launch-tracker
Skill0 starsChanged 16 days agoMITView on GitHub
Trigger: launch tracker, where is it published, launch status, record a submission. Keep the table of channels, statuses and links for a tool's launch.
In this repository5 other files it gives its agents.
- launch-community-draftsSkill
- launch-cross-postSkill
- launch-directoriesSkill
- launch-kitSkill
- launch-listsSkill
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
- Distinctive: line 12
Use when the user wants to start, update or review the record of where a tool is published: after any submission, post, PR or rejection, or …
- Distinctive: line 18
Never delete a row; change its status and note why.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Activation Contract
Use when the user wants to start, update or review the record of where a tool is published: after any submission, post, PR or rejection, or when they ask what is left.
Hard Rules
- The tracker lives at
docs/launch/<slug>/tracker.mdin the launched project (seereferences/launch-folder.md). - Record only what was observed: a live URL, a PR number, a confirmation page. If the user reports a post you cannot see, record it as reported and say it is unverified.
- Never delete a row; change its status and note why.
- Dates are absolute (
YYYY-MM-DD), never "yesterday". - One row per channel. Use the statuses listed in the template.
Decision Gates
| Situation | Action |
| No tracker yet | Copy assets/tracker-template.md, fill {NAME} and {DATE} |
| A URL is given | Check it loads (curl -sIL, or the browser for pages behind a login) before marking published |
| A PR is given | Read its state with gh pr view <n> -R <repo> --json state,mergedAt |
| A gate has a reopening date | Add it under Waiting |
| User asks "what is left" | List channels from references/channels.md that have no row, grouped by level |
Execution Steps
- Find or create the tracker.
- Apply the change the user reported or the skill just completed.
- Refresh stale rows when asked: PR states, review queues, cooldown dates.
- Show the changed rows.
Output Contract
Return the tracker path, the rows added or changed, anything left unverified, and the next gate that opens.
References
../../references/launch-folder.md: where launch files live.../../references/channels.md: the channel list and their gates.
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
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.

