agentleFS
Miyamura80Miyamura80/MCP-Template/.agents/skills/onboarding/SKILL.md

onboarding

Skill1 starsChanged 5 months agoMITView on GitHub

Interview the user, inspect this template repo, run headless onboarding, and prune unused systems so a new project gets running quickly.

  • Reads credentials

104 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use paywalls, popups and 10 more.

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.
  • CesarjoquinSkill

    paywalls

    When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," "in-app pricing," "free users won't upgrade," "trial to paid conversion," or "how do I get users to pay." Use this for any in-product moment where you're asking users to upgrade. Distinct from public pricing pages (see cro) — this focuses on in-product upgrade moments where the user has already experienced value. For pricing decisions, see pricing.

    Also in 19 projects that use this

  • CesarjoquinSkill

    popups

    When the user wants to create or optimize popups, modals, overlays, slide-ins, or banners for conversion purposes. Also use when the user mentions "exit intent," "popup conversions," "modal optimization," "lead capture popup," "email popup," "announcement banner," "overlay," "collect emails with a popup," "exit popup," "scroll trigger," "sticky bar," or "notification bar." Use this for any overlay or interrupt-style conversion element. For forms outside of popups, see cro. For general page conversion optimization, see cro.

    Also in 18 projects that use this

  • coreyhaines31Skill

    marketing-council

    When the user wants several expert takes on a marketing decision, or asks what a famous marketer would say about it: a simulated board (Seth Godin, David Ogilvy, April Dunford, Byron Sharp, and more), each grounded in their documented frameworks, where they disagree, and a recommendation. To execute, hand off to the relevant skill.

    Also in 13 projects that use this

  • roerohanSkill

    prospecting

    When the user wants to find, qualify, and build a list of prospects to reach out to — across B2B SaaS, general B2B, or local small businesses. Also use when the user mentions "prospecting," "build a prospect list," "find prospects," "find leads," "lead gen list," "find SaaS companies that," "find B2B companies," "find local businesses," "ICP-fit accounts," "who should we go after," "outbound list," "target account list," "find clients near me," "businesses without websites," "prospect research," "qualified leads," "find my first customers," "early adopters," "design partners," "beta users," or "who has this problem." Use this for the list-building and qualification phase. For writing the outbound copy after the list is built, see cold-email. For deep competitive research on specific accounts, see competitor-profiling.

    Also in 16 projects that use this

  • roerohanSkill

    emails

    When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," "lifecycle emails," "trigger-based emails," "email funnel," "email workflow," "what emails should I send," "welcome series," or "email cadence." Use this for any multi-email automated flow. For cold outreach emails, see cold-email. For in-app onboarding, see onboarding.

    Also in 18 projects that use this

  • +7 more from Cesarjoquin

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 89 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Use this skill when the user wants to turn this template into a real project, especially when they invoke /onboarding, ask to run …

    line 8
  2. Very specific:

    Use make onboard as the source of truth.

    line 27
  3. Very specific:

    Always start with a dry run: make onboard PROFILE=<profile> DRY_RUN=1.

    line 28
  4. Distinctive:

    Only run a non-dry pass after the user confirms the resolved plan printed by the dry run.

    line 32
  5. Distinctive:

    Verify the selected shape:

    line 43
  6. Distinctive:

    Do not delete auth, DB, API, MCP, docs, payment code, example apps, the landing page, or deploy configs without explicit user confirmation.

    line 55
  7. Distinctive:

    Do not push to main, force-push, or run destructive git commands.

    line 56
  8. Distinctive:

    Treat MCP behavior as current-spec-sensitive.

    line 57
  9. Very specific:

    When editing shared skills or agents, run make sync-agent-config.

    line 58
  10. Distinctive:

    Keep Gmail/Google OAuth, the agentic-payment research docs, and the landing page framed as examples/marketing, not core template …

    line 59

“Common” is measured: kept by at least 6 in 10 of the 89 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboarding

Use this skill when the user wants to turn this template into a real project, especially when they invoke /onboarding, ask to run onboarding, or want to remove unused template systems.

init/onboard.py is the source of truth for every choice, default, and prune action. Read it before changing anything. The enums and OnboardingConfig (ServiceSurface, PaymentStack, ExampleApp, OnboardingProfile, expanded()) define what can be selected and how selections imply each other.

