udacity/cd15542-autonomous-marketing-exercises/sa-google-rsa-best-practices
Claude Code and agent skill by udacity/cd15542-autonomous-marketing-exercises
- community
Checking that the SKILL.md file is still in the repository.
Check and adapt Solstice Active Google Ads RSA (Responsive Search Ad) copy against Google's real formatting rules and character limits. Use whenever RSA headlines, descriptions, or paths are being written, reviewed, or fitted — or when someone asks whether copy "fits," is "within limits," or needs trimming for Google Ads. Counts characters exactly (never estimated) and, when copy is over, reports exactly how many characters over.
Install
npx vskill@latest install udacity/cd15542-autonomous-marketing-exercises/sa-google-rsa-best-practicesSKILL.md
Solstice Active — Google RSA best practices
Validate and fit Solstice Active RSA copy against Google's real asset counts and character limits. The limits live in a spec file — always read them from the file, never from memory — and character counts are always exact, never estimated.
Source of truth
All limits and rules come from:
references/sa-google-rsa-specs.md
Do not hard-code or recall limits from this SKILL.md — that reference file is authoritative. If it changes, follow the new numbers.
The exact-count rule (non-negotiable)
Never eyeball or estimate a character count. Every count must come from scripts/sa_check_copy.py, which uses len() over the raw string. When copy is over, state exactly how many characters over and how many to trim — the script prints this for you.
How to check a piece of copy
Run one field at a time. Prefer --stdin so quotes, apostrophes, and emoji in the copy can't break shell quoting:
Or pass it inline with --text "...". Fields: headline (30 chars), description (90 chars), path (15 chars).
The script prints the exact length and a verdict: OK — n/limit, x to spare or OVER by x characters — trim x. Exit code is 0 when within limit, 1 when over.
Check every headline and description individually — never assume one passing means the rest do.
Workflow
- Confirm the asset counts you need from the spec file: this pipeline
always targets 15 headlines and 4 descriptions.
- Run
sa_check_copy.pyper field. Report the exact count vs. limit for
each.
- For anything over, say by exactly how many characters, then rewrite
to fit — preserving meaning and Solstice Active brand voice — and re-run the script to confirm the rewrite is within limit.
- Apply the non-length rules from the spec file too: no duplicate
headlines, each headline stands alone, descriptions complement (don't repeat) headline claims, pin sparingly.
Notes on counting
Counts are by character (Unicode code point), matching how Google counts. An emoji counts as its code points.
Brand voice and claims
This skill governs fit and formatting only. It does not check brand voice — run sa-brand-voice for that. Order: get the message right (voice), then use this skill to fit it to Google's limits.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingm09-content-pipelines/starter/.claude/skills/sa-google-rsa-best-practices/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/udacity/cd15542-autonomous-marketing-exercises/sa-google-rsa-best-practices)