Run any Skill in Manus with one click

founder-agent

Stars1

Forks0

UpdatedApril 26, 2026 at 16:51

Use when the user wants to build a reusable creative-ops system for a product or company — brand system, voice guide, audience map, brief library, prompt library. Triggers when the user says "build a brand system", "set up creative ops", "founder agent", "/founder-agent", or describes a launch/positioning/brand-foundation task. Invokes the AgentSuite Founder agent via MCP.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

scottconverse

scottconverse/AgentSuite

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Market Research Analysts and Marketing SpecialistsBusiness and Financial Operations Occupations·SOC 13-1161

File Explorer

2 files

SKILL.md

readonly

name	founder-agent
description	Use when the user wants to build a reusable creative-ops system for a product or company — brand system, voice guide, audience map, brief library, prompt library. Triggers when the user says "build a brand system", "set up creative ops", "founder agent", "/founder-agent", or describes a launch/positioning/brand-foundation task. Invokes the AgentSuite Founder agent via MCP.

Founder Agent (AgentSuite)

This skill invokes the Founder agent from the AgentSuite MCP server. It produces 26 reusable creative-ops artifacts in 30-90 seconds and pauses for human approval before promoting them to long-lived storage.

When to use

User wants any of:

Brand system / brand book
Voice and tone guide
Audience map / persona doc
Positioning document
Reusable creative brief library
Prompt library for marketing assets
Any "I keep restating context every time I write copy" problem

When NOT to use

One-off content (a single landing page, single email) — overkill
Technical product spec — that's the Product agent (v0.3+)
Competitive intel / vendor analysis — that's the CIO agent (v0.7+)

Steps

Confirm AgentSuite MCP is configured. Call agentsuite_list_agents first. If it returns {"enabled": ["founder"]}, proceed. If the call fails, tell the user to add the AgentSuite MCP entry to their .mcp.json (paste the snippet from ~/.claude/skills/founder-agent/mcp-snippet.json).
Gather inputs from the user. Ask:
- Business goal (one sentence)
- Slug for _kernel/ promotion (lowercase, hyphenated)
- Path to inputs directory (optional — directory of READMEs, voice samples, screenshots)
Invoke founder_run. Pass the gathered fields plus agent_name="founder", role_domain="creative-ops", user_request=<the user's original ask>. Wait for the JSON-RPC response (30-90 s; do not poll).
Show the user the result. Display the primary_path (always brand-system.md) and the list of open_questions. Tell them to read brand-system.md and qa_report.md.
Wait for approval signal. When the user says "approved" or "ship it", call founder_approve with the same run_id and project_slug.
Confirm promotion. Echo the promoted_paths from the ApprovalResult so the user sees what landed in _kernel/.

Cost expectation

A typical run costs $0.20 – $1.00 against Claude Sonnet or GPT-4o. Hard cap is $5.00 per run. If HardCapExceeded is raised, suggest the user reduce input size or raise AGENTSUITE_COST_CAP_USD.

Failure modes

NoProviderConfigured — tell user to set ANTHROPIC_API_KEY or OPENAI_API_KEY in their shell.
ConsistencyCheckFailed — open consistency_report.json and explain the mismatch.
extract stage produced invalid JSON — re-run, usually transient.

After approval

The Design agent (v0.2+) can read directly from _kernel/<project_slug>/. Until then, the artifacts are ready to feed into ChatGPT, Claude, Midjourney, etc., as context for any creative work.

More from this repository

same repository

cio-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete CIO artifact bundle — IT strategy, technology roadmap, vendor portfolio, digital transformation plan, IT governance framework, enterprise architecture, budget allocation model, workforce development plan, and IT risk appetite statement — for an organization. Triggers when the user says "create an IT strategy", "technology roadmap", "IT governance", "digital transformation", "CIO agent", "/cio-agent", or describes a CIO or IT leadership artifact task. Invokes the AgentSuite CIO agent via MCP.

2026-04-271

trust-risk-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete trust and risk artifact bundle — threat model, risk register, control framework, incident response plan, compliance matrix, vendor risk assessment, security policy, audit readiness report, and residual risk acceptance — for a product, service, or organization. Triggers when the user says "create a threat model", "risk assessment", "security policy", "compliance matrix", "trust risk agent", "/trust-risk-agent", or describes a trust or risk artifact task. Invokes the AgentSuite Trust/Risk agent via MCP.

