PlugWiki

oss-launch skill (samber): plan an open-source launch, gate to day 30

Plans an open-source launch end to end: clearance, readiness gate, positioning, channel order, launch-day run of show and measurement.

Installs
12.8K
on skills.sh
Stars
7
on GitHub
Files
7
besides SKILL.md
Updated
Nov 2026
last repo commit

oss-launch makes your agent interview you about a repository that is about to go public, then write a launch plan you can run without it. It clears the name and license first, scores the repo against a blocker and booster checklist, drafts the one-liner and the "why not X" answer, picks one anchor channel and builds an hour-by-hour launch day.

It triggers when you say you are about to release, announce or "Show HN" a repository, want GitHub Trending, or ask why a launch fell flat. The folder holds SKILL.md and six reference files and bundles no scripts. SKILL.md names no API key or account.

Good for

  • Maintainers about to make a repository public who want a plan before they post
  • Engineers open-sourcing an internal tool at a company
  • Anyone whose launch fell flat and who wants the funnel stage that leaked

Install oss-launch

Claude Code

  1. 1

    Copy this prompt.

    Install the oss-launch skill in Claude Code. Run this command:
    
    /plugin marketplace add samber/developer-relations-skills
    /plugin install developer-relations-skills@developer-relations-skills
    
    Then check that it loaded and tell me how to use it.
  2. 2

    Paste it into Claude Code. It shows the change and asks before running it.

The README recommends installing the whole collection because its skills reference each other, and oss-launch names other skills in the collection to hand work to. The whole-collection routes add all 93 skills in the repo (counted from the git tree); the repo holds no hooks, agents, commands or MCP server files, and 14 of its skills bundle a script. Pick one route per agent.

From the project README. Source.

What's in the skill

When it loads

Plans and runs an open-source project launch end to end - name and license clearance, the readiness gate, positioning and one-liner, channel sequencing, the launch-day war room, star-velocity and GitHub Trending mechanics, and post-launch measurement. Use whenever someone is about to release, announce, open-source or "Show HN" a repository, asks how to reach GitHub Trending, wants the first real users or stars for a new library, is planning a Product Hunt post or a multi-day launch week, or asks why a launch fell flat (even if they only say they are pushing a repo public). Covers individual-developer and company adoption. Not ongoing distribution afterwards - use samber/developer-relations-skills@oss-distribution-strategy instead. Not HN site rules - use samber/developer-relations-skills@hackernews-playbook. Not Product Hunt site rules - use samber/developer-relations-skills@producthunt-playbook.

Sections in SKILL.md

  1. Interview
  2. Step 1 - Clear the name and the license
  3. Step 2 - Run the readiness gate
  4. Step 3 - Sharpen the positioning
  5. Step 4 - Choose the launch shape
  6. Step 5 - Sequence the channels
  7. Step 6 - Stand up the war room and run the day
  8. Step 7 - Concentrate velocity, never manufacture it
  9. Step 8 - Measure honestly
  10. Invocation examples
  11. Expected output
  12. Verdict go / go with reduced scope / not ready (blockers listed)
  13. Clearance name, trademark, license, CLA/DCO status
  14. Positioning one-liner, why-not-X, three claims we can defend
  15. Audience individual / company adoption, and the assets each needs
  16. Shape single spike or caravan, with the reason

Key facts

Installs on skills.sh
12,783 (as of Nov 2, 2026)
Version in SKILL.md
1.0.5

What it includes

  • Asks one question at a time until it can name the audience, anchor channel and goal.

    Eleven questions. Questions 8 to 10 (deadline, spike or compounding goal, effort ceiling) set the channel ranking, so they come before any proposal. SKILL.md also tells the agent to keep a few project notes in memory.

    Interview

  • Treats a trademark or license conflict as a rename before launch, not a risk to carry.

    Runs a trademark clearance check across similar names, secures the domain, organization and handles, and settles license and CLA-versus-DCO in the same pass.

    Step 1 - Clear the name and the license

  • Scores the repo against blockers and boosters; every blocker must pass first.

    The pass test is a cold run: someone who has never used the project follows only the README. If the agent can execute commands it does that run itself in a fresh directory and logs every guess.

    Runs code · Step 2 - Run the readiness gate

  • Writes the one-liner and an explicit "why not X" answer, then checks credibility.

