Skip to main content

The toolkit, free by request

117 skills for AI growth work.

We built Conversion Skills as the library our Marketing and Operations builds run on.

We will send the quickstart, command map, and repo reading path. You can unsubscribe anytime.

Conversion Skills workspace showing plugin install, command families, vault files, ledger, examples, and repo gates
117
Claude skills
8
modules
110
workflow skills
3
profiles
23
template files
6
repo gates

Install

Use it as a plugin, or start with a folder

It gives Claude a governed business vault, durable memory, a daily run, 117 skills, and guardrails for owners, teams, and agencies. The repo is designed for people who want useful AI without buying another platform. The AI is the runtime, markdown files are the database, and git is the journal. It needs Claude Code (terminal, desktop app, or IDE), not the Claude Desktop chat app. Setup was timed once, on 2026-09-01: 1m39s of machine work producing 35 files, our own run on our own repo, not a client result.

  • Zero-infra setup

    Create an empty folder, open Claude in that folder, and run setup. It builds the vault, asks for the business basics, seeds the first files, and gives the AI a place to remember the work.

    • Empty folder
    • Run /setup
    • Plain markdown

  • Claude Code plugin

    Once access is granted, install the plugin when you want the command library available inside Claude Code. The repo includes plugin metadata, marketplace copy, commands, and docs.

    • /plugin marketplace add ConversionSystem/conversion-skills
    • /plugin install conversion-skills@conversion-skills
    • Run /setup

  • No lock-in

    The vault stays in your folder. You can read it, edit it, commit it, move it, or delete it. No proprietary database is required for the basic operating model.

    • Files you own
    • Git history
    • Readable rules

Vault

It gives Claude a memory system

Conversion Skills is not just a pile of prompts. Setup creates a governed business folder with places for company context, memory, pipeline, projects, daily work, content, operations, library files, and inbox material.

  • Business vault

    The vault includes CLAUDE.md, system rules, company files, memory, pipeline, projects, content, operations, daily notes, library material, and an inbox for new context.

    • Company
    • Memory
    • Pipeline

  • KPI ledger

    The append-only ledger captures date, metric, baseline, current value, target, source, confidence, and notes. Reviews can look back at what changed instead of guessing from memory.

    • Baseline
    • Current
    • Confidence

  • Templates

    The repo ships template files for AI agent briefs, automation briefs, brand voice, clients, competitors, daily notes, decisions, ICPs, invoices, meetings, offers, proposals, SOPs, tasks, and workflows.

    • Briefs
    • Reviews
    • Workflows

Setup output

The first run writes the operating folders

Setup does not pretend the AI already knows the business. It creates the places where company context, work history, files, and decisions can live before any agent starts making drafts.

  • Root router and system rules

    Setup writes the root CLAUDE.md and _system folder so Claude knows where facts belong, how to handle budgets, and what needs human review.

    • CLAUDE.md
    • _system/
    • Router rules

  • Company, memory, and pipeline

    The vault creates homes for company truth, durable memory, prospects, deals, projects, and the KPI ledger so repeat work has context to read from.

    • Company/
    • Memory/
    • Pipeline/

  • Daily, content, operations, and inbox

    The operating folders capture daily notes, content drafts, SOPs, workflow files, library references, and loose context that still needs to be routed.

    • Daily/
    • Content/
    • Inbox/

Modules

Eight modules run the operating loop

Seven modules are one skill each: setup, memory, the daily run, the optimizer, Team OS, Client OS, and the connector layer. The eighth, the workflow library, is the other 110 skills. Buyers and teams can see where the value comes from before they ask us to build around their business. The workflow library sits beside them with the delivery skills.

  • Setup, memory, operator

    Setup creates the vault. Memory keeps durable business facts. The Operator module runs the daily rhythm, routes facts, drafts work, and flags decisions for a human.

    • /setup
    • /memory
    • /operator

  • Optimizer, team, client

    Optimizer audits and proposes fixes. Team OS adds roles and shared knowledge. Client OS gives agencies firewalled client folders so one client task does not read another client folder.

    • /optimizer
    • /team
    • /client

  • Connectors and workflows

    The connector layer records optional tool access, budgets, scopes, and audit logs. The workflow library covers growth, content, sales, creative, design, build, and reporting work.

