gh-tickets
Skill1 starsChanged 2 months agoMITView on GitHub
Drive GitHub tickets from the terminal with gh - create a public repo after the human says yes, open one issue per problem from a generated list or data, edit titles and bodies, close with a reason and a comment that quotes its source, and read the state back. Use when a task delivers tickets as GitHub issues, when the user says "open an issue per X", "file these as tickets", "close the tickets that are done". For splitting a plan into issues use plan-to-issues.
In this repository28 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- architect-reviewSkill
- article-writingSkill
- changelog-watchSkill
- coordinator-workersSkill
- cost-forecastSkill
- design-docSkill
- documentSkill
- ea-briefingSkill
- estimateSkill
- eval-toolSkill
- headless-loopSkill
- interview-guideSkill
- job-supervisorSkill
- market-researchSkill
- meeting-notesSkill
- migration-planSkill
- obsidian-noteSkill
- plan-to-issuesSkill
- postmortemSkill
- readSkill
- release-notesSkill
- skill-stocktakeSkill
- slide-deckSkill
- status-reportSkill
- threat-modelSkill
- tradeoff-tableSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Ask the human first: a repo they name, or a new one.
- Very specific: line 30
Put the count in the title in a fixed shape, such as (379 reports).
≈ “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
gh-tickets
Tickets are GitHub issues in one repo. Every step is a gh command; read --help for a flag before you use it, never guess it. gh auth status says whether you are signed in; signing in is the human's step.
1. The repo
Ask the human first: a repo they name, or a new one. Say who will see it. Then:
gh repo create <name> --public --description "<one line>"If the permission classifier refuses a public repo, the durable fix is the allow rule Bash(gh repo create *) in ~/.claude/settings.json; the human adds it or says yes to adding it. Run the bare gh repo create on its own line, not chained with cd or find, or the classifier reads the whole chain. Done when gh api repos/<owner>/<name> --jq .visibility prints public.
2. One issue per problem
Generate the titles and bodies with code from the same data the deliverable renders, so the count in the title and the number on the page cannot drift. Write each to a file, then:
gh issue create --repo <owner>/<name> --title "$(cat title.txt)" --body-file body.mdPut the count in the title in a fixed shape, such as (379 reports). Record the issue numbers in the data file the page reads. Done when gh issue list --json number,title shows every problem once.
3. Changing and closing
gh issue edit <n> --title "..." --body-file body.md
gh issue close <n> --reason completed --comment "<what resolved it, with its source>"
gh issue close <n> --reason "not planned" --comment "<why not, with its source>"
gh issue comment <n> --body "<why it stays open>"Close a ticket only when a source says the work is done, and quote that source in the comment. A problem nobody resolved stays open. Done when gh issue list --state all --json number,state,stateReason matches the sources.
Gotcha
In zsh, for pair in "1 parser"; do set -- $pair does not split words. Use case or separate arrays. Long quoted one-liners of issue bodies break too: write bodies to files from a short Python script.
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.

