github-code
Skill394 starsChanged 7 months agoApache-2.0View on GitHub
Work with GitHub repositories, source code, branches, commits, pull requests, reviews, diffs, CI, and repository credentials. Use for implementation, source investigation, clone/fetch/branch workflows, PR creation or updates, review feedback, GitHub Actions checks, and repository permission failures. Prefer this skill for repository tasks even when they concern a Sentry product.
- Commits and pushes
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
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 8
Use git and gh for repository work.
- Very specific: line 29
Use the requested repo. Otherwise read github.repo with standalone jr-rpc config get github.repo.
- Distinctive: line 31
Read each applicable AGENTS.md before edits.
- Distinctive: line 32
Keep unrelated work. Never delete refs or make destructive merges.
- Distinctive: line 34
Use repository evidence. Report only checks you ran.
- Distinctive: line 36
When an error names a tool, use it.
- Distinctive: line 37
Stop for an unclear target, missing access, destructive work, or a GitHub permission failure.
- Distinctive: line 42
Do not install or repair the GitHub plugin from this skill.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
GitHub code
Use git and gh for repository work.
| Action | Tool / command |
| Create PR | github_createPullRequest (not gh pr create) |
| Update PR title/body/base/state | github_updatePullRequest |
| Mark PR ready / draft | github_updatePullRequest with draft: false / draft: true |
| Submit PR review | github_submitPullRequestReview |
| Resolve review thread | github_resolvePullRequestReviewThread |
| Clone missing repo | github_cloneRepository (not git clone or gh repo clone); on Workspace match error use switchWorkspace |
Open when needed
| Need | Read |
| Commands and permissions | references/api-surface.md |
| Edit, verify, and open a PR | references/workflow.md |
| Command or permission failure | references/troubleshooting-workarounds.md |
Always
- Use the requested repo. Otherwise read
github.repowith standalonejr-rpc config get github.repo. - Pass
--repo owner/repotogh. Usegit -C PATHfor local repos. - Read each applicable
AGENTS.mdbefore edits. - Keep unrelated work. Never delete refs or make destructive merges.
- Force-push only with
--force-with-lease, and only to branches Junior pushed or the requester named. - Use repository evidence. Report only checks you ran.
- Push before
github_createPullRequest. Never ask for a token for bot pushes. - When an error names a tool, use it. Change permissions only when GitHub rejected the request.
- Stop for an unclear target, missing access, destructive work, or a GitHub permission failure.
- Code changes always end in a pushed branch and a PR. Do not ask whether to open one. Skip it only when the user opts out or asks for investigation only.
- Open the PR ready for review when the work is complete and the checks pass. Open a draft when work, checks, or decisions remain. A scope or follow-up question is not a reason to stop: open the PR, and name the question in the PR body and the report.
- Report repo, branch, PR, checks, and skipped checks.
Do not install or repair the GitHub plugin from this skill.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- packages/docs/public/llms.txtllms.txt
- nitroSkill
- pi-agent-integrationSkill
- public-docsSkill
- slack-developmentSkill
- vercel-queuesSkill
- vercel-sandboxSkill
- example-bundle-helpSkill
- example-localSkill
- agent-browserSkill
- demo-videoSkill
- visual-web-qaSkill
- amplitudeSkill
- cloudflareSkill
- datadogSkill
- eval-authSkill
- eval-oauthSkill
- coding-workspace-fixtureSkill
- github-headless-pr-fixtureSkill
- eval-directorySkill
- eval-guardian-actionsSkill
- eval-mcpSkill
- incident-briefSkill
- resilient-working-directorySkill
- source-handbookSkill
- weather-lookupSkill
- figmaSkill
- github-issuesSkill
- hexSkill
- linearSkill
- self-updateSkill
- notionSkill
- octolensSkill
- pagerdutySkill
- sentrySkill
- jr-rpcSkill
- eval-authSkill
- ttsSkill
- vercelSkill
- junior-qaSkill
- juniorSkill
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.