ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Start a clean Claude session with only the context the next task needs, instead of /compact. Captures the goal of your next session, points to the right files (never copies them), and outputs a self-contained prompt to paste into a fresh chat. Use when: "refresh", "refresh
Claude Code
$ npx -y skills add naveedharri/benai-skills --skill refresh --agent claude-code
Codex
$ npx skills add naveedharri/benai-skills --skill refresh -a codex -y
Cursor
$ npx skills add naveedharri/benai-skills --skill refresh -a cursor -y
Gemini CLI
$ npx skills add naveedharri/benai-skills --skill refresh -a gemini-cli -y
GitHub Copilot
$ npx skills add naveedharri/benai-skills --skill refresh -a github-copilot -y
OpenCode
$ npx skills add naveedharri/benai-skills --skill refresh -a opencode -y
Windsurf
$ npx skills add naveedharri/benai-skills --skill refresh -a windsurf -y
version: 0.5.0 name: refresh description: | Start a clean Claude session with only the context the next task needs, instead of /compact. Captures the goal of your next session, points to the right files (never copies them), and outputs a self-contained prompt to paste into a fresh chat. Use when: "refresh", "refresh context", "fresh start", "my chat got sloppy", "start a new chat with context", "hand off this session", outputs degrading, drifting off task. Three levels: lite (quick reset), full (default handoff), ultra (full briefing). NOT for: summarizing in place (that's /compact), or saving permanent notes. disable-model-invocation: true argument-hint: "lite | full | ultra" allowed-tools: Read, Glob, Grep, Write
Long sessions rot: the window fills with stale back-and-forth and outputs get worse. `/compact` summarizes the mess in place and keeps going in the *same* polluted window. Refresh does the opposite. It captures the goal of your next session, points to the right files, and hands you a clean prompt to paste into a fresh chat. Rebuild, not summarize.
1. Ask exactly one question: the goal. Don't interrogate. 2. **Wait for the answer. Stop your turn after asking.** Do not generate the prompt, a draft, or a "default / in the meantime" handoff before the user replies with the goal. The only exception: the user already stated the goal in the trigger, in which case skip the question and proceed. 3. Reference files by **path only**, never copy file content, **but only when the data lives in a file the next session can open.** The fresh session cannot read this chat. So never hand it a pointer to data that has no retrievable home, see the persistence check in the workflow. 4. Be concise. The output is a prompt the user pastes, not a report. No preamble around it. 5. Default level is `full` when none is given.
1. **Get the goal.** Ask "What's the goal of your next session?" then **end your turn and wait**. Do not run any step below until the user answers. Skip this step only if the goal was already stated in the trigger. 2. **Decide where the handoff is going (critical).** A handoff is only useful if its reader can reach the files it references. Figure out the destination:
3. **Scan (full / ultra).** Once you have the goal, work over the conversation already in context and the files it referenced. Lite skips this. 4. **Check every referenced thing is reachable by the reader (critical).** For every piece of work the next session needs, ask: is it saved somewhere that session can open AND that survives into a fresh environment?
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok…
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy…
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative…
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative…
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across…
Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust…
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling…