90 Day SEO Sprint
Bomx/distribb-skill
Run the Distribb 90-Day SEO Sprint - a founder-built 13-week playbook for shipping pre-launch SEO, core pages, a content engine, and a backlink starter stack on the way to compounding organic traffic.
A skill your agent uses when the user wants to review link-building outreach opportunities, find contact information for article authors, generate personalized outreach drafts, process a list of…
$ npx skills add LeoYeAI/openclaw-master-skills --skill link-building-outreach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills link-building-outreach --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/seo-outreach-skill .claude/skills/link-building-outreach && 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 "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .claude/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skillType 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 LeoYeAI/openclaw-master-skills --skill link-building-outreach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills link-building-outreach --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/seo-outreach-skill .agents/skills/link-building-outreach && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .agents/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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 LeoYeAI/openclaw-master-skills --skill link-building-outreach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills link-building-outreach --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/seo-outreach-skill .cursor/skills/link-building-outreach && 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 "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .cursor/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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/LeoYeAI/openclaw-master-skills.git --path skills/seo-outreach-skill--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 LeoYeAI/openclaw-master-skills --skill link-building-outreach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills link-building-outreach --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/seo-outreach-skill .gemini/skills/link-building-outreach && 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 "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .gemini/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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 LeoYeAI/openclaw-master-skills link-building-outreachInstalls 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 LeoYeAI/openclaw-master-skills --skill link-building-outreach -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/seo-outreach-skill .github/skills/link-building-outreach && 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 "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .github/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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 LeoYeAI/openclaw-master-skills --skill link-building-outreach -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills link-building-outreach --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/seo-outreach-skill .opencode/skills/link-building-outreach && 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 "link-building-outreach" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/seo-outreach-skill into .opencode/skills/link-building-outreach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "link-building-outreach", 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.
link-building-outreachA skill your agent uses when the user wants to review link-building outreach opportunities, find contact information for article authors, generate personalized outreach drafts, process a list of…
Link Building Outreach is an agent skill from LeoYeAI/openclaw-master-skills. Use this skill when the user wants to review link-building outreach opportunities, find contact information for article authors, generate personalized outreach drafts, process a list of opportunities, or prepare an outreach campaign for manual sending. Trigger this skill whenever the user mentions "outreach", "link building", "邮件外链", "contact author", "backlink campaign", "find email for", or asks to process a spreadsheet or CSV of outreach targets.
Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including assets (for example `README.md`, `_meta.json` and `agents/openai.yaml`).
It sits in Marketing & SEO, covering Link building and Excel spreadsheets. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
SERPAPI_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Link Building Outreach loads about 4.6k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 2,102 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.
The automated check found no risky patterns in SKILL.md.
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.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 2,102 words, ~4,580 tokens.
.claude/skills/link-building-outreach/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.Reviews the full link building outreach pipeline: reads your opportunity list, finds author contacts, analyzes target articles, and generates personalized outreach drafts for manual sending.
Use this skill to turn outreach opportunities into a structured workflow: article analysis, contact discovery, personalized email drafting, and follow-up planning.
Setup outreach — my product is https://yourproduct.com, my audience is SEO teams, my name is Jane, my title is FounderPrepare outreach draftsPrepare outreach drafts for https://example.com/best-seo-toolsThis workflow can touch external services. Use the minimum credentials needed for the stage you are running:
GOOGLE_SHEETS_TRACKER_URL: optional source for opportunity rows; prefer read-only or exported CSVSERPAPI_API_KEY: recommended for article discovery and search-driven contact researchIf these are unavailable:
Safe default: this skill should stop at research, contact discovery, and draft generation.
Core principle: The only reason outreach emails don't get replies is that authors can tell in one second it's a mass template. Every step in this pipeline exists to produce one thing: an email that could only have been written for that specific article.
First time: Tell Claude:
"Setup outreach — my product is [URL], my audience is [description], my name is [name], my title is [title]"
Every time after:
"Prepare outreach drafts" or "Prepare outreach drafts from this CSV / sheet export"
Ask the user for these four things if not already provided:
| Input | Description | Example |
|---|---|---|
| Product URL | Main product/service page | https://yourproduct.com |
| Target Audience | Who uses the product | SEO professionals, growth hackers |
| Your Name | For email signature | Jane Smith |
| Your Title | Job title | Founder at Acme SEO |
⚠️ Note: Competitor analysis requires either a manually provided competitor list or a connected SEO API. Claude will ask if none is available.
Store all setup output in memory for the session. If context is lost, re-run setup.
Source: A connected tracker if explicitly configured, or a CSV/table pasted directly.
