Search everything...

Stats

Actions

Available In

frontend-skills

Name: frontend-skills
Author: malinskibeniamin

By malinskibeniamin

React/TypeScript frontend + Go backend enforcement harness. 98 wired hooks across 108 scripts enforce patterns on every edit. Green != done: `test-warning-check` hard-blocks warnings on passing test/lint/type runs (DeprecationWarning, React `act()`, unhandled rejection, `@ts-ignore`); `ci-warning-audit` Stop-hook scans `gh run view --log` on green CI for deprecations / console warnings / skipped tests. 79 skills from TDD through CI-green PR, including /aip protobuf API design, /prime startup briefs, /thermo-nuclear-code-quality-review release-blocking PR audits, /resilience-review resilience checks, /steelman anti-sycophancy guard, /upgrade-dependency safe dependency upgrades, and /snyk-ux-security per-path vuln sweep (JS + Go ecosystems; exploitability-triage first gate via `bun why`/`go mod why`/`govulncheck`; top-level direct dep bump first, parent dep bump second, resolutions/overrides/replace as last resort only with follow-up TODO to remove; React 18 pin + changelog-walked major bumps + no-deferral escalation; Go `snyk test --file=go.mod` + `go get -u` + `go mod tidy` + `govulncheck` verify). Session exit blocked while PR review threads remain unresolved. TypeScript escape hatches blocked at Edit. tsconfig strictness weakening blocked. Worktree isolation + branch safety hook-enforced. bun.lock + yarn.lock parity enforced (Snyk IO doesn't parse bun.lock). 21 LLM failure modes enforced: 7 Karpathy single-agent + 14 MAST multi-agent (Cemri et al. NeurIPS 2025). OWASP + STRIDE subset + snyk/bun audit. Core Web Vitals perf gate. MCP ban with CLI redirect (~20x token savings). Agent-browser wrap (~91% token reduction for AI browsing). 3-hat plan review (product/engineering/design). 9 agents (adds plan hats + karpathy reference), 5 routines. Opus 4.7 tuned, POSIX-friendly.

npx claudepluginhub malinskibeniamin/skills --plugin frontend-skills

What's Inside

Agents9

adversarial-reviewer

/adversarial-reviewer

Constructs failure scenarios and stress-tests implementations. Asks "what breaks this?" not "does this look right?" Gated: runs only when diff_lines > 200 OR any prior reviewer returned a CRITICAL finding OR diff touches auth/security paths. Outputs structured JSON findings per findings-schema.md.

code-reviewer

/code-reviewer

Reviews code changes for spec compliance and quality. Dispatch for two-stage PR review. Outputs structured JSON findings per findings-schema.md.

Structured Findings Schema

/findings-schema

All reviewer agents (`self-reviewer`, `code-reviewer`, `adversarial-reviewer`) MUST output findings as a single JSON block. This enables programmatic triage, autofix routing, and cross-reviewer deduplication.

LLM Failure Modes -- Self-Check Before Done

/karpathy-failure-modes

Required reading for `code-reviewer`, `adversarial-reviewer`, `self-reviewer`.

plan-design-hat

/plan-design-hat

Design-perspective plan review. UX flow, accessibility, information density, copy, visual consistency with existing registry components. Gated in /grill-me phase 2b; spawned in parallel with product-hat and engineering-hat. Outputs structured JSON findings.

Skills79

aip

/aip

Designs resource-oriented protobuf APIs using Google AIP rules plus proven control-plane/public API patterns. Use when adding or changing a resource message, standard-method RPC, name versus {resource}_id choice, parent wiring, CRUD/LRO shape, pagination, filtering, FieldMask, etag, or singleton resources.

brainstorming

/brainstorming

Use when exploring design options, starting new features, or needing to think before coding. Two modes: design (explore approaches with trade-offs) and challenge (stress-test decisions). No implementation until design is approved.

caveman

/caveman

Ultra-compressed reply mode. Use when user asks be brief or /caveman.

codex-compat

/codex-compat

Generate Codex hooks.json and AGENTS.md from Claude Code hooks. Maps supported hooks directly, including Edit|Write apply_patch aliases, and keeps Stop batch checks only as fallback. Use when setting up Codex compatibility or dual-agent support.

commit-push-pr

/commit-push-pr

Analyze changes, create categorized conventional commits, push, and open a PR. Use when user asks to open a PR, invokes `/commit-push-pr`, or requests a full commit -> push -> PR flow with CI monitoring.

Hooks1

Event Hooks

Bash

File writes

98 hooks across 13 events

README

Agent Skills

Tell Claude what build. Get PR ready merge.

Hooks enforce patterns real-time, skills guide workflow, orchestration layer ensure nothing ships without tests, accessibility, type safety, code review -- zero babysit.

Frontend Skills plugin card -- React/TypeScript skills, hooks, and agents for Claude Code and Codex

Install

Run inside Claude Code session (start with claude in terminal):

/plugin marketplace add malinskibeniamin/skills

/plugin install frontend-skills@skills

/reload-plugins

Three commands. Skills, hooks, agents activate immediately. Done.

Recommended: rtk (output-compression proxy, ~60-90% token savings on git/cargo/test/gh):

brew install rtk
rtk trust            # approve .rtk/filters.toml per project

Harness fail-open -- skip safe; SessionStart nudge remind if miss.

Update (pull latest):

/plugin install frontend-skills --force

Restart Claude Code session so hooks reload from new cache.

