integrations
Skill1 starsChanged 6 months agoApache-2.0View on GitHub
Generate an integration page documenting how the site's product/service connects to a named third-party tool ("[Site] + [Tool]" or "[Site] [Tool] integration"). Captures decision-stage searchers verifying compatibility before purchase ("does [site] work with [tool]?"). Pulls real integration details from `site-info.md` or supplied integration dossier — refuses to invent integration capabilities. Satisfies Tier 1 on-page SEO, validates schema, and ships per the site's publishing method. Use when the user types `/integrations` or asks for an integration page.
16 other projects use a version of this.
Adopted by
Most recently taken up by
- nomorehappypath/nomorehappypaththeir own version, first seen Nov 15, 2026
- Dev-KAIDO/agent-skillstheir own version, first seen Nov 1, 2026
- ankul5/internship-hunt-skilltheir own version, first seen Nov 1, 2026
- MartinOlivero/saas-buildertheir own version, first seen Oct 13, 2026
- psubramanian/Claude-Skillstheir own version, first seen Oct 13, 2026
- rohinipachanta/claude-code-quickstarttheir own version, first seen Oct 13, 2026
Used with
Projects with it also use payments and learn.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillpayments
Stripe payments integration guidance — native Vercel Marketplace setup, checkout sessions, webhook handling, subscription billing, and the Stripe SDK. Use when implementing payments, subscriptions, or processing transactions.
Also in 3 projects that use this
genomewalkerSkilllearn
Learn from web sources, generate SKILL.md, and store key patterns in soul memory. Trigger keywords: learn, skill-gen, web-learn, documentation, tutorial.
Also in 3 projects that use this
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- indranilbanerjee/digital-marketing-pro★ 934same name
- Automattic/wordpress-activitypub★ 583same name
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- buriedsignals/spotlight★ 60same name
- drafthq/draft★ 40same name
- nomorehappypath/nomorehappypath★ 22same name
- MartinOlivero/saas-builder★ 4same name
- ankul5/internship-hunt-skill★ 2same name
- Dev-KAIDO/agent-skills★ 2same name
6 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- alternativeSkill
- auditSkill
- blogSkill
- broken-backlinksSkill
- case-studySkill
- clusterSkill
- comparisonSkill
- competitor-backlinksSkill
- glossarySkill
- haroSkill
- lovable-deploySkill
- pricingSkill
- programmatic-batchSkill
- refreshSkill
- semrush-baselineSkill
- serp-featuresSkill
- serviceSkill
- triageSkill
- wireframeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Step 0 — Product-type guard: if site-info.md does not declare product_type=saas or product_type=api, the skill warns and asks for …
- Distinctive: line 46
If ANY of the 5 is missing from documented sources, refuse — integration pages that fudge details rank temporarily but get rebuked in …
- Very specific: line 67
Every claim about the integration's capabilities MUST be in site-info.md integrations registry or in supplied dossier.
- Very specific: line 68
If integration is verified-by=roadmap, the page MUST show a banner: "This integration is on our roadmap.
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/integrations — Third-party integration page generator
Integration pages capture a narrow but high-converting search behavior: prospects who already want the site's product but need to verify it plays nicely with their existing stack. These pages also stack topical authority — a SaaS with 50 integration pages outranks one with 0 even if the underlying product is identical.
This skill is most useful for SaaS, API products, and developer tools. Service businesses (consulting, catering, medical) rarely need integration pages — the skill flags this at start.
Inputs
Required (asked at start if not given):
- Site — must match a folder under
sites/[name]/. Must haveproduct_type=saasorproduct_type=apiinsite-info.md. - Integration target — the named tool (Salesforce, HubSpot, Zapier, Slack, Notion, etc.).
Optional (per-run overrides):
- Integration type —
native(built-in feature) |via-zapier(no-code middleware) |via-api(custom API connection) |via-webhook(event-driven). Defaults to reading from site's integrations registry insite-info.md. - Verified by —
engineering(defaults — implies actual integration code exists) |roadmap(planned but not shipped — flagged on page). Skill refuses if undeclared.
Workflow
This skill follows /service's workflow (Steps 0–11) with the page-type-specific differences listed below. Read .claude/skills/service/SKILL.md end-to-end before running.