Required columns:
| Column | Description | Example |
|---|---|---|
URL | Target article to get a link from | https://example.com/best-seo-tools |
Target Page | Your page to link to | https://yourproduct.com |
Status | Processing flag | pending |
Auto-detected optional columns: Article Type, Anchor Text, Notes
If a tracker is explicitly configured, filter to rows where Status = pending. Update Status to processed after each row completes. If no tracker is configured, ask the user for a pasted list or CSV export instead.
Fetch each target URL and classify based on title keywords and page structure:
| Type | Detection Signals | Author's Core Interest |
|---|---|---|
| Best / Top List | Title: best, top, N tools, review of | Content coverage — did I miss anything important? |
| How-to / Tutorial | Title: how to, guide, tutorial, step-by-step | Reader success — can readers actually complete each step? |
| Review / Comparison | Title: review, vs, comparison, alternatives | Helping readers choose — did I cover the right options? |
| Resource Page | Many outbound links, aggregator structure | Resource completeness — is this list genuinely useful? |
| Other | Cannot classify | Flag for manual review |
Why this matters: The same product needs a completely different pitch depending on article type. For a Top List, the angle is "your list is missing this tool." For a How-to, the angle is "this tool removes the hardest manual step in your tutorial." Same product, entirely different email. Getting the type wrong means the entire email will feel off.
If user pre-filled Article Type, skip detection and use their value.
Priority principle: Finding the right person matters more than finding any email. Sending to the actual author or site owner gets 3-5x higher reply rates than sending to a generic contact address.
Never guess an email address. A guessed email that bounces damages your sending domain's reputation and flags your domain as a spam source. An honest "Not Found" is always better than an unreliable guess.
Search in this priority order. Stop as soon as a high-confidence result is found:
1. Article byline
→ Extract author full name
→ Search "author name + site domain" to find their contact
2. Website Contact / About page
→ Visit /contact, /about, /team, /advertise
→ Extract any email directly listed — this is the most reliable source
3. Author personal website
→ If byline links to author's own site, visit it
→ Check their About or Contact page
4. Twitter/X bio
→ If author has a linked Twitter profile, visit it
→ Check bio text and pinned tweet for email
5. Not found
→ Mark as Not Found
→ Recommend Twitter DM or LinkedIn message instead
→ Do NOT attempt to guess or construct an email address⚠️ LinkedIn: LinkedIn prohibits automated data scraping. If LinkedIn is the only available source, flag the entry as
confidence: Lowand explicitly recommend manual DM. Do not attempt to extract data from LinkedIn profiles.
Output per entry:
email: john@example.com
source: contact page / byline search / Twitter bio / not found
confidence: High / Medium / Low / Not FoundConfidence levels and recommended actions:
| Confidence | Meaning | Action |
|---|---|---|
| High | Directly from Contact page or official source | Send immediately |
| Medium | From social bio or indirect page | Quick verify on Hunter.io before sending |
| Low | Single unverified source | Must verify on Hunter.io before sending |
| Not Found | All channels exhausted | Switch to Twitter DM or LinkedIn message |
This step determines email quality. Generic outreach tools stop at Step 3. The difference between a reply and an ignored email is almost entirely decided here.
Fetch and read the full article content. Extract four things:
① Find a specific, quotable reference to use in the email
Goal: Make the author know in the first sentence that you genuinely read their article — not a bot, not a template.
Find one specific thing from the article: a concrete claim, a data point, a recommendation, or a position the author took. This will be the opening of the email.
❌ Without this analysis:
"I really enjoyed your article on SEO tools. It was very insightful!" (Could apply to any article. Author ignores it.)
✅ With this analysis:
"Read your SEO tools comparison — you pointed out that most tools have a 24-48hr backlink data lag. That's something we hear constantly from users too." (References something specific. Author thinks: "This person actually read it.")
② Identify the content gap — your entry point
Find what the article does NOT cover: a tool category, a use case, a type of user, or a feature area that's missing.
This gap is the reason your product belongs in the article. It's not "our product is great" — it's "your article covers X and Y but not Z, and Z is what [Your Product] does."
Example: An article reviewing 10 SEO tools covers keyword research, technical audit, and backlink analysis — but says nothing about AI Overview tracking. If your product tracks AI Overviews, that's the gap. The pitch writes itself.
③ Assess the author's writing style and audience
Determine: Is this author data-driven or experience-driven? Are they writing for beginners or experts? Is the tone formal or casual?
