MetaOfficialCertified

coding-guardrails

by Skills Hub

Installs behavioral guardrails against classic LLM coding failures and audits the current session against them. Encodes six enforceable rules: verify APIs exist in node_modules or docs before calling them, state assumptions before coding, prefer minimal diffs over rewrites, re-read the actual error text instead of pattern-matching a fix, never claim done without running the code, and express uncertainty numerically. Writes the rules into CLAUDE.md with an idempotent merge and demonstrates each with a before/after example from this repo. Use when you hear: install guardrails, coding guardrails, stop hallucinating APIs, the agent keeps rewriting everything, add LLM safety rules, make Claude more careful, audit this session, why did you claim it works, anti-slop rules, Karpathy-style guidelines, tighten your coding behavior.

v2.0.0New

Signing

SignedSLSA L2
Signed by
skills-hub.ai distributor
Method
Distributor-signed by skills-hub.aiCryptographically signed by the skills-hub.ai distributor key at publish time.
Signed

Install this skill

Run this command in your terminal. No account required — it auto-detects your AI tool and installs the skill file.

npx @skills-hub-ai/cli install coding-guardrails
Or download directly:
Browse all CLI commands →

Setup by platform

Claude Code

~/.claude/skills/<skill>/SKILL.md

Setup guide →

Install

One-click setup for your editor

Run in your project root

npx @skills-hub-ai/cli install coding-guardrails --target claude-code
0

Instructions

This skill doesn’t include stateful context yet, instructions only. Learn about stateful skills.

Security

Loading security scan...

Reviews (0)

View full changelog & diffs →

Related skills

Browse all →
humanizerMulti-pass editor that removes AI-writing tells from drafted content — eliminates filler phrases, balances sentence length, restores opinion and voice, and strips em-dash overuse so posts sound human and opinionated rather than ChatGPT-generic. Use when the user wants to humanize AI-generated marketing copy, blog posts, landing pages, or social content.14 installscleanup-sprintDeep codebase cleanup — kills dead code, fixes all lint/format warnings, removes orphaned files, cleans stale TODOs, strips security hazards, tightens TypeScript strict mode, and organizes imports. Triggers on: clean up, dead code, unused imports, lint, technical debt cleanup, spring cleaning, tidy up the codebase, remove dead code, code hygiene, declutter.14 installsresponsiveAudit and fix responsive design issues across all breakpoints. Scans for fixed widths that cause mobile overflow, missing media query variants, non-responsive images, undersized touch targets below 48px, unreadable typography, and horizontal scroll violations. Auto-detects framework (Flutter, Tailwind, React, Vue, Angular) and responsive system, then fixes layouts with proper flex/grid, clamp-based fluid typography, responsive image sizing, and adequate touch target spacing. Verifies every screen at mobile (375px), tablet (768px), desktop (1280px), and wide (1920px). Use when you need to fix mobile layout bugs, audit responsive breakpoints, fix overflow issues, ensure touch targets meet accessibility minimums, or verify no horizontal scroll at any viewport width.12 installsskill-writerLearn to build and publish your own AI agent skills -- from idea to published on skills-hub.ai12 installsrecallReconstructs the development cycle from git history, distills sequential/parallel patterns, and produces actionable insights for improving future iterations. Triggers: recall, retrospective, development analysis, what happened, dev cycle analysis.11 installsandroid-appScaffold a production-ready native Android app -- generate a complete Kotlin project with Jetpack Compose UI, MVVM architecture, Hilt dependency injection, Room database with offline-first caching, Retrofit and OkHttp networking with auth interceptors, Firebase push notifications with notification channels, Material 3 theming with dynamic color and design tokens, EncryptedSharedPreferences for secure storage, NavHost navigation with typed routes, build variants (debug, staging, release) with per-environment API URLs, Gradle version catalog (libs.versions.toml), ProGuard/R8 rules, and Vitest unit and Compose UI test setup. Build an Android app, create Android project, generate Kotlin app, native mobile app scaffold.10 installs

More from Skills Hub

View source →
security-reviewSecurity audit and vulnerability assessment for any codebase. Scans for authentication bypasses, missing auth middleware, broken JWT validation (algorithm confusion, weak secrets, missing expiry), OAuth state and PKCE flaws, IDOR and horizontal privilege escalation, vertical privilege escalation via role manipulation, SQL injection, NoSQL injection, XSS (stored, reflected, DOM), command injection, path traversal, SSRF, CSRF, hardcoded secrets and API keys (sk_live_, AKIA, ghp_), .env and credential file exposure, PII leaking in logs and error responses, overfetching sensitive fields, CORS misconfiguration, session fixation, missing secure/httpOnly/sameSite cookie flags, and Firebase/Firestore rule weaknesses. Produces a severity-ranked findings report with exploit scenarios and fix recommendations. Covers OWASP Top 10.35 installsunit-testGenerate comprehensive unit tests with edge cases, error paths, and boundary values. Auto-detects test framework (Vitest, Jest, pytest, go test, flutter_test, RSpec, cargo test, JUnit), scans for untested functions by priority, adopts existing test conventions, generates tests with proper mocks, runs them, and self-heals failures in up to 3 iterations. Measures coverage before and after. Use when you need to add unit tests, increase code coverage, test edge cases, or verify error handling paths.34 installsdesign-to-codeTurn a design into production-quality frontend code: extract a design system with tokens and components, make layouts responsive across breakpoints, add dark mode with WCAG-compliant theming, then run a UX audit to validate everything. Use when implementing UI from Figma, adding theming, making an app responsive, or overhauling frontend design consistency.31 installspreflightPre-deploy verification gate. Checks git status, build, tests, migrations, secrets, and commit conventions. Reports READY or NOT READY. Read-only, no changes. Trigger words: preflight, pre-deploy check, ready to deploy, deployment checklist.18 installsskill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.16 installsdesign-claudeHTML-first hi-fi design skill: interactive prototypes, slide decks, animation demos, design variant exploration, visual direction advising, and expert critique. Triggers: make a prototype, design demo, interactive prototype, HTML presentation, animation demo, design variants, hi-fi design, UI mockup, prototype, design exploration, make an HTML page, make a visualization, app prototype, iOS prototype, mobile app mockup, export MP4, export GIF, 60fps video, design style, design direction, design philosophy, color scheme, visual style, recommend style, pick a style, make it look good, review, does this look good, review this design. Core capabilities: Junior Designer workflow (show assumptions+reasoning+placeholders first, then iterate), anti-AI-slop checklist, React+Babel best practices, Tweaks variant switching, Speaker Notes presentation, Starter Components (slide shell/variant canvas/animation engine/device frames), App prototype rules (default real images from Wikimedia/Met/Unsplash,16 installs

