SEO Drift
AgriciDaniel/codex-seo
SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time.
Manage public/private repository pairs. An agent skill from thatrebeccarae/claude-marketing.
Install Sync Repos
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install thatrebeccarae/claude-marketing sync-repos --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/sync-repos .claude/skills/sync-repos && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .claude/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-reposType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install thatrebeccarae/claude-marketing sync-repos --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/sync-repos .agents/skills/sync-repos && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .agents/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install thatrebeccarae/claude-marketing sync-repos --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/sync-repos .cursor/skills/sync-repos && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .cursor/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/thatrebeccarae/claude-marketing.git --path skills/sync-repos--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install thatrebeccarae/claude-marketing sync-repos --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/sync-repos .gemini/skills/sync-repos && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .gemini/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install thatrebeccarae/claude-marketing sync-reposInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/sync-repos .github/skills/sync-repos && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .github/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install thatrebeccarae/claude-marketing sync-repos --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/sync-repos .opencode/skills/sync-repos && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "sync-repos" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/sync-repos into .opencode/skills/sync-repos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sync-repos", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
sync-repos- GitHub stars
- 162
- Token cost
- ~1.7k tokens
- SKILL.md length
- 825 words
- Files
- 4
- Skills in repo
- 55
- Repo updated
- First seen
- Licence
- MIT
At a glance
Manage public/private repository pairs. An agent skill from thatrebeccarae/claude-marketing.
- Works in 5 steps: Validate paths. Confirm both paths exist… → Detect sync script. Look for… → Compare file lists. Generate sorted file… → …
- Projects that maintain separate dev and public repositories
- SKILL.md covers Install, When to Use, Usage and Procedure, plus 2 more sections
- Calls claude, bash and git; reaches github.com
What it does
Sync Repos is an agent skill from thatrebeccarae/claude-marketing. Manage public/private repository pairs. Verify parity, detect drift, run sync scripts, and validate no sensitive data leaks to the public repo. Use for projects that maintain separate dev and public repositories.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `EXAMPLES.md` and `REFERENCE.md`).
It sits in Marketing & SEO. It works with Git. The repository describes itself as: A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more. Audit, optimize, and report using natural language. The licence is MIT.
When your agent uses it
- Projects that maintain separate dev and public repositories
Example prompts
- “/sync-repos”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Validate paths. Confirm both paths exist and contain .git/ directories. Abort with a clear message if either is not a git repo.
- Detect sync script. Look for scripts/sync-public.sh, scripts/sync-public.conf, or .syncignore in the dev repo. Report whether a sync…
- Compare file lists. Generate sorted file lists for both repos (excluding .git/, node_modules/, dist/). Categorize differences
- Check last sync timestamp. If scripts/sync-public.sh exists, check its last execution time via the most recent commit in the public repo…
- Report. Present a summary table
What it can do on your machine
Read from SKILL.md and the folder at commit a8a63ec. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
claudebashgit
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Sync Repos loads about 1.7k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 825 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:95
- Environment files: `.env`, `.env.*` (except `.env.example`) - NoteMentions a .env fileSKILL.md:127
| `.env`, `.env.*` | Secrets and environment config |
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from thatrebeccarae/claude-marketing at commit a8a63ec, republished under its MIT licence (© thatrebeccarae). 825 words, ~1,749 tokens.
Download SKILL.mdSave it as
.claude/skills/sync-repos/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- sync-repos
- description
- Manage public/private repository pairs. Verify parity, detect drift, run sync scripts, and validate no sensitive data leaks to the public repo. Use for projects that maintain separate dev and public repositories.
- license
- MIT
- origin
- custom
- author
- Rebecca Rae Barton
- author_url
- https://github.com/thatrebeccarae
- metadata.version
- 1.0.0
- metadata.category
- devops
- metadata.domain
- git
- metadata.updated
- 2026-03-19
- metadata.tested
- 2026-03-19
- metadata.tested_with
- Claude Code v2.1
Sync Repos
Manage public/private repository pairs. Verify parity between a dev (private) repo and its public counterpart, detect drift, run sync scripts, validate results, and ensure no PII or secrets leak to the public side.
Install
claude install-skill https://github.com/thatrebeccarae/claude-skills/tree/main/sync-reposWhen to Use
- Before pushing a public repo — verify the sync is clean and current
- After major dev work — check whether the public repo has drifted behind
- On a periodic cadence — weekly or before releases, catch unsynced changes early
- When setting up a new public/private repo pair for the first time
Usage
/sync-repos check [dev-path] [public-path]— Compare repos and report drift/sync-repos sync [dev-path] [public-path]— Run sync script and validate/sync-repos setup [dev-path] [public-path]— Create initial sync-public.sh and config
If paths are omitted, prompt the user for them. Look for .syncignore or scripts/sync-public.conf in the dev repo to auto-detect the pair.
Procedure
Check Mode
Validate paths. Confirm both paths exist and contain
.git/directories. Abort with a clear message if either is not a git repo.Detect sync script. Look for
scripts/sync-public.sh,scripts/sync-public.conf, or.syncignorein the dev repo. Report whether a sync mechanism exists.Compare file lists. Generate sorted file lists for both repos (excluding
.git/,node_modules/,dist/). Categorize differences:- Expected exclusions — files matching known exclusion patterns (see Common Exclusion Patterns below) or listed in
.syncignore/sync-public.conf - Unexpected drift — files present in dev but missing from public that are NOT in any exclusion list
- Diverged files — files present in both repos but with different content (compare via
sha256sumorgit hash-object) - Public-only files — files in public but not in dev (legitimate: README, CONTRIBUTING, LICENSE, .github/)
- Expected exclusions — files matching known exclusion patterns (see Common Exclusion Patterns below) or listed in
Check last sync timestamp. If
scripts/sync-public.shexists, check its last execution time via the most recent commit in the public repo that matches a sync pattern. Compare against the latest commit in the dev repo.Report. Present a summary table:
- Sync script: found / not found
- Files only in dev (expected): count
- Files only in dev (unexpected): count + list
- Diverged files: count + list
- Public-only files: count + list
- Estimated drift: number of dev commits since last sync
- Recommendation: "in sync", "minor drift", or "sync needed"
Sync Mode
Run check first. Execute the full check procedure above. If no drift is detected, report "already in sync" and stop.
Locate sync script. Look for
scripts/sync-public.shin the dev repo. If not found, ask the user whether to run setup mode to create one.Preview the sync. Show what the sync script will do — files to copy, exclusions, text replacements. Require user confirmation before proceeding.
Execute the sync script. Run from the dev repo root:
bash bash scripts/sync-public.shCapture stdout and stderr. If the script exits non-zero, report the error and stop.
Post-sync validation. After the script completes:
- Run the check procedure again to confirm parity
- Scan the public repo diff for PII and secrets (see REFERENCE.md for scan patterns)
- Flag any findings and block until resolved
Report results. Summarize:
- Files synced: count
- Exclusions applied: count
- PII/secrets scan: clean or findings
- Next step: "Review changes in public repo, then
/safe-pushwhen ready"
Show full SKILL.md (318 more words)Show less
Setup Mode
Scan the dev repo. Identify files and directories that should NOT sync to public:
- Environment files:
.env,.env.*(except.env.example) - Planning/internal:
.planning/,.claude/,CLAUDE_CONTEXT.md,briefs/ - Data/build artifacts:
data/,dist/,node_modules/,.git/ - Sync infrastructure:
scripts/sync-public.sh,scripts/sync-public.conf - Sensitive config:
*.pem,*.key,*.plist,config/soul.md - Project-specific patterns detected via
.gitignoreanalysis
- Environment files:
Generate sync-public.conf. Create a config file with:
SOURCE_DIRandTARGET_DIRvariablesPACKAGE_NAMEfor the public repoEXCLUDE_PATHSarray with all identified exclusionsPRESERVE_PATHSarray for public-only files (README, LICENSE, .github/)
Generate sync-public.sh. Create the sync script using the rsync-based template from REFERENCE.md. Include:
- Config file sourcing
- Path validation
- Target cleanup (preserve
.git/andPRESERVE_PATHS) - rsync with
--delete-excludedand exclusion list - Personal data leak check
- File count summary
User review. Display the generated config and script. Wait for explicit approval before writing.
Write files. Save
scripts/sync-public.sh(chmod +x) andscripts/sync-public.confto the dev repo.
Common Exclusion Patterns
These patterns are excluded from sync by default. Append project-specific patterns as needed.
| Pattern | Reason |
|---|---|
.git/ | Git history stays separate |
.env, .env.* | Secrets and environment config |
.planning/ | Internal planning docs |
.claude/ | Claude Code project config |
CLAUDE_CONTEXT.md | Internal agent context |
data/ | Local data / databases |
dist/, node_modules/ | Build artifacts |
*.pem, *.key | Private key material |
*.plist | macOS service config |
scripts/sync-public.* | Sync infrastructure itself |
briefs/ | Internal content briefs |
config/soul.md | Personal agent config |
Key Principles
- Never auto-push. Sync writes files locally. Pushing to remote is always a separate, user-confirmed step via
/safe-push. - Always validate after sync. Every sync run ends with a PII/secrets scan on the public repo. No exceptions.
