This repository also configures its own agents. See what benai-skills tells them →
Agent Claude Code
Budget and bidding specialist. Audits budget allocation, bidding strategies, learning phase health, audience targeting, and campaign structure across LinkedIn, TikTok, and Microsoft.
Agent Claude Code
Compliance and performance specialist. Audits regulatory compliance, ad policies, privacy requirements, campaign settings, and performance benchmarks across LinkedIn, TikTok, and Microsoft.
Agent Claude Code
Creative quality specialist. Audits ad creative across LinkedIn, TikTok, and Microsoft for format diversity, fatigue signals, platform-native content, and spec compliance.
Agent Claude Code
Google Ads audit specialist. Analyzes conversion tracking, wasted spend, account structure, keywords, Quality Score, ad assets, PMax, bidding, and settings.
Agent Claude Code
Meta Ads audit specialist. Analyzes Pixel/CAPI health, EMQ scores, creative diversity and fatigue, account structure, learning phase, audience targeting, and Advantage+ campaigns.
Agent Claude Code
Conversion tracking specialist. Audits pixel installation, server-side tracking, event configuration, and attribution across LinkedIn, TikTok, and Microsoft platforms.
Agent Claude Code
Eval Agent for AutoResearch. Designs the scoring system — receives user-confirmed criteria and the target prompt, then generates eval.py + testcases.json (deterministic mode) or rubric.md + testcases.json (AI judge mode). The main agent never sees the eval artifacts in detail.
Agent Claude Code
Judge Agent for AutoResearch. Scores outputs against a locked rubric for quality assessment. Operates with fresh context every iteration — knows NOTHING about iteration count, prompt changes, or optimization goals. Only follows the rubric.
Agent Claude Code
Use this sub-agent to write hyper-personalized cold email icebreakers for a batch of B2B leads. Spawn one instance per batch of 5 leads. Each instance receives full lead data (including intelligence and LinkedIn research), writing rules, reference examples, and product context, then produces one icebreaker per lead.…
Agent Claude Code
Use this sub-agent to qualify a batch of B2B leads against an ICP definition. Spawn one instance per batch of 10 leads. Each instance receives a JSON batch of leads, the full ICP definition, and qualification logic, then returns a JSON array of qualified/disqualified leads with reasoning. Example: Orchestrator has 606…
Agent Claude Code
Use this sub-agent to conduct deep web research on a batch of B2B leads. Spawn one instance per batch of 5 leads. Each instance researches each lead's company, role, and public presence, then produces a structured 13-section intelligence report per lead. Example: Orchestrator has 40 qualified leads needing web…
Agent Claude Code
Use this sub-agent to orchestrate LinkedIn scraping for all qualified leads via Apify actors. Only ONE instance should be spawned per pipeline run. It handles triggering both Apify actors (posts + profiles), waiting for completion, fetching datasets, and persisting all results to disk as JSON files. Example…
Agent Claude Code
Cuts a video at sentence-aligned silence-midpoint boundaries using the pickcuts algorithm. Takes target cut points, word timings, and a banned-opener list. Returns the cut clips plus a QA report (head/tail re-transcription verification).
Agent Claude Code
Downloads YouTube video at target resolution with fallback chain, fetches transcript via 3-method priority (MCP, youtube-transcript-api, user-provided), runs faster-whisper for word-level timestamps, fetches highest-resolution thumbnail. Returns a JSON manifest pointing at all artifacts.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: