ConquistadorRequest access

Private alpha · 0.0.14

Give your coding agent the growth work.

Conquistador helps your coding agent do growth, marketing, sales, product and knowledge work. Give it an outcome and the facts. It picks from 38 methods, names the specialists it uses, and returns one reviewed draft with its review findings.

Request private-alpha accessSee how it works
Methods
38
Coding agents
6
Setup command
1
Deps added
0
Conquistador, a round forest-green companion with leaf ears, holds a folded map and points ahead.

Live demo

One request in. One reviewed draft out.

You ask for the outcome in your own coding agent. Conquistador shows the plan, names the specialists, writes the draft, reviews it, and marks every fact it could not find.

Coding agent · ~/ledgerline

Finished

You

Use Conquistador to draft a launch plan from the product facts in this project. Mark missing facts. Keep it as a draft.

Conquistador

Engagement brief

Outcome
Launch plan for Ledgerline. Draft only.
Methods
research-positioning · plan-campaign · write-copy · write-social
Specialists
Copy · SaaS landing · Creative assets
Review
fresh-eyes-review in a separate context
Needs you
Publishing, spend and sends

Launch plan · Ledgerline Draft

  1. Launch bet. Freelancers who chase late invoices. One promise: get paid without the follow-up emails.
  2. Channels. Product Hunt listing and maker comment, one X thread, one waitlist email. Reply bank for each.
  3. Sequence. T−7 prepare assets and hunters. Launch day at [missing: launch date]. T+7 readout.
  4. Offer. Free trial, then [missing: price]per month.
  5. Decision signal. Qualified trials in week one against [missing: baseline].

Review findings

  • Revise“2× faster invoicing” has no source in the project facts. Removed.
  • GapLaunch date is not in the facts. Marked.
  • GapPrice is not in the facts. Marked.
  • PassEvery channel asset keeps one promise and one call to action.

Missing facts marked: 3. One correction applied. Re-review passed. Nothing was posted or sent.

Example session with a fictional product. Output shortened. Your coding agent's interface will look different.

How it works

Install once. Ask in any project.

One guided command sets up a project. You confirm once. After that you talk to your coding agent the way you already do.

  1. Step 01

    Install the CLI once

    Private alpha: access by invitation. Invited accounts install a pinned private release with Node 24 and npm. There is no public registry package yet.

    Invitation only

  2. Step 02

    Run conquistador in the project

    It picks the project, detects your coding agent, shows the plan and asks once. No dependency or lockfile is added. No daemon, watcher or schedule starts.

    .conquistador/
    SKILL.md
    Start here
    README.md
    Usage and lifecycle
    library/
    All 38 methods and their resources
    agent/agent.json
    Portable operator contract
    hosts/
    BB specialist adapter

  3. Step 03

    Ask for an outcome

    Open a fresh session in that project, select Conquistador, and say what you need.

    YouUse Conquistador to draft a launch plan from the product facts in this project. Mark missing facts. Keep it as a draft.

Commands you will use

  • conquistadorGuided setup for this project
  • conquistador startShow the skill location and first task again
  • conquistador skillsBrowse the available capabilities
  • conquistador doctorCheck local files, routing and hook registration
  • conquistador route --prompt '…'Preview a route before you run it
  • conquistador uninstallRemove the unchanged owned copies
Conquistador stands on a green highland ridge with an open map, looking over coffee hills toward a low sun.
FORSVN studio · Buon Ma Thuot · 47

What it does

38 methods. One entry in your agent.

Your agent sees one Conquistador skill. The full library loads only after routing, so the methods do not crowd its context. As work runs, it shows the methods and specialists it uses.

Growth and launch

13

Decide what to do next, then plan it.

  • Shape an ambiguous initiativeshape-initiative
  • Research market and positioningresearch-positioning
  • Research content ideasresearch-content-ideas
  • Diagnose a growth problemdiagnose-growth
  • Prioritize opportunitiesprioritize-opportunities
  • Model a growth or revenue targetmodel-growth-funnel
  • Allocate a marketing budgetallocate-marketing-budget
  • Design pricing and packagingdesign-pricing-and-packaging
  • Research or choose a channelresearch-channel
  • Plan a campaign or launchplan-campaign
  • Create paid mediacreate-paid-campaign
  • Create a run of showcreate-run-of-show
  • Improve search and answer visibilityoptimize-search

Marketing and sales

10

Finished work in the native form of each channel.