- Exclusion list is append-only. Never remove exclusion patterns without explicit user approval. It is safer to exclude too much than too little.
- Preserve public-only files. The public repo may have its own README, LICENSE, CONTRIBUTING, .github/ workflows. Sync must never overwrite these.
- Conf is separate from script. Keep
sync-public.confseparate so exclusion lists are easy to review and update without touching script logic.
© thatrebeccarae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files in skills/sync-repos of thatrebeccarae/claude-marketing.
- SKILL.md
- EXAMPLES.md
- LICENSE
- REFERENCE.md
Open the folder on GitHubat commit a8a63ec
Compare with similar skills
Sync Repos next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Sync Repos this skillthatrebeccarae/claude-marketing | 162 | — | ~1.7k | Automated safety check: Notes | MIT | |
| SEO DriftAgriciDaniel/codex-seo | 797 | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| SEO Autopilotkennyzir/7deer_skills | 322 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Yalc OrientationOthmane-Khadri/YALC-the-GTM-operating-system | 317 | — | ~1k | Automated safety check: Notes | MIT | |
| Idea Validatorluongnv89/skills | 131 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Wiki LLMs Txtmicrosoft/skills | 3.1k | — | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
SEO Autopilot
kennyzir/7deer_skills
全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录，自动生成落地页和博客文章，运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。
Yalc Orientation
Othmane-Khadri/YALC-the-GTM-operating-system
First-touch onboarding for someone who just opened the YALC repo.
Idea Validator
luongnv89/skills
Validate app/startup ideas with market, feasibility, commercial, and open-source competitor analysis.
- Official
Wiki LLMs Txt
microsoft/skills
Generates llms.txt and llms-full.txt files for LLM-friendly project documentation following the llms.txt specification.
SEO AI Optimizer
luongnv89/skills
Audit and optimize websites for technical SEO, content SEO, and AI bot accessibility.
More from thatrebeccarae/claude-marketing
All 55 skills in this repoGoogle Analytics
thatrebeccarae/claude-marketing
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements.
Content Creator
thatrebeccarae/claude-marketing
Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.
Klaviyo Analyst
thatrebeccarae/claude-marketing
Klaviyo marketing operations and analyst expertise. An agent skill from thatrebeccarae/claude-marketing.
Klaviyo Developer
thatrebeccarae/claude-marketing
Klaviyo API and developer integration expertise. An agent skill from thatrebeccarae/claude-marketing.
Looker Studio
thatrebeccarae/claude-marketing
Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.
Shopify
thatrebeccarae/claude-marketing
Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.
Related
Works with
Categories
Questions about Sync Repos
What does Sync Repos do?
Manage public/private repository pairs. An agent skill from thatrebeccarae/claude-marketing. Sync Repos is an agent skill from thatrebeccarae/claude-marketing. Manage public/private repository pairs.
When should I use Sync Repos?
Sync Repos fits situations like: projects that maintain separate dev and public repositories.
How do I install Sync Repos in Claude Code?
Run `npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a claude-code`. Or copy the skill folder (skills/sync-repos in thatrebeccarae/claude-marketing) into .claude/skills/sync-repos in your project. Claude Code loads it when a task matches its description.
How do I install Sync Repos in Codex?
Run `npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a codex`. Or copy the skill folder (skills/sync-repos in thatrebeccarae/claude-marketing) into .agents/skills/sync-repos in your project. Codex loads it when a task matches its description.
Can I use Sync Repos in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thatrebeccarae/claude-marketing --skill sync-repos -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sync-repos, .gemini/skills/sync-repos, .github/skills/sync-repos and .opencode/skills/sync-repos in your project.
What does Sync Repos need to run?
Going by SKILL.md and its folder, Sync Repos needs the command-line tools its instructions call (claude, bash and git).
Does Sync Repos access the network?
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Sync Repos safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Sync Repos use?
Sync Repos is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Sync Repos use?
About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Sync Repos?
Skills that share tags, products or a category with Sync Repos: SEO Drift (AgriciDaniel/codex-seo, 797 stars), SEO Autopilot (kennyzir/7deer_skills, 322 stars), Yalc Orientation (Othmane-Khadri/YALC-the-GTM-operating-system, 317 stars) and Idea Validator (luongnv89/skills, 131 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Sync Repos?
thatrebeccarae (a GitHub user) maintains it in thatrebeccarae/claude-marketing, which has 162 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on May 14, 2026.
Source: thatrebeccarae/claude-marketing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.