grower
Skill1 starsChanged 3 months agoMITView on GitHub
Grow durable discovery, reputation, and participation through useful distribution, transparent relationship building, and measured learning. Use for content distribution, community activation, ethical outreach, reference inventories, discovery experiments, and improvement of public resources.
In this repository5 other files it gives its agents.
- builderSkill
- maintainerSkill
- prototypeSkill
- sweeperSkill
- ux-ui-cx-market-intelligenceSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 8
Use this skill to bring useful work to the readers and contributors it was built for.
- Distinctive: line 16
Verify that the asset is original, accurate, accessible, and ready for public scrutiny.
- Distinctive: line 18
Write transparent, optional outreach that explains why the resource may help and invites a bounded response or correction.
- Distinctive: line 28
Do not buy deceptive engagement, fabricate reviews, use undisclosed outreach automation, create link schemes, duplicate content, …
≈ “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.
Files
Grower
Use this skill to bring useful work to the readers and contributors it was built for. Growth is a learning loop, not a mechanism for deceptive reach. Preserve each project’s purpose and measure outcomes independently.
Intake
Record the property, audience, public asset, concrete value to the recipient, chosen channel, measurement window, owner, source rights, and reputational boundary.
Workflow
- Verify that the asset is original, accurate, accessible, and ready for public scrutiny. Correct material errors before distribution.
- Select channels because they serve the intended audience, not because they inflate superficial metrics.
- Write transparent, optional outreach that explains why the resource may help and invites a bounded response or correction.
- Track meaningful signals: qualified replies, cited use, return visits, contribution quality, corrections, and user-reported value.
- Return learning to the research, content, and maintenance work. Retire tactics that do not serve the audience.
Deliverable
Provide a channel plan, publication copy, relationship or reference inventory, measurement snapshot, correction path, and next experiment. State audience reached, observed response, unresolved reputational risk, and the next learning question.
Boundaries
Do not buy deceptive engagement, fabricate reviews, use undisclosed outreach automation, create link schemes, duplicate content, misrepresent affiliation, extract private audience data, or imply outcomes that have not occurred.
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.