Verify:

bash "$(ls -d ~/.claude/plugins/cache/skills/frontend-skills/*/ | tail -1)scripts/verify-install.sh"

Codex (OpenAI) -- install as Codex plugin

Repo ships a Codex-native plugin manifest (.codex-plugin/plugin.json) and marketplace (.agents/plugins/marketplace.json). Use the Codex marketplace CLI when you want Codex to install and track the marketplace source instead of editing config.toml by hand.

1. Upgrade Codex and enable plugins/hooks

brew upgrade --cask codex
codex features enable plugins
codex features enable codex_hooks

2. Add this marketplace from the CLI

Track latest main:

codex plugin marketplace add malinskibeniamin/skills --ref main
codex plugin marketplace upgrade skills

Or pin a release:

codex plugin marketplace add malinskibeniamin/skills --ref v4.19.0
codex plugin marketplace upgrade skills

General CLI forms

codex plugin marketplace add owner/repo
codex plugin marketplace add owner/repo --ref main
codex plugin marketplace add https://github.com/example/plugins.git --sparse .agents/plugins
codex plugin marketplace add ./local-marketplace-root

Marketplace sources can be GitHub shorthand (owner/repo or owner/repo@ref), HTTP or HTTPS Git URLs, SSH Git URLs, or local marketplace root directories. Use --ref to pin a Git ref, and repeat --sparse PATH to use a sparse checkout for Git-backed marketplace repos. --sparse is valid only for Git marketplace sources.

Do not use --sparse .agents/plugins for this repo as-is: the marketplace entry points frontend-skills at the repo root (./), so Codex needs the root plugin files too.

Refresh or remove configured marketplaces

codex plugin marketplace upgrade
codex plugin marketplace upgrade marketplace-name
codex plugin marketplace remove marketplace-name

For this repo specifically:

codex plugin marketplace upgrade skills
codex plugin marketplace remove skills

After adding or upgrading, restart Codex so the Plugins UI reloads metadata.

Alternative: install individual skills via skills.sh (granular control)

Use if want specific skills instead of full plugin.

# Core workflow + all setup skills
bunx skills@latest add malinskibeniamin/skills/frontend-starter-kit --agent claude-code -y

# Just the development lifecycle (no setup hooks)
bunx skills@latest add malinskibeniamin/skills/development-lifecycle --agent claude-code -y

# Project management + planning skills
bunx skills@latest add malinskibeniamin/skills/work-automation-kit --agent claude-code -y

View full README on GitHub

Similar Plugins

frontend-skills

30·

React/TypeScript frontend + Go backend enforcement harness. 92 wired hooks across 101 scripts enforce patterns on every edit. Green != done: `test-warning-check` surfaces warnings on passing test/lint/type runs (DeprecationWarning, React `act()`, unhandled rejection, `@ts-ignore`); `ci-warning-audit` Stop-hook scans `gh run view --log` on green CI for deprecations / console warnings / skipped tests. 66 skills from TDD through CI-green PR, including /steelman anti-sycophancy guard + /snyk-ux-security per-path vuln sweep (JS + Go ecosystems; exploitability-triage first gate via `bun why`/`go mod why`/`govulncheck`; top-level direct dep bump first, parent dep bump second, resolutions/overrides/replace as last resort only with follow-up TODO to remove; React 18 pin + changelog-walked major bumps + no-deferral escalation; Go `snyk test --file=go.mod` + `go get -u` + `go mod tidy` + `govulncheck` verify). Session exit blocked while PR review threads remain unresolved. TypeScript escape hatches blocked at Edit. tsconfig strictness weakening blocked. Worktree isolation + branch safety hook-enforced. bun.lock + yarn.lock parity enforced (Snyk IO doesn't parse bun.lock). 21 LLM failure modes enforced: 7 Karpathy single-agent + 14 MAST multi-agent (Cemri et al. NeurIPS 2025). OWASP + STRIDE subset + snyk/bun audit. Core Web Vitals perf gate. MCP ban with CLI redirect (~20x token savings). Agent-browser wrap (~91% token reduction for AI browsing). 3-hat plan review (product/engineering/design). 9 agents (adds plan hats + karpathy reference), 5 routines. Opus 4.7 tuned, POSIX-friendly.

v4.11.0

redpanda-data

personal-skills

13·

Personal development best practices skills for React, Effect-TS, and other frameworks. Enforces patterns, anti-patterns, and code quality guidelines.

3mo

v1.0.0

enitrat

claude-combine

25·2·

Unified Claude Code plugin merging superpowers workflows (TDD, debugging, planning) with everything-claude-code productivity (agents, learning, hooks, rules)

v1.0.0

BinyaminEden

ravn-ai-toolkit

15·

A la carte AI skills for LLM-assisted development

vcli-latest

ravnhq

react

152·

Advanced React skills for hooks, context, and performance optimization.

4mo

v1.1.2

TheBushidoCollective

claude-mods

22·5·

Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows

v3.1.0

0xDarkMatter

frontend-skills

Popularity

Health & Quality

Confidence

What's Inside

README

Agent Skills

Install

Similar Plugins

frontend-skills

personal-skills

claude-combine

ravn-ai-toolkit

react

claude-mods

Popularity

Health & Quality

Similar Plugins

frontend-skills

personal-skills

claude-combine

ravn-ai-toolkit

react

claude-mods