  • Establish a brand foundationcreate-brand
  • Write a production briefbrief-creative
  • Write product and campaign copywrite-copy
  • Write social and community postswrite-social
  • Write direct outreachwrite-outreach
  • Write long-form workwrite-longform
  • Inspect a supplied videoanalyze-video
  • Create short-form videocreate-shortform
  • Improve a conversion surfaceimprove-conversion
  • Create or revise Vietnamesepolish-vietnamese

Product and engineering

06

When you ask for product work, not by accident.

  • Map a product journeymap-user-flow
  • Specify an interfacebrief-product-ui
  • Architect a systemarchitect-software-system
  • Build an iOS experiencebuild-ios-app
  • Build a web experiencebuild-web-app
  • Write technical documentationwrite-technical-docs

Knowledge and review

08

Learn from real results. Check the claims.

  • Learn from growth resultsmeasure-growth
  • Evaluate paid resultsevaluate-paid-campaign
  • Evaluate a sent outreach cycleevaluate-outreach
  • Evaluate published short-formevaluate-shortform
  • Audit a marketing packageaudit-marketing
  • Review a finished artifactfresh-eyes-review
  • Audit the facts behind a claimknowledge-review
  • Resolve a consequential decisiondecision-panel

+01Share product feedback, opt-in: submit-feedback drafts a redacted issue and sends nothing until you approve the exact text.

SpecialistsAds · Copy · Direct-response landing · SaaS landing · Data diagnosis · Campaign data · Creative assets

Works where you build

Your coding agent stays in charge.

Setup writes one project skill for the agent you use. It does not replace your agent, your model or your tools.

  • Codex

    .agents/skills/conquistador

    Native project skill

  • Claude Code

    .claude/skills/conquistador

    Native project skill

  • Cursor

    .cursor/skills/conquistador

    Native project skill

  • GitHub Copilot

    .github/skills/conquistador

    Native project skill

  • BB

    .conquistador/

    Complete operator and specialist adapter

  • Hermes Agent

    .hermes/skills/conquistador

    Via conquistador --bot hermes, then a separate trust step

Another agent? Ask it to read .conquistador/SKILL.md. Open a fresh session after setup and check that your agent lists the skill. Product names belong to their owners.

Principles

You steer every output.

Conquistador prepares the work. You decide what ships, what gets spent and what gets sent.

Conquistador sits at a small desk and marks a sheet of paper with check marks.

  • 01

    Drafts, not auto-posts

    Publication, spend, sends, external writes and saved memory keep their human decision. Accepting a draft does not authorize saved memory or feedback disclosure.

  • 02

    Your model, your tools, your permissions

    Your coding agent supplies the model, context, tools and permissions. Credentials stay with the host or its connection manager.

  • 03

    Nothing runs in the background

    Installation starts no daemon, watcher, hook or schedule. Activation defaults to manual: it works when you ask.

  • 04

    Evidence kept separate

    A passing local check does not prove a good result. Conquistador reports install checks, observed behavior and your acceptance as separate things.

FAQ

Plain answers.

Conquistador sits calmly and holds a small cup.

What is Conquistador?

Conquistador helps your coding agent do growth, marketing, sales, product and knowledge work. You give it an outcome and the relevant facts. It selects from 38 methods, names the specialists it uses, and returns one reviewed draft with review findings.

Which coding agents does it work with?

Codex, Claude Code, Cursor and GitHub Copilot get a native project skill. BB uses the complete operator with its specialist adapter. Hermes Agent uses conquistador --bot hermes and a separate trust step. Any other agent can read .conquistador/SKILL.md directly. Open a fresh session after setup to confirm your host discovers it.

What does it cost, and what is the license?

The source carries the MIT License; during the private alpha, source access is by invitation. Conquistador does not include a model: your coding agent supplies the model and tools, so model usage stays on the plan you already have with your host.

What does “private alpha” mean?

Version 0.0.14 is a private 0.0.x release. The repository is private and access is by invitation. Invited accounts install a pinned, checksum-verifiable release from the private Git repository. No package is published to the npm registry.

When is the public alpha?

The public alpha starts at version 0.1.0. There is no date yet. Its registry install command stays unannounced until the exact public package and a clean install lifecycle are verified.

What does setup change in my project?

Guided setup writes a .conquistador folder and, for your host, one project skill folder. It adds no package manifest, dependency or lockfile to your project. conquistador uninstall removes the unchanged owned copies.

Where do my data and credentials go?

They stay with your host. Work from supplied facts needs no connected account. When a task needs live access, Conquistador helps you connect only that service, and the credential stays with the host or connection manager. There is no automatic transcript collection or background feedback upload.

Private alpha · 0.0.14

Bring one real task.

Access is by invitation. Tell us what you build, which coding agent you use, and one outcome you want drafted.

Request private-alpha accesshi@hungv47.com
Conquistador waves hello.