agentleFS
Sign inStart free
QuixiAIQuixiAI/agi-memory/skills/installed/github-issues/SKILL.md

github-issues

Skill617 starsChanged 10 months agoMITView on GitHub

Search, read, create, and comment on GitHub issues through the GitHub MCP server.

  • Reads credentials

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 1

    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. Very specific:

    Search before creating: Use mcp_github_search_issues to check whether the issue already exists.

    line 28
  2. Distinctive:

    After creating, report the issue URL from the tool result — never invent one.

    line 36

“Common” is measured: kept by at least 6 in 10 of the 52 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

Work with GitHub issues on repositories the configured token can reach. This skill binds the GitHub MCP server: activating it starts the server (first use only) and unlocks the bound tools for this turn.

Workflow

  1. Search before creating. Use mcp_github_search_issues to check whether the issue already exists; duplicate issues waste maintainer attention. Comment on the existing issue instead when appropriate.
  2. Creating an issue is an outward-facing action. Confirm with the user before filing unless they explicitly asked you to file it. Show the title and body you intend to submit.
  3. Reference concrete evidence (file paths, line numbers, reproduction steps) that you actually verified this turn.
  4. After creating, report the issue URL from the tool result — never invent one.

If activation reports needs_setup

Relay the exact next_step to the user (#102). It will point them to run hexis auth github setup-token in a terminal — never ask for or accept a token pasted into chat; the tool activation path already checks Hexis's own stored credential automatically on retry. Explain, if useful, why a public repo still needs this: reading it is public, but creating or commenting on an issue as a specific account is not. Do not claim GitHub capability is missing — it is installed and one step away.

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.

Reviews can't be read right now.

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