    The one-liner format is "<name> is a <category> for <audience> that <capability the alternatives lack>". It names real alternatives and publishes limitations up front.

    Step 3 - Sharpen the positioning

  • Picks a single spike or a multi-day launch caravan.

    The default is a single spike. A caravan needs at least three announceable items, a conference or fixed date on the calendar and staff to name an owner per day.

    Step 4 - Choose the launch shape

  • Picks one anchor channel and ranks six rows of work by outcome per maintainer hour.

    Registry publish, anchor post, secondary communities, your own accounts, newsletters and lists, and a long-form write-up. Rows 1 to 3 are the default launch.

    Step 5 - Sequence the channels

  • Builds an hour-by-hour run of show with one named owner per channel.

    Includes the first top-level comment, a response rotation and a separate path for security reports that bypasses the rotation.

    Step 6 - Stand up the war room

  • Bans soliciting votes or stars and sets day 1, day 7 and day 30 readings.

    It tells you to capture a baseline the evening before launch and to read stars against cloners and downloads.

    Step 7 and 8 - Velocity and measurement

  • Produces a launch plan with nine sections, agreed one section at a time.

    Verdict, Clearance, Positioning, Audience, Shape, Channels, Run of show, Measurement and Risks.

    Try: “We're open-sourcing our internal feature-flag service next month. Can you plan the launch?”

    Launch plan output

From the official docs

Permissions

Low risk

The agent can run your README commands in a fresh directory and save notes to a file called devrel-context.md, so use an empty directory and check that file before you commit it.

What it can do

  • Read your data
  • Create and change things
  • Delete things
  • Read-only mode

Watch out for

  • The cold run executes your README commands

    Step 2 has the agent follow your README in a fresh directory when it can execute commands. Our advice: use an empty directory or container and read each command before it runs. github.com

  • It may keep notes in devrel-context.md

    SKILL.md tells the agent to store a few details about the current task or project, and to use a file called devrel-context.md when its memory lives in a file. Our advice: open that file before you commit or share the folder. github.com

  • The plugin route installs the whole collection

    The README's plugin and extension routes add every skill in the repo; its git tree holds 93. The repo has no hooks, agents, commands or MCP server files, and 14 of its skills bundle a script. Our advice: use the skills CLI command for this skill if you want only it. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details
Turning on read-onlySKILL.md describes no read-only mode.
Scopes
  • Can run your README commands in a fresh directory for the readiness cold run (Step 2)

Questions

How do I install oss-launch?

The README says to install every skill in the collection, because its skills reference each other. In Claude Code that is the plugin route in the install box above, which adds all 93 skills in the repo. The skills CLI can add just this one. Our advice: pick one route per agent.

What do I get at the end?

A launch plan with nine sections: Verdict, Clearance, Positioning, Audience, Shape, Channels, Run of show, Measurement and Risks. SKILL.md has the agent present it section by section and get agreement before moving on.

Will it get me on GitHub Trending?

It will not promise that. SKILL.md says the Trending selection formula is unpublished and tells the agent to name your language page as the realistic target and refuse to promise placement. It also bans asking anyone to upvote or star.

oss-launch vs oss-distribution-strategy: which one?

Use oss-launch for the one-time launch window and oss-distribution-strategy for how people keep finding the project afterwards. SKILL.md says "Not ongoing distribution afterwards" and hands that to oss-distribution-strategy, which the README describes as the ongoing distribution mix after launch.

Does oss-launch need an API key, and where does it work?

SKILL.md names no API key, account or environment variable. The README documents installs for Claude Code, Claude.ai (add the repo as a plugin marketplace), Codex, Cursor, Gemini CLI and any Agent Skills-compatible tool through the skills CLI. The install box has the steps for each.

Is oss-launch safe to install?

It is instructions plus six reference files, and the folder bundles no scripts. In Step 2 the agent may run your README commands in a fresh directory, and it may save project notes to devrel-context.md. Our advice: let it do the cold run in an empty directory or container and read each command first.

Information

updated Nov 2, 2026

Folder
skills/oss-launch

samber/developer-relations-skillsskills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2
  1. developer-relations-skills README · github.com
  2. oss-launch SKILL.md · github.com

Updated Nov 2, 2026.