What's unique to /integrations
Step 0 — Product-type guard: if site-info.md does not declare product_type=saas or product_type=api, the skill warns and asks for confirmation. Service-business sites rarely benefit from integration pages.
Step 2 — Keyword selection:
- Common forms:
[Site] [Tool] integration,[Site] + [Tool],does [Site] work with [Tool]?,connect [Site] to [Tool]. - Pick from
service-keywords.csvrows with intent=integration. If none exist, add one before proceeding.
Step 4 — SERP analysis (integration-specific):
- Top 3 results — these are often the target tool's own integration directory (Zapier's Salesforce page, HubSpot's marketplace). Hard to beat for the exact query. Aim to rank for the long-tail variant ("does [Site] sync [field] to [Tool]?") rather than the head term.
- Extract: do the top results show real screenshots? Real config steps? Real field-mapping tables? Most do — match or exceed.
Step 5 — Integration data gathering:
- Required from engineering (or
site-info.mdintegrations registry):- What data flows (fields, frequency, direction — one-way vs two-way sync)
- Configuration steps (numbered, from zero to working)
- Authentication method (OAuth, API key, webhook URL)
- Known limitations (rate limits, unsupported fields, edge cases)
- Pricing implications (does this integration cost extra? require a higher plan?)
If ANY of the 5 is missing from documented sources, refuse — integration pages that fudge details rank temporarily but get rebuked in reviews and damage trust.
Step 6 — Wireframe (integration-specific):
- Hero: "Connect [Site] to [Tool] in [time-estimate] minutes" or "[Site] + [Tool]: the [primary-use-case] integration"
- Quick answer (above fold): 2-sentence summary — "What syncs: [primary-fields]. How: [native | Zapier | API]. Time to set up: [minutes]."
- Use cases section (3–5 named scenarios): each 80–150 words. "If you're a [role] in [team-type], here's what this unlocks for [workflow]."
- Data flow diagram or table (required): which fields move in which direction, at what frequency, under what trigger. Visual or table — pick based on complexity.
- Configuration steps (numbered, screenshots): the actual zero-to-working setup. This is the section that wins the SERP — most integration pages skip the real steps.
- Limitations section (required, not optional): rate limits, unsupported fields, gotchas. Trust signal.
- Pricing note (if applicable): "This integration is included in [plan]" or "Requires [plan] starting at $X."
- FAQ: 5–8 Qs — "Is this real-time or batch?", "Does it support [edge-case-field]?", "Can I customize the mapping?", "What if my [Tool] account uses [variant]?"
- CTA: "Start a free trial" (for SaaS) or "Try the integration" (API products).
Step 7 — Schema (integration-specific):
ServicewithserviceType: "Software integration"andprovider: [our org]mentionsfor the integrated tool's organization (e.g.,{@type: SoftwareApplication, name: "Salesforce"})HowToschema for the configuration steps (each step as aHowToStep)FAQPageBreadcrumbList
Step 8 — Voice (integration-specific extras):
- Every claim about the integration's capabilities MUST be in
site-info.mdintegrations registry or in supplied dossier. No "we plan to" implied as "we have." - If integration is
verified-by=roadmap, the page MUST show a banner: "This integration is on our roadmap. Estimated availability: [date]." Page can still exist for SEO capture, but the banner is non-removable. - One opinion max — usually "[Use case] is where this integration matters most" backed by usage data from stats.md.
- AI-search rules: Q+A density critical — integration questions are heavily LLM-cited ("does Acme work with Salesforce?" is a common LLM-mediated query).
Refusal conditions
This skill refuses to ship if:
- Site is not
product_type=saasorproduct_type=api. - Any of the 5 required integration data points is undocumented.
- Integration is
verified-by=roadmapbut the date estimate is missing. - An integration page for this tool already exists in
used-keywords.md(refresh via/refresh).
Output
Standard _drafts/[slug]/ layout. Slug pattern: integrations/{tool-slug} (path-based to support the multi-page integration directory pattern).
Length target: 800–1,800 words. Integration pages skew shorter than blog posts — readers want config and limitations, not narrative.
Routine versioning + idempotency contract
Same as /service. Idempotency key: (site, tool-slug, language). Integration pages auto-decay — refresh quarterly when the integration registry version-bumps.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