    • /connect
    • Audit logs
    • Workflow library

Templates

The repo includes 23 reusable starting files

Templates keep the system from asking a blank-page AI to invent structure every time. They give common business artifacts a predictable shape.

  • Agent and automation briefs

    AI agent briefs and automation briefs define the job, inputs, outputs, approvals, and constraints before a workflow becomes a build task.

    • ai-agent-brief.md
    • automation-brief.md
    • workflow-file.md

  • Operating documents

    Daily notes, weekly reviews, monthly reviews, decision logs, meeting summaries, SOPs, task briefs, and project briefs give the operator a consistent work trail.

    • daily-note.md
    • weekly-review.md
    • sop.md

  • Go-to-market context

    Brand voice, ICP, offer, client profile, competitor, proposal, invoice, and KPI ledger templates keep sales and marketing work tied to real business context.

    • brand-voice.md
    • icp.md
    • offer.md

Skill families

The 117 skills are grouped by real work

The page should make the repo easier to understand than a raw file tree. These are the command families buyers can map to the work they already repeat.

  • Core and daily

    Run the operating rhythm: setup, memory, daily briefs, meeting capture, pipeline updates, project updates, weekly reviews, business reviews, SOPs, and dashboards.

    • /setup
    • /daily
    • /weekly-review

  • SEO, GEO, and content

    Audit and improve search work with SEO audits, schema, programmatic pages, comparisons, GEO optimization, content plans, technical SEO, sitemaps, image SEO, and publishing skills.

    • /seo-audit
    • /geo-optimize
    • /blog-post

  • Paid ads and campaigns

    Plan, audit, budget, and draft paid media across Google, Meta, LinkedIn, TikTok, Microsoft, YouTube, creative, competitors, and landing page work.

    • /ads-audit
    • /ads-google
    • /ads-creative

  • Sales and pipeline

    Research, qualify, enrich, mine CRM context, review pipeline, inspect win-loss patterns, draft LinkedIn outreach, analyze reps, and prepare free-audit style discovery.

    • /lead-research
    • /crm-mining
    • /pipeline-review

  • Creative and media

    Turn ideas into useful assets with YouTube ideation, briefs, outlines, scripting, packaging, title generation, thumbnails, infographics, visuals, video, GIFs, and transcription.

    • /youtube-scripting
    • /generate-visual
    • /audio-transcriber

  • Build and utilities

    Shape the systems around the work with MCP builder, agent builder, deep research, fact checking, humanizer, file organizer, n8n planning, course creator, and launch kits.

    • /mcp-builder
    • /agent-builder
    • /n8n

Orchestration

Some skills fan out, then judge the work

The repo documents an orchestration pattern for bigger audits. The main skill gathers the facts, specialist agents inspect their slice, and a judge cuts weak or uncited findings before the draft reaches a human.

  • Gather once, fan out

    Orchestrating skills collect the raw signals into the project folder first. Specialists then read only the slice they are assigned.

    • Site audit
    • SEO audit
    • Ads audit

  • Merge and judge

    The main skill assembles the scorecard. The judge agent tries to refute each finding, and thin or uncited claims get removed.

    • Main skill merges
    • Judge reviews
    • Citations required

  • Draft-only by design

    The skills diagnose, draft, and recommend. A human applies changes, sends messages, publishes content, deletes files, or changes permissions. The same toolkit runs our Marketing and Operations builds.

    • No surprise sends
    • No live publishing
    • Human approval
    Open

Agent examples

See what AI can run

The agent pages translate public skill patterns into buyer-friendly workflows: what each agent reads, prepares, writes, and leaves for human review.

  • Sales Agent

    Lead research, qualification, enrichment, pipeline review, draft follow-up, and sales analysis.

    • Research
    • Qualify
    • Review
    Open

  • Marketing Agent

    Content plans, SEO work, landing pages, ads, newsletters, social posts, and draft publishing packages.

    • Plan
    • Draft
    • Improve
    Open

  • Client Agent

    Meeting capture, onboarding, delivery updates, health checks, proof requests, and case-study drafts.

    • Capture
    • Update
    • Protect
    Open

  • Report Agent

    KPI memory, weekly reviews, business reviews, dashboards, pipeline reads, and claim checks.