This directly controls the email's tone and vocabulary. A mismatch in tone — too formal for a casual blogger, too casual for a professional publication — will make even good content feel wrong.
| Author Style | Email Approach |
|---|---|
| Data-driven, cites research | Lead with numbers or a specific metric |
| Experience-based, practical | Lead with a relatable scenario or problem |
| Beginner-focused | Plain language, explain what your product does simply |
| Expert/technical | Skip basics, reference specific technical differentiation |
| Casual, conversational | Short sentences, informal language, no corporate speak |
| Formal, professional | Complete sentences, structured, no slang |
④ Define the one-sentence relevance statement
Combine the above three into a single sentence: what your product does for THIS article's readers in THIS specific context.
This sentence is the core of the email body. Everything else supports it.
Produce this analysis card before writing the email:
article_summary: [one sentence on what the article covers and its main conclusion]
key_reference: [the specific quote, claim, or section to open the email with]
gap_identified: [what topic/tool/use case is missing that your product covers]
author_style: [data-driven / experience / beginner / expert + formal / casual]
relevance_statement: [one sentence: your product helps this author's readers do X]Using setup data + the Step 4 analysis card, generate one email per opportunity.
Five non-negotiable rules:
Rule 1: Under 150 words — strictly enforced
Authors are busy. Every word over 150 reduces reply probability. The email must be completable in 30 seconds. If you cannot say it in 150 words, cut — don't expand.
Rule 2: First sentence must prove you read the article
Never open with:
Open with the specific reference identified in Step 4①. Make the author's first reaction be "this person actually read my piece."
Rule 3: Reference ONE specific piece of content — never generic praise
One precise reference > five vague compliments.
❌ Generic: "Your article was really comprehensive and well-researched." ✅ Specific: "Your point about backlink data lag (24-48hrs for most tools) is something our users bring up constantly."
Rule 4: One ask only — make it impossible to misunderstand
The author must finish reading and know exactly what you want them to do.
❌ Vague: "Would love to explore some collaboration opportunities or a potential partnership." ✅ Clear: "Would it make sense to add [Product] to your list? Happy to set up a free trial account."
One action. Clear outcome. Low effort to say yes.
Rule 5: Match tone to author style
Use the author style assessment from Step 4③. Casual author = casual email. Technical author = technical email. This is not optional — tone mismatch is one of the most common reasons good pitches get ignored.
Full before/after example:
Target article: "Top 10 SEO Tools in 2025" Author style: Data-driven, professional, expert audience
❌ Email without Skill:
Subject: Partnership Opportunity
Hi,
Hope this email finds you well. I came across your article about SEO
tools and found it very helpful and insightful.
I wanted to reach out because we have a great SEO tool called [Product]
that I think would be a great fit for your article. It has many amazing
features including keyword tracking, backlink analysis, site audit,
and much more.
Would love to discuss a potential partnership or collaboration.
Please let me know if you're interested.
Best regards,
[Name]✅ Email with Skill:
Subject: One gap in your SEO tools roundup
Hi [Name],
Read your SEO tools comparison — your point about backlink data lag
(24-48hrs for most tools) is something we hear constantly from users.
One category your roundup doesn't cover: AI Overview tracking.
It's becoming a significant organic traffic source, and [Product]
focuses on exactly this — showing which queries trigger AI Overviews
and whether your content appears in them.
Happy to set up a free trial if you're considering adding a new category.
[Name] · [Title]Why the second email works:
| Dimension | ❌ Without Skill | ✅ With Skill |
|---|---|---|
| Opening | Generic filler | References specific article content |
| Product description | "Amazing, many features" | One sentence, specific use case |
| Relevance | None | Tied directly to an identified gap |
| Ask | Vague (partnership) | Clear (free trial for new category) |
| Author reaction | "Another mass email" | "This person read my article" |
Templates by article type (use as base, always customize with Step 4 analysis):
Best/Top List:
Hi [Name], read your [article title] — [specific reference from Step 4①]. One tool missing from your list: [Your Product]. [One-sentence relevance from Step 4④]. Happy to set up a free trial if you're considering an update. — [Your Name], [Title]
How-to / Tutorial:
Hi [Name], your guide on [topic] is one of the cleaner ones I've found — especially [specific section from Step 4①]. One addition that might help your readers: [Your Product] handles [the hard manual step] automatically. Worth a mention if it fits. — [Your Name], [Title]
Review / Comparison:
Hi [Name], solid breakdown of [tools compared] — [specific reference from Step 4①]. One tool that didn't make the list: [Your Product]. Key difference from [competitor they mentioned]: [differentiator from gap analysis]. Happy to share more if you're considering an update. — [Your Name], [Title]
Resource Page:
Hi [Name], found your [page title] while researching [topic]. [Your Product] might be worth adding — [one-sentence relevance]. Let me know if you'd like to take a look. — [Your Name], [Title]
This is where drafts become a fully automated pipeline. Step 6 has three parts: review, send, and loop.
