Updated 2w ago
by sandbaseai
sandbase-skills
88 installable open-source Agent Skills for research, social intelligence, marketing, and business workflows—compatible with Codex, Claude Code, Cursor, Gemini CLI, and DeepSeek Harness.
201 GitHub stars (201)
+1 in 20 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | +1 |
| Sep 30 | +1 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | −1 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +1 |
| Oct 10 | +1 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | −1 |
| Oct 15 | 0 |
| Oct 16 | −1 |
- 30 skills (30 skills found in its SKILL.md files)
- 20 forks (20 forks)
- 2w ago last update (Last updated 2w ago)
Install
Skills CLI
npx skills add sandbaseai/sandbase-skills
Asks which skills and agents to install. Just one: npx skills add sandbaseai/sandbase-skills --skill accessibility-review — add -g for every project.
Claude Code
git clone https://github.com/sandbaseai/sandbase-skillscp -r "sandbase-skills/marketing/accessibility-review" ~/.claude/skills/
Copies the accessibility-review skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add sandbaseai/sandbase-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 246 files.
-
accessibility-review
Create, implement, or review accessibility review work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on accessibility review.
marketing/accessibility-review/SKILL.md on GitHub (opens in a new tab) -
agentic-eval
Plan, implement, or review agentic eval work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests agentic eval work.
marketing/agentic-eval/SKILL.md on GitHub (opens in a new tab) -
ai-seo
Create or review ai seo deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for ai seo work.
marketing/ai-seo/SKILL.md on GitHub (opens in a new tab) -
airflow-dag-patterns
Apply airflow dag patterns in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses airflow dag patterns or its strengths fit the task.
marketing/airflow-dag-patterns/SKILL.md on GitHub (opens in a new tab) -
alternative-blog-writer
Create or review alternative blog writer deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for alternative blog writer work.
marketing/alternative-blog-writer/SKILL.md on GitHub (opens in a new tab) -
api-designer
Plan, implement, or review api designer work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests api designer work.
marketing/api-designer/SKILL.md on GitHub (opens in a new tab) -
appinsights-instrumentation
Plan, implement, or review application insights instrumentation work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests application insights instrumentation work.
marketing/appinsights-instrumentation/SKILL.md on GitHub (opens in a new tab) -
audit-support
Create or review audit support deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for audit support planning or analysis.
marketing/audit-support/SKILL.md on GitHub (opens in a new tab) -
azure-role-selector
Plan, implement, or review azure role selector work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests azure role selector work.
marketing/azure-role-selector/SKILL.md on GitHub (opens in a new tab) -
backlink-analysis
Research and evaluate backlink analysis with current authoritative sources, provenance, and explicit evidence gaps. Use when the user asks for backlink analysis findings or verification.
marketing/backlink-analysis/SKILL.md on GitHub (opens in a new tab) -
backlink-gap-analysis
Find and prioritize ethical backlink and digital-PR opportunities using SandBase DataForSEO backlink data. Use when asked to analyze backlink profiles, find referring-domain gaps, compare link competitors, or prepare a link-outreach target list.
marketing/backlink-gap-analysis/SKILL.md on GitHub (opens in a new tab) -
backtesting-frameworks
Apply backtesting frameworks in reproducible local data workflows with version-aware APIs, explicit assumptions, and validation. Use when the user chooses backtesting frameworks or its strengths fit the task.
marketing/backtesting-frameworks/SKILL.md on GitHub (opens in a new tab) -
beautiful-article
Create, implement, or review beautiful article work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on beautiful article.
marketing/beautiful-article/SKILL.md on GitHub (opens in a new tab) -
behave-skill
Plan, implement, or review behave bdd work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests behave bdd work.
marketing/behave-skill/SKILL.md on GitHub (opens in a new tab) -
brainstorm-experiments-new
Create or review brainstorm experiments new deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for brainstorm experiments new planning or analysis.
marketing/brainstorm-experiments-new/SKILL.md on GitHub (opens in a new tab) -
business-model
Create or review business model deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for business model planning or analysis.
marketing/business-model/SKILL.md on GitHub (opens in a new tab) -
call-prep
Create or review call prep deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for call prep planning or analysis.
marketing/call-prep/SKILL.md on GitHub (opens in a new tab) -
captions-overlay
Create, implement, or review captions overlay work with format, accessibility, performance, and visual-verification controls. Use when the requested deliverable depends on captions overlay.
marketing/captions-overlay/SKILL.md on GitHub (opens in a new tab) -
cash-flow-snapshot
Create a 30/60/90-day cash-flow forecast from AR, AP, opening cash, payment timing, and fixed-cost data. Use when asked about runway, payroll coverage, liquidity risks, or a near-term cash crunch.
marketing/cash-flow-snapshot/SKILL.md on GitHub (opens in a new tab) -
chrome-devtools
Plan, implement, or review chrome devtools work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests chrome devtools work.
marketing/chrome-devtools/SKILL.md on GitHub (opens in a new tab) -
churn-prevention
Create or review churn prevention deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for churn prevention work.
marketing/churn-prevention/SKILL.md on GitHub (opens in a new tab) -
ci-cd-and-automation
Plan, implement, or review ci/cd and automation work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests ci/cd and automation work.
marketing/ci-cd-and-automation/SKILL.md on GitHub (opens in a new tab) -
claude-automation-recommender
Plan, implement, or review claude automation recommender work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests claude automation recommender work.
marketing/claude-automation-recommender/SKILL.md on GitHub (opens in a new tab) -
claude-md-improver
Plan, implement, or review claude.md improver work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests claude.md improver work.
marketing/claude-md-improver/SKILL.md on GitHub (opens in a new tab) -
close-management
Create or review close management deliverables with traceable assumptions, decision criteria, ownership, and risk controls. Use when the user asks for close management planning or analysis.
marketing/close-management/SKILL.md on GitHub (opens in a new tab) -
code-documenter
Plan, implement, or review code documenter work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests code documenter work.
marketing/code-documenter/SKILL.md on GitHub (opens in a new tab) -
comparison-article-writer
Create or review comparison article writer deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for comparison article writer work.
marketing/comparison-article-writer/SKILL.md on GitHub (opens in a new tab) -
competitor-content-intelligence
Analyze competitor content coverage and uncover differentiated content opportunities using web search, page extraction, and DataForSEO content analysis. Use when asked for competitor content research, editorial gap analysis, content brief inputs, or topic whitespace.
marketing/competitor-content-intelligence/SKILL.md on GitHub (opens in a new tab) -
copy-editing
Create or review copy editing deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for copy editing work.
marketing/copy-editing/SKILL.md on GitHub (opens in a new tab) -
cowork-plugin-customizer
Plan, implement, or review cowork plugin customizer work in an existing codebase with compatibility, security, and verification controls. Use when the user explicitly requests cowork plugin customizer work.
marketing/cowork-plugin-customizer/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.