Content Moderation Patterns

by softspark

Content Moderation Patterns is an AI Engineering skill for Claude Code, published by softspark in ai-toolkit.

170 stars20 forkson softspark/ai-toolkitAdded 2026/09/08+2% in starsRepository updated 2026/09/07

View source on GitHub Download repo ZIP

ai-agentsai-skillsanthropicclaudeclaude-codeclinecodexcopilotcursorgeminimcpopencodetoolkitwindsurf

Install in seconds

Install Content Moderation Patterns

Copy Content Moderation Patterns into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/softspark/ai-toolkit/tree/main/app/skills/content-moderation-patterns ~/.claude/skills/content-moderation-patterns

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/softspark/ai-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: app/skills/content-moderation-patterns/SKILL.md in softspark/ai-toolkit
Installs to: ~/.claude/skills/content-moderation-patterns
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Content Moderation Patterns does

Content Moderation Patterns shows a two-stage moderation pipeline with cheap pre-filters, LLM classification, thresholds, and human review. Use it to enforce content policy with audit trails and structured decisions.

Content Moderation Patterns is cataloged under AI Engineering on DirSkills. Content Moderation Patterns comes from a repository tagged ai-agents, ai-skills, anthropic, claude and claude-code.

Documentation

README

Excerpt

Content Moderation Patterns

Two-stage pattern that balances cost, latency, and quality: cheap deterministic filters first, then LLM classification only on survivors.

Architecture

[ input ]
   │
   ▼
[ pre-filter ]  ── (regex, allow/block lists, length check) ──► reject early
   │
   ▼
[ LLM classifier ]  ── (Haiku, structured output) ──► categories + confidence
   │
   ▼
[ decision router ]
   ├── high confidence + policy violation → reject
   ├── high confidence + clean → pass
   └── low confidence or edge categories → human review queue

Pre-filter Stage (cheap)

Catch the obvious cases before paying an LLM call:

This is the opening of the README. Read the full README on GitHub.

Commands Content Moderation Patterns provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/json-mode-patterns
/security-patterns
/prompt-caching-patterns
/model-routing-patterns

Frequently asked about Content Moderation Patterns

What else does softspark publish alongside Content Moderation Patterns?
Content Moderation Patterns is one of 25 skills that DirSkills catalogs from softspark/ai-toolkit, the repository it ships in. Its siblings there include API Patterns, Accessibility Validator and Agent Creator. Each one is a separate skill with its own page in this directory, installs the same way Content Moderation Patterns does, and is maintained by softspark in that same repository. The rest of the collection is listed on the softspark/ai-toolkit page.
How does Content Moderation Patterns compare to other AI Engineering skills?
Content Moderation Patterns ranks #3273 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Content Moderation Patterns against them. Open each page to compare what they document and how they install.