MCP Playbooks

Playbooks are markdown skills plus a mapped workflow (or local content path). Prefer run_playbook(skillId) over loading the markdown and inventing steps. Marketing use-cases: SEO agent, ship gate, security audit, marketing agent.

Payload first: pass workspace files / HTML / text. Ask for a live URL only when the user explicitly wants link analysis, or the matched job cannot run without a fetch (PageSpeed, TLS, mixed content, live headers).

Agent contract

plan_task → solve_task | run_playbook → verify_task

High-value playbooks

Skill id	Goal phrases	Workflow / mode
`ship-gate`	ship gate, go live check	`ship-gate-job` (live URL)
`pr-code-gate`	ship this PR, before merge, my code	`secrets-hygiene-job` (files/text; no fetch)
`pr-preview-gate`	preview gate, PR deploy check	`ship-gate-job`
`fix-verify-ship-gate`	verify ship gate after fix	`ship-gate-job` + `verify_task`
`fix-verify-security-headers`	verify headers after fix	`security-headers-job` + `verify_task`
`fix-verify-web-security-audit`	verify full security after fix	`full-security-audit` + `verify_task`
`fix-verify-social-preview`	verify OG after fix	`social-preview-audit-job` + `verify_task`
`fix-verify-core-web-vitals`	verify LCP/CLS after fix	`core-web-vitals-job` + `verify_task`
`fix-verify-seo-audit`	verify seo after fix	`full-seo-audit` + `verify_task`
`fix-verify-email-auth`	verify SPF/DKIM after fix	`email-auth-security-job` + `verify_task`
`frontend-supply-chain`	SRI, mixed content, CORS	`frontend-supply-chain-job`
`fix-verify-frontend-supply-chain`	verify supply chain after fix	`frontend-supply-chain-job` + `verify_task`
`auth-token-hygiene`	decode jwt, token hygiene	`auth-token-hygiene-job`
`dev-json-pipeline`	json validate format zod typescript	`dev-json-pipeline-job`
`dev-auth-debug`	jwt headers curl request builder	`dev-auth-debug-job`
`dev-format-transform`	format minify cron color	`dev-format-transform-job`
`developer-ship-checklist`	before deploy, prod readiness	`developer-ship-checklist-job`
`seo-site-audit`	full seo audit	`full-seo-audit`
`technical-seo-audit`	technical seo, mid-sprint seo	`technical-seo-audit-job`
`full-seo-optimization`	full seo optimization	`full-seo-optimization-job`
`keyword-opportunity-review`	keyword opportunity, keyword review	`keyword-opportunity-review-job`
`seo-staging-diff`	staging vs production seo	`seo-deploy-regression-diff-job`
`seo-deploy-regression`	post-deploy bulk seo	`seo-deploy-regression-job`
`crawl-readiness`	robots sitemap redirects launch	`crawl-readiness-job`
`structured-data-audit`	schema meta social tags	`structured-data-audit-job`
`ai-overview-readiness`	AI Overview / GEO readiness	`ai-overview-readiness-job`
`site-icons-audit`	favicon apple-touch icons	`site-icons-audit-job`
`campaign-tracking-setup`	utm ads macros tracking	`campaign-tracking-setup-job`
`paid-ads-copy-gate`	ads copy rsa limits	`paid-ads-copy-gate-job`
`growth-unit-economics`	roas cpc ctr cpa cac	`growth-unit-economics-job`
`email-campaign-qa`	email subject spam words	`email-campaign-qa-job`
`landing-conversion-check`	landing cta forms tags	`landing-conversion-check-job`
`fix-verify-crawl-readiness`	verify crawl after fix	`crawl-readiness-job` + `verify_task`
`fix-verify-structured-data`	verify schema/meta after fix	`structured-data-audit-job` + `verify_task`
`fix-verify-ai-overview-readiness`	verify AIO after fix	`ai-overview-readiness-job` + `verify_task`
`fix-verify-site-icons`	verify icons after fix	`site-icons-audit-job` + `verify_task`
`fix-verify-technical-seo`	verify technical SEO after fix	`technical-seo-audit-job` + `verify_task`
`fix-verify-seo-deploy-regression`	verify bulk SEO after fix	`seo-deploy-regression-job` + `verify_task`
`page-performance`	core web vitals, LCP/CLS	`core-web-vitals-job`
`social-preview`	open graph, twitter card	`social-preview-audit-job`
`web-security-audit`	security audit URL	`full-security-audit`
`content-ship`	ship this html, local content	local HTML (free unless `enhance:true`)
`dns-email-security`	SPF DKIM DMARC	`email-auth-security-job`
`secrets-and-auth-hygiene`	secret leak scan	`secrets-hygiene-job`

Marketing playbook inputs

Pass fields on run_playbook(skillId, input) (same keys agents use for the underlying tools):

Skill	Minimum input
`campaign-tracking-setup`	`baseUrl`/`url`, `utm_source`, `utm_medium`, `utm_campaign` (+ optional `platform`)
`paid-ads-copy-gate`	`platform` + copy fields and/or `headlines[]` + `descriptions[]`
`growth-unit-economics`	numeric `revenue`/`spend`/`clicks`/`impressions`/`conversions`/`customers` as needed
`email-campaign-qa`	`subject` (+ optional `preheader` / `text`)
`landing-conversion-check`	`url`

Browser hub: Marketing tools. Agent use-case: Marketing agent. Headline/subject “AI” slugs are template variants only (not LLM).

Fix → verify loop

After applying fixes in the harness:

verify_task(goal, { url }, baselinePreviousReport)
# or async
verify_task(goal, input, baseline, async: true) → get_run(runId) → read resultStatus
# or
run_playbook("fix-verify-ship-gate", { url })

Baseline can be a prior solve_task result, verify_task.after, a get_run payload, or a raw jobReport. Prefer verify_task when you still have that baseline — responses are deltas only. Score direction uses metric status (good / needs_improvement / poor), not raw “higher number wins.”

Credits

plan_task estimates credits (heuristic: ~2–3 per tool step). Exact billing matches REST tool costs (1–10 credits).