2026-04-271

marketing-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete marketing specification bundle — campaign brief, target audience profile, messaging framework, content calendar, channel strategy, SEO keyword plan, competitive positioning, launch plan, and measurement framework — for a product, service, or brand initiative. Triggers when the user says "create a campaign brief", "write a messaging framework", "marketing strategy", "content calendar", "channel strategy", "marketing agent", "/marketing-agent", or describes a marketing artifact task. Invokes the AgentSuite Marketing agent via MCP.

2026-04-271

engineering-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete engineering specification bundle — architecture decision record, system design, API spec, data model, security review, deployment plan, runbook, tech-debt register, and performance requirements — for a system, service, or technical initiative. Triggers when the user says "create an ADR", "write a system design", "architecture decision record", "API spec", "engineering spec", "engineering agent", "/engineering-agent", or describes an engineering artifact task. Invokes the AgentSuite Engineering agent via MCP.

2026-04-271

product-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete product specification bundle — PRD, user story map, feature prioritization, success metrics, competitive analysis, user personas, acceptance criteria, product roadmap, and risk register — for a product, feature, or initiative. Triggers when the user says "create a PRD", "write a product spec", "product roadmap", "feature requirements", "product agent", "/product-agent", or describes a product management artifact task. Invokes the AgentSuite Product agent via MCP.

2026-04-271

design-agent

scottconverse/AgentSuite

Use when the user wants to produce a complete design specification bundle — visual direction, design brief, mood board, brand rules, image generation prompts, accessibility audit, and asset acceptance checklist — for a campaign, product, or brand. Triggers when the user says "design a campaign", "create design specs", "design agent", "/design-agent", or describes a visual direction / brand identity / asset brief task. Invokes the AgentSuite Design agent via MCP.

2026-04-271

name	founder-agent
description	Use when the user wants to build a reusable creative-ops system for a product or company — brand system, voice guide, audience map, brief library, prompt library. Triggers when the user says "build a brand system", "set up creative ops", "founder agent", "/founder-agent", or describes a launch/positioning/brand-foundation task. Invokes the AgentSuite Founder agent via MCP.

Founder Agent (AgentSuite)

When to use

User wants any of:

Brand system / brand book
Voice and tone guide
Audience map / persona doc
Positioning document
Reusable creative brief library
Prompt library for marketing assets
Any "I keep restating context every time I write copy" problem

When NOT to use

One-off content (a single landing page, single email) — overkill
Technical product spec — that's the Product agent (v0.3+)
Competitive intel / vendor analysis — that's the CIO agent (v0.7+)

Steps

Confirm AgentSuite MCP is configured. Call agentsuite_list_agents first. If it returns {"enabled": ["founder"]}, proceed. If the call fails, tell the user to add the AgentSuite MCP entry to their .mcp.json (paste the snippet from ~/.claude/skills/founder-agent/mcp-snippet.json).
Gather inputs from the user. Ask:
- Business goal (one sentence)
- Slug for _kernel/ promotion (lowercase, hyphenated)
- Path to inputs directory (optional — directory of READMEs, voice samples, screenshots)
Invoke founder_run. Pass the gathered fields plus agent_name="founder", role_domain="creative-ops", user_request=<the user's original ask>. Wait for the JSON-RPC response (30-90 s; do not poll).
Show the user the result. Display the primary_path (always brand-system.md) and the list of open_questions. Tell them to read brand-system.md and qa_report.md.
Wait for approval signal. When the user says "approved" or "ship it", call founder_approve with the same run_id and project_slug.
Confirm promotion. Echo the promoted_paths from the ApprovalResult so the user sees what landed in _kernel/.

Cost expectation

A typical run costs $0.20 – $1.00 against Claude Sonnet or GPT-4o. Hard cap is $5.00 per run. If HardCapExceeded is raised, suggest the user reduce input size or raise AGENTSUITE_COST_CAP_USD.

Failure modes

NoProviderConfigured — tell user to set ANTHROPIC_API_KEY or OPENAI_API_KEY in their shell.
ConsistencyCheckFailed — open consistency_report.json and explain the mismatch.
extract stage produced invalid JSON — re-run, usually transient.

After approval

The Design agent (v0.2+) can read directly from _kernel/<project_slug>/. Until then, the artifacts are ready to feed into ChatGPT, Claude, Midjourney, etc., as context for any creative work.