PaulRBerg

60 mods across 6 repositories, 1.8k stars between them.

effect-ts

26

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago A 56 tokens original MIT

evm-atlas

27

PaulRBerg/agent-skills

Skill Claude CodeCodex

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…

70 4d ago A 158 tokens original MIT

fresh-eyes-sweep

28

PaulRBerg/agent-skills

Skill Claude CodeCodex

Audit an entire repository with fresh eyes for correctness errors, bugs, omissions, duplication, inconsistencies, and other evidenced mistakes; fix every safe issue and verify the result.

70 4d ago A 40 tokens original MIT

frontend-design

29

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago A 48 tokens original MIT

git-squash

30

PaulRBerg/agent-skills

Skill Claude CodeCodex

Squash a feature branch into one commit via soft reset to the merge base, ready for a clean PR.

70 4d ago A 27 tokens original MIT

grill-me

31

PaulRBerg/agent-skills

Skill Claude CodeCodex

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".

70 4d ago A 54 tokens original MIT

html-debrief

32

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use for interactive HTML debriefs or saved HTML findings/reports from the current task.

70 4d ago A 22 tokens original MIT

html-playground

33

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use to build interactive single-file HTML playgrounds, explorers, or tools with visual controls, live preview, and prompt copy-out.

70 4d ago A 30 tokens original MIT

interview-me

34

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago A 56 tokens original MIT

large-file-refactor

35

PaulRBerg/agent-skills

Skill Claude CodeCodex

Discover large source-file refactor candidates and propose cohesion- and risk-driven split plans using available semantic tooling.

70 4d ago A 26 tokens original MIT

naming-refactor

36

PaulRBerg/agent-skills

Skill Claude CodeCodex

Refactor naming and repository structure exhaustively while preserving behavior and external contracts.

70 4d ago A 20 tokens original MIT

node-deps-bumper

37

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

70 4d ago A 29 tokens original MIT

pdf

38

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago A 65 tokens original MIT

repo-harmonization

40

PaulRBerg/agent-skills

Skill Claude CodeCodex

Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication.

70 4d ago A 24 tokens original MIT

repo-rename

41

PaulRBerg/agent-skills

Skill Claude CodeCodex

Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references.

70 4d ago B 32 tokens original MIT

skill-doctor

42

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use to audit Agent Skills catalogs or installed skill roots for metadata and doc-link issues; optionally apply conservative --fix-safe repairs.

70 4d ago A 29 tokens original MIT

skill-map

44

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine.

70 4d ago A 33 tokens original MIT

skill-writing

45

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago B 35 tokens original MIT

spreadsheets

46

PaulRBerg/agent-skills

Skill Claude CodeCodex

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.

70 4d ago A 57 tokens original MIT

PaulRBerg/agent-skills

Skill Claude CodeCodex

Audit and fix JavaScript, TypeScript, and Go comments that are verified as stale, orphaned, misleading, or redundant.

70 4d ago A 32 tokens original MIT

tailwind-css

48

PaulRBerg/agent-skills

Skill Claude CodeCodex

Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.

70 4d ago A 35 tokens original MIT