Output all processed entries in a table:
| # | Target URL | Article Type | Source | Confidence | Subject | Body | Status | |
|---|---|---|---|---|---|---|---|---|
| 1 | [url] | Best/Top | john@x.com | Contact page | High | [subject] | [body] | processed |
| 2 | [url] | How-to | not found | — | Not Found | [subject] | [body] | processed |
User reviews each row. Confidence-based actions before sending:
| Confidence | Action |
|---|---|
| High | Ready to send |
| Medium | Quick verify on Hunter.io, then send |
| Low | Must verify on Hunter.io before sending |
| Not Found | Switch to Twitter DM or LinkedIn message — remove from send queue |
Always review emails before sending. This Skill generates drafts — you approve. Speed is the AI's job. Quality is yours.
This public skill stops at reviewed drafts, contact notes, and follow-up plans.
If the user wants actual delivery or inbox handling:
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 5 other files (assets) in skills/seo-outreach-skill of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
Link Building Outreach 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 |
|---|---|---|---|---|---|---|
| Link Building Outreach this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.6k | Automated safety check: Pass | MIT | |
| 90 Day SEO SprintBomx/distribb-skill | 197 | — | ~3.6k | Automated safety check: Pass | None | |
| FLOW SEO FrameworkAgriciDaniel/claude-seo | 19k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | |
| SEO DataforseoAgriciDaniel/codex-seo | 799 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Backlink CheckRyze-AI-Adgent/open-seo-mcp-skills | 4.7k | — | ~515 | Automated safety check: Pass | MIT | |
| Beyondseobeyondtahir/beyondseo | 161 | — | ~4.3k | Automated safety check: Pass | MIT |
Bomx/distribb-skill
Run the Distribb 90-Day SEO Sprint - a founder-built 13-week playbook for shipping pre-launch SEO, core pages, a content engine, and a backlink starter stack on the way to compounding organic traffic.
AgriciDaniel/claude-seo
Brings the FLOW framework's stage-specific SEO prompts into the agent, from keyword discovery through backlinks, on-page work and conversion to local SEO, loaded on demand.
AgriciDaniel/codex-seo
Live SEO data via DataForSEO MCP server. An agent skill from AgriciDaniel/codex-seo.
Ryze-AI-Adgent/open-seo-mcp-skills
Backlink profile for any domain — referring domains, authority, anchors, new/lost links, and a side-by-side vs a competitor.
beyondtahir/beyondseo
Audit websites, apply authorised SEO improvements and plan content, competitors and backlinks with evidence, design checks and optional project monitoring.
xnohat/webobsidian
Read, write, search, and manage notes in a WebObsidian vault through its Agent REST API (/api/v1).
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Categories
A skill your agent uses when the user wants to review link-building outreach opportunities, find contact information for article authors, generate personalized outreach drafts, process a list of…. Link Building Outreach is an agent skill from LeoYeAI/openclaw-master-skills. Use this skill when the user wants to review link-building outreach opportunities, find contact information for article authors, generate personalized outreach drafts, process a list of opportunities, or prepare an outreach campaign for manual sending.
Link Building Outreach fits situations like: the user wants to review link-building outreach opportunities; find contact information for article authors; generate personalized outreach drafts; process a list of opportunities.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill link-building-outreach -a claude-code`. Or copy the skill folder (skills/seo-outreach-skill in LeoYeAI/openclaw-master-skills) into .claude/skills/link-building-outreach in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill link-building-outreach -a codex`. Or copy the skill folder (skills/seo-outreach-skill in LeoYeAI/openclaw-master-skills) into .agents/skills/link-building-outreach in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill link-building-outreach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/link-building-outreach, .gemini/skills/link-building-outreach, .github/skills/link-building-outreach and .opencode/skills/link-building-outreach in your project.
Going by SKILL.md and its folder, Link Building Outreach needs credentials named SERPAPI_API_KEY. Our summary lists: Python 3; A credential in SERPAPI_API_KEY.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Link Building Outreach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Link Building Outreach: 90 Day SEO Sprint (Bomx/distribb-skill, 197 stars), FLOW SEO Framework (AgriciDaniel/claude-seo, 19k stars), SEO Dataforseo (AgriciDaniel/codex-seo, 799 stars) and Backlink Check (Ryze-AI-Adgent/open-seo-mcp-skills, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.