--- title: "Paul Berg (@paulrberg) skills · skilld" canonical_url: "https://skilld.dev/gh/paulrberg" meta: description: "46 agent skills written by Paul Berg on skilld." "og:description": "46 agent skills written by Paul Berg." "og:title": "Paul Berg on skilld" --- ` ![Avatar for Paul Berg](https://skilld.dev/_img/avatar?url=https%3A%2F%2Fgithub.com%2Fpaulrberg.png) # **Paul Berg** [@paulrberg](https://github.com/paulrberg)person Open-source builder Co-founded @sablier-labs Now on a sabbatical 46 skills 94 Synced 1 day ago [GitHub](https://github.com/paulrberg) [Website](https://prberg.com) ## Skills ### [paulrberg/agent-skills](https://skilld.dev/gh/paulrberg/agent-skills) PRB's collection of agent skills 46 skills 94 `npx skilld add paulrberg/agent-skills` - [ **/agents-brain**94 Create or polish repo agent context: README.md, AGENTS.md/CLAUDE.md, project-installed and source-catalog skills, and other Markdown context docs. /agents-brain by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/agents-brain) - [ **/agents-docs**94 Use for current official documentation about Codex, Codex CLI, or Claude Code behavior, configuration, prompting, skills, permissions, tools, surfaces, capabilities, troubleshooting, hooks, app-server, or hook trust; consult the relevant official source before answering. /agents-docs by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/agents-docs) - [ **/agents-introspection**94 Assess recurrence risk for agent behavior using local Codex/Claude Code transcripts and recommend evidence-backed durable fixes to AGENTS.md or skills. Not for routine post-success skill-evolution or agent self-improvement reviews. /agents-introspection by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/agents-introspection) - [ **/ai-prune**94 Prune agent scratch directories on macOS by moving clearly outdated \`.ai/\` files into \`.ai/archive/YYYY-MM-DD/\` and trashing clearly outdated \`.cache/\` entries, leaving \`.ai/todos\` untouched. /ai-prune by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/ai-prune) - [ **/autoresearch**94 Use for autoresearch or "optimize X overnight/in a loop"; plans bounded measurable experiment batches, then delegates execution through codex-handoff. /autoresearch by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/autoresearch) - [ **/brainstorm**94 Brainstorm with the user to generate, combine, and refine non-obvious ideas into a promising concept. Use when the user wants to brainstorm, ideate, explore possibilities, escape obvious approaches, or find a creative solution. /brainstorm by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/brainstorm) - [ **/chromium-browser**94 Use Chrome DevTools through PRB's shared attach-only Chromium browser for browsing, debugging, automation, visual inspection, console or network analysis, performance or memory profiling, screencasts, and Wayback Machine research. /chromium-browser by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/chromium-browser) - [ **/claude-handoff**94 Orchestrate read-only Explore research subagents in any mode, or one to eight Claude subagents to implement an approved plan. /claude-handoff by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/claude-handoff) - [ **/cli-cast**94 Use for Foundry cast transaction actions: prepare, trace, simulate, sign, or broadcast; sign messages; or encode/decode ABI/calldata. Delegate every standalone RPC read to evm-atlas. /cli-cast by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/cli-cast) - [ **/cli-coingecko**94 Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, or historical/OHLC data. /cli-coingecko by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/cli-coingecko) - [ **/cli-gh**94 Use for GitHub CLI automation: repository reads, workflow runs, search, codespaces, releases, configuration, or gh command syntax. Use yeet for contribution writes to PRs, issues, comments, or discussions. /cli-gh by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/cli-gh) - [ **/cli-just**94 Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows. /cli-just by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/cli-just) - [ **/code-polish**94 Polish changed code when the user explicitly asks, or when an active workflow requests post-implementation simplification and risk-profiled review over a fixed file scope. /code-polish by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/code-polish) - [ **/codebase-design**94 Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. /codebase-design by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/codebase-design) - [ **/codex-handoff**94 Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude Code or Codex CLI. /codex-handoff by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/codex-handoff) - [ **/commit**94 Commit staged or intended changes: compose a Conventional Prefix or Natural Language message, then use ai-commit — with --all, --staged, --close, --finding, or --push. /commit by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/commit) - [ **/copy-transcript-path**94 Copy the active Claude Code or Codex CLI chat transcript path to the macOS clipboard. /copy-transcript-path by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/copy-transcript-path) - [ **/effect-ts**94 Use for nontrivial Effect 3 work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, Effect Atom, or @prb/effect-next. /effect-ts by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/effect-ts) - [ **/evm-atlas**94 Use for targeted EVM chain, account, transaction, RPC, explorer, bridge, and DEX evidence: chain name/ID, native symbol, RouteMesh, wallet balances via Blockscan in Chromium, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Across, Bungee, deBridge, Hop, Layerswap, LayerZero, LI.FI, Relay, Socket, Symbiosis; Uniswap v1-v4, Universal Router, Permit2, 1inch Classic/Fusion/Fusion+, and CoW Swap, CoWSwap, CoW Protocol, or GPv2 swaps, orders, liquidity, approvals, permits, rewards, migrations, wrapping, cancellations, and refunds. /evm-atlas by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/evm-atlas) - [ **/fresh-eyes-sweep**94 Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, stale or duplicate tests, stale comments, and other evidenced mistakes; fix every safe issue and verify the result. /fresh-eyes-sweep by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/fresh-eyes-sweep) - [ **/frontend-design**94 Use when creating or substantially redesigning web interfaces, landing pages, dashboards, components, or other frontend UI where visual direction and implementation quality matter. Produces subject-specific art direction, accessible responsive code, and rendered visual verification. /frontend-design by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/frontend-design) - [ **/git-squash**94 Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR. /git-squash by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/git-squash) - [ **/grill-me**94 Interview the user relentlessly about a plan or design until every branch of the decision tree has an explicit recorded decision and no open questions remain. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". /grill-me by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/grill-me) - [ **/html-debrief**94 Use for interactive HTML debriefs or saved HTML findings/reports from the current task. /html-debrief by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/html-debrief) - [ **/html-playground**94 Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out. /html-playground by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/html-playground) - [ **/interview-me**94 Interview the user about a plan, idea, or design through a short sequence of high-leverage questions, then summarize the direction and next step. Use when the user wants a relaxed interview, lightweight clarification, or says "interview me", without exhaustive grilling. /interview-me by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/interview-me) - [ **/large-file-refactor**94 Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling. /large-file-refactor by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/large-file-refactor) - [ **/naming-refactor**94 Refactor naming and repository structure exhaustively while preserving behavior and external contracts. /naming-refactor by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/naming-refactor) - [ **/node-deps-bumper**94 Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze. /node-deps-bumper by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/node-deps-bumper) - [ **/pdf**94 Use when PDF files are the primary input or output: read, compare, reconcile, extract text/tables/images, OCR scans, fill forms, split, merge, rotate, rename, compress, or convert between PDF and images. Optimized for private financial, tax, legal, and health documents on macOS. /pdf by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/pdf) - [ **/release-bumper**94 Cut a release: bump versions, write changelogs, commit, tag. /release-bumper by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/release-bumper) - [ **/repo-cross-pollination**94 Compare agent guidance, workflows, and dependencies across repositories, then adopt the practices each recipient would benefit from. /repo-cross-pollination by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/repo-cross-pollination) - [ **/repo-harmonization**94 Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication. /repo-harmonization by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/repo-harmonization) - [ **/repo-rename**94 Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references. /repo-rename by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/repo-rename) - [ **/skill-doctor**94 Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs. /skill-doctor by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/skill-doctor) - [ **/skill-harmonization**94 Harmonize a repository's skill portfolio across catalog and user-installed skills. /skill-harmonization by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/skill-harmonization) - [ **/skill-map**94 Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine. /skill-map by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/skill-map) - [ **/skill-writing**94 Create/scaffold/init a project-local agent skill under \`.agents/skills\` in an ordinary repository; defer to repository instructions that define a source catalog and lifecycle. /skill-writing by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/skill-writing) - [ **/spreadsheets**94 Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: design or review text-table schemas; inspect, transform, validate, convert, or recalc formulas; or create/fix spreadsheets. Do not trigger when tabular data is incidental. /spreadsheets by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/spreadsheets) - [ **/tailwind-css**94 Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css. /tailwind-css by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/tailwind-css) - [ **/task-handoff**94 Create one decision-complete task handoff in its repository or on the Desktop for cross-repository work, return a command for a fresh interactive Codex session, and recommend Codex subagent delegation for complex tasks. /task-handoff by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/task-handoff) - [ **/todo-archive**94 Archive checked \`.ai/TODO.md\` tasks into \`.ai/todos/YYYY-MM/DD.md\`, leaving unchecked tasks. /todo-archive by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/todo-archive) - [ **/tool-finder**94 Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task. /tool-finder by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/tool-finder) - [ **/vitest**94 Use for Vitest in TypeScript projects (Node, bun, React/Next.js, Effect): write, run, or debug unit/component tests, mocks, testing utilities, and coverage. /vitest by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/vitest) - [ **/wrap-up**94 Wind down a long-running session fast when the user must leave — freeze new work, preserve active subagents, secure finished work, and hand off the remainder via task-handoff. /wrap-up by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/wrap-up) - [ **/yeet**94 Use for GitHub PR/issue/discussion workflows: create/update PRs, issues, or discussions and post issue or discussion comments; triggers include yeet. /yeet by paulrberg](https://skilld.dev/gh/paulrberg/agent-skills/yeet) Curated skills from @paulrberg. Checked GitHub just now