upstream-contribution
Skill0 starsChanged yesterdayMITView on GitHub
Prepare an issue, commit or pull request for a project you don't maintain, following its contribution and AI policy, its conventions and its CI. Use before writing anything to submit to another project's repository.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- alblez/hermes-skillstheir own version, first seen Nov 15, 2026
- jmrplens/gitlab-mcp-servertheir own version, first seen May 30, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- jmrplens/gitlab-mcp-server★ 47same name
- alblez/hermes-skills★ 29same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository34 other files it gives its agents.
- astroSkill
- bun-standardsSkill
- postgresSkill
- react-engineeringSkill
- rust-standardsSkill
- spring-bootSkill
- tailwind-v4Skill
- typescript-standardsSkill
- vitest-testingSkill
- api-designSkill
- architecture-reviewSkill
- benchmark-readiness-reviewSkill
- cli-designSkill
- codebase-scoutingSkill
- code-review-findingsSkill
- config-projection-reviewSkill
- documentation-hygieneSkill
- domain-modelingSkill
- formal-verificationSkill
- implementation-planningSkill
- orchestration-workflowSkill
- problem-clarificationSkill
- product-copySkill
- refactorSkill
- repository-text-hygieneSkill
- researchSkill
- security-scope-reviewSkill
- setup-canastaSkill
- system-designSkill
- task-closeoutSkill
- tddSkill
- technical-writingSkill
- writing-issuesSkill
- writing-prSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read the project's rules before writing: Read CONTRIBUTING, any AI or agent policy it links, its pull request and issue templates, any …
- Distinctive: line 16
Stop when the policy forbids the contribution: If it rules out this contribution as prepared, for example AI help on an issue reserved for …
- Very specific: line 21
Disclose AI use exactly as the project asks: Follow its placement (pull request description, commit trailer or both) and its format.
- Distinctive: line 28
Make the smallest change that fits its design: Before submitting, review the diff against its standards, and check that every pattern you …
- Distinctive: line 31
Predict CI only by reproducing it: Use the same workflow, platform, branches and job types.
≈ “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
Upstream contribution
The project's rules decide what you submit. Your own organization's conventions, such as risk notes, merge policies, templates and attribution habits, stay out unless the project asks for them.
- Read the project's rules before writing. Read
CONTRIBUTING, any AI or agent policy it links, its pull request and issue templates, any contributorAGENTS.md, and three recently merged pull requests from outside contributors. Note what it asks for and what it forbids. - Stop when the policy forbids the contribution. If it rules out this contribution as prepared, for example AI help on an issue reserved for newcomers or an AI-written description, don't write the submission. Tell the user which rule applies and what the policy allows instead: another issue, doing it without AI, or asking the maintainers.
- Disclose AI use exactly as the project asks. Follow its placement (pull
request description, commit trailer or both) and its format. Don't use a
format it forbids, such as an
Assisted-by:trailer. If it says nothing, ask the user. Never add a sign-off, DCO line or CLA statement for the human; they add their own. - Match the project's style. Copy the title format, sections, length and tone of its merged pull requests. Address the project, not one maintainer.
- Make the smallest change that fits its design. Before submitting, review the diff against its standards, and check that every pattern you copied has a reason that applies here.
- Predict CI only by reproducing it. Use the same workflow, platform, branches and job types. Name any job you didn't run.
- Lead with the general problem. Then cite the project's own stated rule it breaks, then your case as evidence. Keep your own product's internals out; the reproduction must not need them.
- The user posts it. The user reviews and posts, or approves, everything that leaves their machine.
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.