    • Measure
    • Review
    • Verify
    Open

  • Operations Agent

    The Client Agent and the Report Agent as one agent: updates, recaps, health checks, and the weekly brief, all checked by a person.

    • Client work
    • Weekly brief
    • Human gate
    Open

Trust model

Connectors and actions stay controlled

The repo is careful about tool access. It can run without connectors. When connectors are added, each one gets purpose, scope, rate limits, secrets handling, and audit logging.

  • Optional connectors

    Possible connectors include meetings, chat, email, calendar, CRM, analytics, WordPress, image data, and ad data. The default setup still works from pasted context, exports, and files.

    • No connector required
    • Scoped reads
    • Audit log

  • Human approval

    The skills can draft emails, posts, reports, pages, automations, and plans. A human still approves sending, publishing, deleting, pricing changes, permission changes, and client contact.

    • Draft first
    • Approval gate
    • No surprise sends

  • Secrets stay out

    Credentials do not live in the vault. Connector docs reference the secret manager name, and scripts scan for keys before the repo or a client workspace gets sloppy.

    • Secret manager
    • Scan scripts
    • Readable audit

Profiles

Solo, Team, and Agency have different guardrails

The same library can serve one owner, a team, or an agency. The difference is how much permissioning, collaboration, and client separation the folder needs.

  • Solo

    For one owner who wants Claude to remember the business, keep a pipeline, capture calls, draft follow-up, and keep the week pointed at the right work.

    • Pipeline
    • Daily notes
    • Projects

  • Team

    For teams that need shared company knowledge, people profiles, who can see which clients, permissions, access notes, and a clearer audit trail around what the AI touched.

    • Roles
    • Permissions
    • Team context

  • Agency

    For agencies that need firewalled client workspaces. Each client gets its own folder, one client is active at a time, and scripts check that client context does not leak across accounts.

    • Client vaults
    • Firewall
    • Portfolio view

Repo gates

The repo has checks, not just claims

This matters for trust. Conversion Skills is inspectable once you have access: docs, scripts, examples, six gates on every push, and a judged eval scorecard that records the failures as well as the passes.

  • Six quality gates

    Every push runs checks for clean-room language, instruction budgets, secrets, client firewall leaks, brand rules, and section structure, plus a check that each skill only promises outputs its own process writes.

    • Clean room
    • Budgets
    • Firewall

  • Seeded examples

    Solo, Team, and Agency examples show the vault structure in practice, including system rules, permissions, memory, daily notes, company files, and KPI ledger examples.

    • Solo vault
    • Team vault
    • Agency vault

  • Nine scripts

    Repo scripts check brand, budgets, client firewall boundaries, clean-room language, secrets, sections, skill sync, command docs, and the full verify run.

    • check-firewall.sh
    • scan-secrets.sh
    • verify.sh

Buyer questions

Plain answers about Conversion Skills

Use this section when you need the short version before reading the repo. The detailed sections above show the actual folders, skill families, templates, gates, and agent patterns.

  • What is Conversion Skills?

    We built Conversion Skills as the library our builds run on: 117 Claude skills that give Claude a governed business vault, durable memory, a daily run, audits, and a firewalled client workspace. It is free, by request, and our Marketing and Operations builds run on it.

  • What can Conversion Skills help a team run?

    It can help structure sales research, marketing drafts, client workspaces, meeting capture, weekly reviews, KPI memory, reports, SEO work, ad planning, content production, creative briefs, and agent or automation briefs.

  • Does Conversion Skills replace a custom AI system?

    No. Conversion Skills is the toolkit and the method. A custom AI system is still useful when the work needs live integrations, proprietary data, custom interfaces, or a workflow built around a specific team.

  • How does a team start with Conversion Skills?

    Request access (free, reader access usually lands the same day), then install the Claude Code plugin or open an empty folder in Claude Code and run setup. Setup creates the business vault, asks for company context, writes the operating folders, and gives the AI a place to read and remember work. It needs Claude Code, not the Claude Desktop chat app.

Next step

Request access

Access is free and by request. Leave your email and we send the quickstart, the command map, and the install path, and a person grants reader access to the repository, usually the same day.