bash tool's PATH while the plugin is enabled.
Steal the workflow, not the code. /dev-like Every and your agent develops like the shops you admire — with receipts.
dev-like profiles a tech company or developer's engineering culture from public sources
only (their shipped agent configs, linter configs, CI files, engineering blogs, talks) and
distills it into an installable, spec-compliant Agent Skill:
develop-like-every, develop-like-theo, develop-like-<your-heroes>.
Every claim in a generated skill links to the public source it came from. No source, no claim.
# Universal — symlinks into every detected harness (Claude Code, Codex, Cursor, Copilot, ...)
npx skills add marcusrbrown/dev-like
# Claude Code plugin (bare /dev-like command)
/plugin marketplace add marcusrbrown/dev-like
/plugin install dev-like
# CLI — install a cached profile's skill directly, no LLM needed
npx dev-like oxide
/dev-like Every # cached: installs develop-like-every from the registry
/dev-like Theo # aliases work: theo.gg, t3.gg, t3
/dev-like SomeNewShop # uncached: live OSINT profile -> skill -> offers to PR it back
What changes? Same prompt, before and after — see the dry-run transcript: a generic senior-engineer review becomes one that runs on the shop's actual operating model, every point traceable to a cited source.
| Slug | Kind | Consent tier | Skill |
|---|---|---|---|
37signals | org | self-published | develop-like-37signals |
every | org | self-published | develop-like-every |
linear | org | self-published | develop-like-linear |
oxide | org | self-published | develop-like-oxide |
theo | person | stated | generated on demand |
Want a shop profiled? Request it
— or run /dev-like <target> and PR the result back.
profile.md becomes a develop-like-<slug> skill in your
project (.agents/skills/ + .claude/skills/).Public professional sources only, official APIs over scraping, consent tiers on every profile
(self-published > stated > observed > social), a stated-tier floor for individuals,
opt-out honored within 48h, and provenance links on every claim. We
extract principles and workflow shapes — never reproduce prose.
bun install
bun run validate # frontmatter + registry schema + index sync
bun run test # generator, CLI install, link-collection suites
Plain node works too (node scripts/validate.mjs, node --test tests/) — the package has
zero runtime dependencies. Provenance links are re-checked weekly in CI; trigger evals and the
paired workflow eval live in evals/.
See CONTRIBUTING.md for adding registry profiles.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Structured engineering workflows for Claude Code.
npx claudepluginhub marcusrbrown/dev-like --plugin dev-likeDesign fluency for frontend development. 1 skill with 23 commands (/impeccable polish, /impeccable audit, /impeccable critique, etc.) and curated anti-pattern detection.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.