agentleFS
Sign inStart free
fmindfmind/dotfiles/skills/github-issues/SKILL.md

github-issues

Skill13 starsChanged 4 days agoMITView on GitHub

Plan, draft, update, link, and close GitHub issues.

52 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use github-repo-management, native-mcp and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • math-incSkill

    github-repo-management

    Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.

    Also in 13 projects that use this

  • math-incSkill

    native-mcp

    Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Gauss Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.

    Also in 8 projects that use this

  • john-data-chenSkill

    touchdesigner-mcp

    Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.

    Also in 5 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 4 projects that use this

  • Tommy-ywSkill

    songwriting-and-ai-music

    Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.

    Also in 8 projects that use this

  • +7 more from math-inc

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 50 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Distinctive:

    Use gh for account selection, repository identity without printing raw remote URLs, bounded API calls, and request serialization when …

    line 19
  2. Distinctive:

    Refresh current state: before proposing a change:

    line 22
  3. Distinctive:

    Deduplicate: update the existing issue that represents the same outcome.

    line 31
  4. Very specific:

    Green is not closed: verify the issue's acceptance criteria and requested delivery boundary before gh issue close.

    line 44

“Common” is measured: kept by at least 6 in 10 of the 50 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

GitHub Issues

Plan, read, and mutate GitHub issues from verified repository and remote state.

Workflow

Use gh for account selection, repository identity without printing raw remote URLs, bounded API calls, and request serialization when needed.

  1. Confirm the target: resolve the repository from the explicit URL or gh repo view --json nameWithOwner,visibility and state OWNER/REPO; never infer another repository from a similarly named checkout.

  2. Refresh current state before proposing a change:

    gh issue view <number> -R <owner>/<repo> --json number,title,body,state,stateReason,labels,assignees,milestone,url
gh issue list -R <owner>/<repo> --state all --search '<distinct terms>' --limit 20 --json number,title,state,url
gh search issues '<problem in plain words>' -R <owner>/<repo> --search-type hybrid --limit 20 --json number,title,state,url
  3. Load discussion when relevant: fetch comments separately when decisions, acceptance criteria, or requested replies depend on them; preserve that context before editing. Narrow or paginate a lexical search that reaches its limit, and add the hybrid search (one relevance-ranked page) for differently worded duplicates, before claiming no duplicate exists.
  4. Deduplicate: update the existing issue that represents the same outcome; keep reproduction, acceptance criteria, dependencies, decisions, and proof; drop stale logs and duplicate checklists.
  5. Draft before creating: for multiple findings or dependency-aware work, apply the backlog workflow, present the reviewable set, and stop unless issue creation is already authorized.

  6. Apply one bounded mutation the user authorized. Write substantial bodies to a temporary file and pass --body-file; avoid shell interpolation and interactive prompts:

    gh issue create -R <owner>/<repo> --title '<title>' --body-file <body-file>
gh issue edit <number> -R <owner>/<repo> --body-file <body-file>
  7. Verify from GitHub: re-read with gh issue view --json ..., compare the intended fields, and report the URL; a zero exit code alone is not proof of final state.

Gotchas

  • Green is not closed: verify the issue's acceptance criteria and requested delivery boundary before gh issue close; local passing code is not delivery.
  • Change coordination fields only when named: assignments, comment notifications, milestones, and project changes are coordination acts; make them only when the request names them.

Documentation

  • Upstream: github/awesome-copilot ships a same-name github-issues (GitHub MCP tools); preview it, never install it under that name (vendor-skill policy).
  • gh issue manual
  • Releases: GitHub CLI
  • Companion skills: full-review (verified findings), github-pull-request (the PR).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free