agentleFS
jhonatan-oliveiradevjhonatan-oliveiradev/agent-skills/skills/preparing-project-launch/SKILL.md

preparing-project-launch

Skill1 starsChanged 3 months agoMITView on GitHub

Use when a finished product or open source project is ready to be presented publicly and its demo, install path, claims, access, and launch assets need an evidence-based readiness check.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check whether the public surfaces have a usable title, description, social preview, accessible media alternatives, legal/privacy links when …

    line 15
  2. Distinctive:

    Verify the fixed blockers against the same release.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Preparing a Project Launch

A launch is ready when a new visitor can understand the project, try or install it, and get help if a step fails. Inspect the deployed product or distributable, repository, documentation, and intended primary action; do not infer readiness from a passing build alone.

Workflow

  1. Identify the intended audience, launch goal, primary CTA, target channels, and exact release or commit. Distinguish a new project from a feature update. Ask for missing access only when it blocks verification.
  2. Walk the visitor path from the launch link to the first useful outcome. Verify live links, public access, installation steps, sample data, responsive presentation, and the actual download or signup action using the available environment. Record which checks cannot be performed.
  3. Inventory claims, screenshots, demo flows, prices, availability, version, platform support, and credits. Match each meaningful promise to inspectable product behavior or documented evidence. Mark unverified claims for correction; never manufacture usage numbers, testimonials, or metrics.
  4. Check whether the public surfaces have a usable title, description, social preview, accessible media alternatives, legal/privacy links when the product requires them, and a clear path to report problems. Avoid adding bureaucracy to a small open source release.
  5. Produce a launch brief: audience, one-sentence value, differentiator, primary CTA, two or three real demonstration moments, approved proof, asset inventory, unresolved blockers, and the exact links. Rank blockers by whether a visitor can complete the promised action.
  6. Verify the fixed blockers against the same release. Keep evidence tied to its date and version; avoid calling a feature stable just because its marketing materials exist.

Handoff

Pass the verified brief to brag-slim for a video, building-project-showcases for durable presentation, and planning-launch-distribution for channel-specific release work. This method owns readiness and truthful claims, not the video's editing, page design, deployment, or the launch schedule.

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.