ads-audit
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads…
Bootstrap a second-brain structure inside a Baalda vault and run personalized onboarding. Creates all directories, system files, per-folder routing indexes and starter context, then interviews the user to personalize everything. Two modes — Solopreneurs/Professionals (default),
$ npx -y skills add naveedharri/benai-skills --skill setup --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/setupContext preview
The summary Claude sees to decide when to auto-load this skill.
Bootstrap a second-brain structure inside a Baalda vault and run personalized onboarding. Creates all directories, system files, per-folder routing indexes and starter context, then interviews the user to personalize everything. Two modes — Solopreneurs/Professionals (default),
name: setup description: Bootstrap a second-brain structure inside a Baalda vault and run personalized onboarding. Creates all directories, system files, per-folder routing indexes and starter context, then interviews the user to personalize everything. Two modes — Solopreneurs/Professionals (default), Business/Teams. Use when the user says "set up my Baalda vault", "set up my second brain", "bootstrap", "initialize", "onboarding", or runs /setup.
USE WHEN the user runs `/setup` or asks to set up their Baalda vault, bootstrap the second brain, initialize the system, or turn a folder of notes into an AI-operated OS.
Baalda notes are plain `.md` files on disk, so everything this skill builds is just files and folders — no plugins to install, no import step. The moment you write them, the app indexes them, and if the vault is synced they appear for every teammate live.
These are app invariants, not preferences. Breaking them corrupts note identity or the sync state.
1. **Run from the vault root.** The vault root is the folder the user opened in Baalda. Everything below writes relative to it. If the current directory isn't that folder, stop and ask. 2. **`.context/` is off-limits.** Baalda keeps its SQLite index, CRDT store and `config.json` in `<vault>/.context/`. Never read, write, walk, move, index, or `git add` it. Same for `.git`. 3. **Write files, don't shell out to move them.** Creating and editing `.md` files with normal tools is fully supported — the watcher picks the change up in ~150ms and merges it as a CRDT operation, so an AI edit and a human keystroke coexist instead of clobbering. 4. **Never `mv` or `rm` a note that is already synced.** A note's identity is a `doc_id`, not its path. An external move looks like *delete + create* to the app: the note gets a **new** `doc_id`, and its history, backlinks and share settings do not follow. Rename and move synced notes **in the app**, or through the `move_note` / `move_folder` tools if this session is connected over Baalda's MCP endpoint. During first-time setup on a brand-new vault there is nothing to fork yet, so the `mkdir`s below are safe. 5. **Attachments live in `attachments/`.** Images and files the user drops into a note land there. Leave that folder alone; it is not part of the note pipeline. 6. **Markdown Baalda understands:** YAML frontmatter, `[[wikilinks]]` (backlinks + graph view are derived from them), `#tags`, and standard CommonMark. Prefer wikilinks over relative paths so links survive a later move.
---
This is a three-phase process:
First confirm **where** you are. Print the current directory and check for `.context/`:
pwd && ls -a | grep -E '^\.context$' || echo "no .context/ — not yet opened in Baalda"
anyway, and at the end tell the user to open this exact folder in Baalda (**Open vault**), which creates `.context/` and indexes everything you just wrote. Do not create `.context/` yourself.
Then check if `claude.md` or `CLAUDE.md` exists **only** in the current working directory (do NOT search subdirectories or parent directories — check only the exact CWD path).
---
Ask the user to pick a mode using AskUserQuestion with these exact `label` and `description` values:
**CRITICAL**: You MUST pass both `label` AND `description` for each option in AskUserQuestion. The `description` field is what explains each mode to the user. Never leave `description` empty.
Mode mapping:
Accept any clear signal: "solo", "professional", "freelancer", "business", "org", "team", etc.
If the user skips or says "I don't know", use **Solopreneurs/Professionals** (professional mode).
Store the selected mode. It will be written to `CLAUDE.md` frontmatter as `os-mode: professional | business`.
---
Create the directory structure and write all system files for the selected mode.
Every `references/<file>.md` mentioned below lives in the `references/` subdirectory next to **this SKILL.md** — not in the user's working directory. Two conventions matter:
If the Read tool can't open a `references/...` path directly (some harnesses mount the skill at a path that differs between Read and Bash), run a quick discovery step **once** before Step A.2:
# Find the references directory; cache the result for the rest of Phase A. find / -type d -path '*/setup/refer
Expert automation skills for Claude Code, organized by department.
Repo: naveedharri/benai-skills
Full multi-platform paid advertising audit with parallel subagent delegation. Analyzes Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads, and Microsoft Ads…
Budget allocation and bidding strategy review across all ad platforms. Evaluates spend distribution, bidding strategy appropriateness, scaling readiness, and…
Competitor ad intelligence analysis across Google, Meta, LinkedIn, TikTok, and Microsoft. Analyzes competitor ad copy, creative strategy, keyword targeting,…
Cross-platform creative quality audit covering ad copy, video, image, and format diversity across all platforms. Detects creative fatigue, evaluates…
Google Ads deep analysis covering Search, Performance Max, Display, YouTube, and Demand Gen campaigns. Evaluates 74 checks across conversion tracking, wasted…
Landing page quality assessment for paid advertising campaigns. Evaluates message match, page speed, mobile experience, trust signals, form optimization, and…