github-tickets
Skill20 starsChanged 43 days agoMITView on GitHub
Break a plan, spec, or conversation into tracer-bullet GitHub issues for this repo, creating a parent tracking issue with sub-issues when publishing multiple tickets.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- joel611/skillstheir own version, first seen Nov 8, 2026
- RafalKielbasa/claude-skillstheir own version, first seen Nov 6, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- joel611/skills★ 1same name
- RafalKielbasa/claude-skills★ 1same 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 repository26 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- breakdownSkill
- bug-investigationSkill
- code-review-adversarialSkill
- code-review-multiSkill
- code-review-with-followupSkill
- document-changesSkill
- grillingSkill
- type-test-codeSkill
- explain-changesSkill
- github-actions-ciSkill
- github-appSkill
- implementation-planSkill
- implement-simpleSkill
- implementSkill
- implement-ttcSkill
- orchestrationSkill
- pull-requestSkill
- review-and-wrap-upSkill
- verusSkill
- specSkill
- ticketsSkill
- update-working-copySkill
- verifySkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 4 are distinctive, and 8 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.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Read the /tickets and /to-tickets skill and follow its full process.
- Very specific: line 19
If the /tickets skill is unavailable, just use /to-tickets.
- Very specific: line 21
If /to-tickets skill does not exist on this machine, stop and tell the user the to-tickets skill is missing.
- Very specific: line 28
Create all issues with ${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app.sh issue create.
- Very specific: line 32
After each create command, extract the issue number strictly from the printed URL.
- Very specific: line 37
If the approved breakdown has exactly one ticket, keep the base behavior: create one ready-for-agent issue and do not create a parent issue.
- Distinctive: line 40
If the approved breakdown has two or more tickets:
- Distinctive: line 42
Create a parent epic tracking issue first.
- Distinctive: line 48
Create child issues in dependency order.
- Distinctive: line 50
Use the base issue template.
- Very specific: line 52
After each child issue is created, attempt: ${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app-issue-sub-issue.sh add --parent N --child M
- Very specific: line 65
After all children are created, update the parent with ${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app.sh issue edit N --body-file FILE, …
≈ “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
/github-tickets
This project builds on top of the tickets/to-tickets skill so multi-ticket breakdowns
are published with a parent tracking issue (epic) and native GitHub sub-issue links.
It also asks for more detail in the ticket.
Delegate first
Read the /tickets and /to-tickets skill and follow its full process. This skill just modifies the publishing portion.
If the /tickets skill is unavailable, just use /to-tickets.
If /to-tickets skill does not exist on this machine, stop and tell the user the
to-tickets skill is missing.
Publishing override for this repo
This section provides specific details for how to publish to "A real issue tracker"
Create all issues with ${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app.sh issue create. Write issue
bodies to temp files and pass them with --body-file; never pass Markdown with
--body.
After each create command, extract the issue number strictly from the printed
URL. It must match https://github.com/<owner>/<repo>/issues/<digits> for this
repo's origin. If extraction fails, stop and report the URL instead of passing a
garbage number to another script.
If the approved breakdown has exactly one ticket, keep the base behavior: create
one ready-for-agent issue and do not create a parent issue.
If the approved breakdown has two or more tickets:
- Create a parent epic tracking issue first.
- Title: the short name of the work.
- Body: the source spec verbatim, or a synthesized spec if working only from conversation, prefixed with one line saying this is a tracking issue whose sub-issues are the implementation tickets.
- Labels: none.
- Create child issues in dependency order.
- Apply the
ready-for-agentlabel. - Use the base issue template.
- Include
## Parentwith a reference to the parent issue number.
- Apply the
- After each child issue is created, attempt:
${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app-issue-sub-issue.sh add --parent N --child M - Sub-issue linking is failure-tolerant. If linking fails because of a 403, 422, rate limit, or similar API issue, record the failure, keep creating the remaining children, and report all link outcomes at the end.
- Once every child issue exists, record the approved breakdown's blocking
edges as native dependencies. For each ticket with declared blockers, run:
${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app-issue-dependency.sh add --blocked M --blocker K(Mis the blocked child's issue number,Kis each blocker's). Do this as a final pass after all children exist — a blocker's issue number isn't necessarily known yet when its dependents are created. Same failure-tolerant contract as sub-issue linking: on 403, 422, rate limit, or similar, record the failure, keep going, and report all outcomes at the end. - After all children are created, update the parent with
${CLAUDE_SKILL_DIR}/../github-app/scripts/gh-app.sh issue edit N --body-file FILE, re-sending the full body plus an appended## Implementation ticketssection. List every child URL in dependency order, note its blockers in prose (e.g.blocked by #12, #13) so the graph survives even where a link attempt failed, and note any native sub-issue or blocked-by links that failed.
Relay all created issue URLs back to the user, parent first, including any sub-issue or blocked-by link failures.
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.