Workflow

  1. Inspect the repo before changing anything:
    • AGENTS.md / CLAUDE.md, pyproject.toml, Makefile, README.md
    • init/onboard.py - especially the config enums, for_profile, expanded() (dependency implications), and _pruned_path_groups (exactly which files each choice removes)
    • The surfaces themselves: service registry (services/), CLI (src/cli/), MCP server (mcp_server/, incl. apps/, enhancers/), API server (api_server/, incl. routes/, auth/, billing/), db/, docs/, and relevant tests
    • Systems make onboard does NOT manage (handle these manually - see step 7): landing-page/, render.yaml, Dockerfile
  2. Interview the user briefly. Prefer grouped multi-select questions:
    • Project shape (--profile): cli-only, local-mcp, remote-mcp, full-saas, or custom
    • Service surfaces (--surfaces): cli, mcp, http_api, mcp_apps
    • Infra: auth (--auth, WorkOS AuthKit OAuth 2.1 resource server on /mcp), database (--database), docs (--docs)
    • Payments (--payments): stripe_billing, stripe_metering, x402, mpp_stub, acp_stub, or none
    • Examples (--examples): gmail_google_oauth, agentic_payment_research_docs, or none
  3. Use make onboard as the source of truth. It maps PROFILE=, CONFIG=, and DRY_RUN=1 to flags and passes everything else through ARGS=:
    • Always start with a dry run: make onboard PROFILE=<profile> DRY_RUN=1.
    • Override individual axes via ARGS, e.g. make onboard PROFILE=remote-mcp DRY_RUN=1 ARGS="--surfaces cli,mcp,http_api --payments x402 --no-docs". Boolean axes use paired flags: --auth/--no-auth, --database/--no-database, --docs/--no-docs.
    • For a custom shape, write a YAML/JSON config and pass CONFIG=<path> (keys: profile, service_surfaces, payments, examples, auth, database, docs).
    • Bare make onboard (no headless flags) launches the interactive wizard (branding, rename, cli-name, deps, env, hooks, mcp, media, jules).
    • Only run a non-dry pass after the user confirms the resolved plan printed by the dry run.
  4. Apply dependency implications before pruning (expanded() enforces these):
    • Stripe metering implies Stripe billing.
    • Stripe billing implies HTTP API, auth, and database.
    • x402 implies HTTP API and auth.
    • Gmail/Google OAuth example implies HTTP API, MCP, MCP Apps, auth, and DB.
    • MCP Apps imply the MCP surface; auth implies database; full-saas implies docs.
  5. Let onboarding prune deterministically; do not hand-delete. A non-dry run removes files and also rewrites pyproject.toml (deps, packages, scripts, vulture, MCP Apps force-include), .importlinter, api_server/server.py route registrations, mcp_server/_tool_factory.py scope/quota guards, Makefile targets, and .env.example keys in the same pass. Pruning the API surface also drops railway.json; pruning MCP drops server.json, smithery.yaml, and the registry-publish workflow.
  6. Verify the selected shape:
    • CLI: run the CLI help and one simple command.
    • API/MCP: import the server, check /health, and confirm /mcp if kept.
    • MCP behavior: run the fast MCP E2E tier (make test); reach for make mcp_conformance only if the user kept MCP and has Node.
    • Shared changes: run focused tests first, then make ci when scope is large.
  7. Handle the systems onboarding does not touch, after confirming with the user:
    • landing-page/ is a GmailMCP-branded Astro marketing site (privacy/terms, comparison pages, WebMCP, Server Card, llms.txt). For a real project it almost always needs rebranding or removal, which make onboard will not do for you.
    • render.yaml and Dockerfile are deploy configs not wired into pruning; update or remove them to match the kept surfaces.

Guardrails

  • Do not delete auth, DB, API, MCP, docs, payment code, example apps, the landing page, or deploy configs without explicit user confirmation.
  • Do not push to main, force-push, or run destructive git commands.
  • Treat MCP behavior as current-spec-sensitive; verify current docs before designing new MCP semantics.
  • When editing shared skills or agents, run make sync-agent-config.
  • Keep Gmail/Google OAuth, the agentic-payment research docs, and the landing page framed as examples/marketing, not core template infrastructure.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.