More Meta skills

Browse category →
skillifyCreate a reusable, self-healing, self-evolving global skill — either from the current conversation context OR from a plain-language description of a workflow. Triggers on: 'turn this into a skill', 'make a skill from this', 'skillify this', 'capture this as a skill', 'save this workflow as a skill', 'create a skill for this', 'make this repeatable', 'skill this up', 'build me a skill that does X', 'I want a skill for Y', or any time a workflow just played out and the user wants to preserve it. Invoke even if the user only hints at wanting to reuse what just happened.7 installssave-tokensToken-efficient codebase navigation. Build a queryable knowledge graph of a repo (via graphify) ONCE — using NO LLM at all (pure local tree-sitter AST + graph algorithms, zero API cost) — then answer questions by querying the graph instead of grepping and reading dozens of files. Invoke when about to explore an unfamiliar or large codebase, when the user says 'save tokens', 'save context', 'don't burn tokens', 'use the graph', 'graph this repo', 'map this codebase', 'how does X connect to Y', 'where is X', 'what calls X', 'explain this architecture', or any time you're tempted to fan out Grep/Read across many files to understand structure. Use BEFORE a broad code exploration, not after.5 installsload-contextLoad a saved conversation context to resume previous work. Supports local files, git repos, and URLs. Triggered by 'load context', 'resume previous work', 'pick up where I left off', 'load saved session', 'reload context'.3 installsyoutube-researchResearch pipeline — search YouTube, ingest into NotebookLM, generate deliverables, organize in Obsidian vault3 installspublish-skillPublish a locally installed skill to the skills-hub registry and sync it to the production platform. Use when: 'publish skill X', 'push skill to hub', 'add skill to registry', 'publish to skills hub', 'share this skill', 'make skill available globally'. Runs entirely from the Mac Studio — no VPS needed.3 installssave-contextSave the current conversation context as a reloadable snapshot. Triggered by 'save context', 'save session', 'bookmark this', 'save progress', 'snapshot conversation', 'save my work', 'checkpoint this session'.2 installs

Frequently asked questions about coding-guardrails

What does the coding-guardrails skill do?

Installs behavioral guardrails against classic LLM coding failures and audits the current session against them. Encodes six enforceable rules: verify APIs exist in node_modules or docs before calling them, state assumptions before coding, prefer minimal diffs over rewrites, re-read the actual error text instead of pattern-matching a fix, never claim done without running the code, and express uncertainty numerically. Writes the rules into CLAUDE.md with an idempotent merge and demonstrates each with a before/after example from this repo. Use when you hear: install guardrails, coding guardrails, stop hallucinating APIs, the agent keeps rewriting everything, add LLM safety rules, make Claude more careful, audit this session, why did you claim it works, anti-slop rules, Karpathy-style guidelines, tighten your coding behavior. It's a reusable SKILL.md instruction set that loads into your AI coding assistant on demand, no prompt engineering, no copy-pasting every session.

How do I install the coding-guardrails skill?

Run `npx @skills-hub-ai/cli install coding-guardrails` from your terminal. The CLI writes the SKILL.md to the correct location for your AI tool (e.g. ~/.claude/skills/coding-guardrails/ for Claude Code or ~/.cursor/skills/ for Cursor with --target cursor) and adds it to your project's .skills.json lockfile.

Which AI tools does coding-guardrails work with?

coding-guardrails runs in Claude Code. It follows the open Agent Skills standard (SKILL.md), so the same skill works in every supported tool without modification.

Is the coding-guardrails skill free?

Yes. Every skill on skills-hub.ai is free and open-source. There are no premium tiers, paywalls, or usage limits. You only pay for whatever AI assistant you're already using.

How do I use coding-guardrails after installing it?

In Claude Code, type `/coding-guardrails` (or whatever slash command the skill registers) and the AI follows the skill's instructions immediately. You can also reference it by name in natural language, your AI loads the skill into context when relevant.

Can I share the coding-guardrails skill with my team?

Yes. Commit your project's .skills.json lockfile and teammates run `npx @skills-hub-ai/cli install` (no args) to install every skill at the exact version you pinned. Organization-scoped installs work via skills-hub.ai organizations.