Agent Skill
Programmatic SEO Playbook skill
programmatic-seo-playbookirinabuht12-oss/marketing-skillsskills/programmatic-seo-playbook/SKILL.md
Replicate the 7 programmatic SEO plays that took Zapier, Clay, Composio, Gamma, Mintlify, HeyGen and HubSpot to
always on
38 tokname + description
once used
2,289 tokSKILL.md body
bundled files
0
repo stars
5.2kGitHub
Install the Programmatic SEO Playbook skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/irinabuht12-oss/marketing-skills --skill programmatic-seo-playbook
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/irinabuht12-oss/marketing-skills.git /tmp/marketing-skills mkdir -p ~/.claude/skills cp -R /tmp/marketing-skills/skills/programmatic-seo-playbook ~/.claude/skills/programmatic-seo-playbook
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 38 tok |
| When the agent uses it | The SKILL.md instructions | 2,289 tok |
| Only if opened | No bundled files | — |
Until it is used, programmatic-seo-playbook costs about 36× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 49 skills from irinabuht12-oss/marketing-skills would load 361 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Programmatic SEO Playbook
- Process
- The 7 plays
- Scoring table
- Play design cards
- Play notes
- Rollout plan
- AI-citation checks
- Output format
- Data access (Ryze MCP)