Citedy Skills

Curated collection of AI agent skills for data extraction and analysis.

Citedy Skills

Curated collection of AI agent skills by Citedy — works with Claude Code, Codex, Gemini CLI, Droid, and any AI coding agent that reads .md skill files.

This package is actively maintained. We regularly add new skills and improve existing ones. Run npx @citedy/skills update to get the latest version at any time.

Install

npx @citedy/skills install

That's it. All skills and slash commands are copied into your project's .claude/ directory, ready to use.

Install specific skills only

npx @citedy/skills install youtube tiktok

Stay up to date

npx @citedy/skills@latest update

New skills are added regularly. Use @latest to make sure you always get the newest version — no stale cache.

See what's available

npx @citedy/skills list

Available Skills

Extraction Skills

NameSlash CommandDescriptionRequires
youtube/any-youtubeExtract structured metadata from any public YouTube videoAnyCrawl API
instagram/any-instagramExtract public Instagram profile, post, and reel dataAnyCrawl API
tiktok/any-tiktokExtract public TikTok video, profile, and hashtag dataAnyCrawl API
social/any-socialAuto-detect platform and route to the correct extractorAnyCrawl API

Knowledge Skills (no API keys needed)

NameSlash CommandDescription
schema/schema-markupAdd, fix, or optimize schema.org JSON-LD structured data
icons/icon-designSelect semantically appropriate icons (Lucide/Heroicons/Phosphor)
domains/domain-hunterSearch domains, compare prices, find promo codes
skill-eval/skill-evalValidate slash command quality (frontmatter, jargon, descriptions)
symphony/codex-symphonyBootstrap local OpenAI Symphony + Linear orchestration for any repo
token-usage/token-usageAnalyze Claude Code token consumption and estimated costs
prompt-analyzer/prompt-analyzerAnalyze prompts for constraint complexity, audit risks, and generate optimized rewrites for Claude/GPT

Agent Team Skills (Claude Code only)

NameSlash CommandDescription
spawning-plan/spawning-planDesign and spawn optimal agent teams
code-review/code-review-teamParallel multi-agent code review with 4 reviewers

Agent Team skills require Claude Code with Agent Teams support (TeamCreate, TaskCreate, SendMessage).

Extraction skills use the AnyCrawl Scrape API for LLM-powered structured data extraction.

Setup

1. Get an AnyCrawl API key

Sign up at anycrawl.dev and get your API key.

2. Add to your environment

# .env.local (or .env)
ANYCRAWL_API_KEY_DEV=ac-your-key-here

3. Install

npx @citedy/skills install

Usage

Once installed, Claude Code automatically picks up skills when you provide a social media URL. Or invoke directly:

/any-youtube https://www.youtube.com/watch?v=VIDEO_ID
/any-instagram https://www.instagram.com/username/
/any-tiktok https://www.tiktok.com/@user/video/VIDEO_ID
/any-social <any-supported-url>

What gets extracted

Each skill returns a structured JSON artifact saved to /tmp/ with:

  • normalized — Platform-specific structured data (title, stats, channel/author, description, etc.)
  • anycrawl — Raw AnyCrawl response with markdown content
  • request — The exact API payload used

Requirements

Prompt Analyzer Skill

The prompt-analyzer skill applies findings from "How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism" (Rocchetti & Ferrara, 2026) to audit and optimize prompts.

What it does:

  1. Decomposes prompts into constraint types (structural, lexical, semantic, stylistic)
  2. Scores complexity: Constraint Density, Cross-Type Mixing Index, Order Risk
  3. Audits for conflicts, ambiguity, implicit constraints, and model-specific risks
  4. Generates optimized rewrites — separate variants for Claude and GPT

Usage:

/prompt-analyzer path/to/prompts.md

The file can contain multiple prompts separated by ---. Works with plain text, system prompts, and structured files (JSON/YAML).

Install just this skill:

npx @citedy/skills install prompt-analyzer

Symphony Skill

The symphony skill is different from the extraction skills. It bootstraps local OpenAI Symphony orchestration into the current repository and installs:

  • WORKFLOW.symphony.md
  • scripts/symphony/*
  • .env.symphony.example
  • codex-symphony wrapper in ~/.local/bin

Install just that skill:

npx @citedy/skills install symphony

Then in your target repo:

/codex-symphony

You will still need your own:

  • LINEAR_API_KEY
  • LINEAR_PROJECT_SLUG
  • SOURCE_REPO_URL
  • SYMPHONY_WORKSPACE_ROOT
  • optional GH_TOKEN

License

MIT — Citedy