agentleFS
manoharanandmanoharanand/claude-skills/skills/account-setup/SKILL.md

account-setup

Skill0 starsChanged 3 months agoMITView on GitHub

Interactive setup for Jira and GitHub credentials — prompts for a Jira API token and a GitHub personal access token, saves them to ~/.claude/.env, and registers the "atlassian" and "github" MCP servers with Claude Code. Use when the user asks to set up Jira/GitHub integration, configure MCP for Jira or GitHub, run account-setup, or connect Claude to their Jira/GitHub accounts.

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. neonwatty/job-apply-plugin★ 139same name
    2. microsoft/aibast-agents-library★ 8same 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.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    Ask the user to paste their token into the chat.

    line 47
  2. Distinctive:

    Run the script yourself via the Bash tool with a token as an argument — the value would land in the transcript and shell history.

    line 48
  3. Very specific:

    If asked to check current status, use only non-secret checks, e.g.: test -f ~/.claude/.env && echo present || echo missing and claude mcp …

    line 55
  4. Very specific:

    After the user confirms they've run it, verify with claude mcp list and remind them to restart Claude Code for new MCP servers to take …

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

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

account-setup

Sets up Jira and GitHub access for Claude Code:

  1. Collects a Jira site URL, Jira account email, Jira API token, and a GitHub personal access token.
  2. Saves them to ~/.claude/.env (chmod 600).
  3. Registers the github and atlassian MCP servers (user scope) via the claude mcp add CLI, so Claude Code can call GitHub and Jira directly in any project.

The actual work is done by setup.sh in this skill's directory.

Run this in a real terminal — never through Claude's chat

Tokens must never be typed into a Claude chat message — anything pasted into chat becomes part of the conversation transcript and history. When this skill is invoked, tell the user to run the script themselves in their terminal:

bash ~/.claude/skills/account-setup/setup.sh

It prompts interactively with hidden input (read -s) for the tokens. For non-interactive use it also accepts flags:

bash ~/.claude/skills/account-setup/setup.sh \
  --jira-url https://yourorg.atlassian.net \
  --jira-email you@example.com \
  --jira-token <token> \
  --github-token <token>

Do not:

  • Ask the user to paste their token into the chat.
  • Run the script yourself via the Bash tool with a token as an argument — the value would land in the transcript and shell history.

What Claude should do when this skill is invoked

  • Explain the script does the setup and give the user the command above to run themselves.
  • If asked to check current status, use only non-secret checks, e.g.: test -f ~/.claude/.env && echo present || echo missing and claude mcp list — never cat the .env file or otherwise surface token values.
  • After the user confirms they've run it, verify with claude mcp list and remind them to restart Claude Code for new MCP servers to take effect.

Requirements

Implementation notes

  • GitHub is wired to GitHub's official remote MCP endpoint (https://api.githubcopilot.com/mcp/) via an Authorization: Bearer header — no local process needed.
  • Jira uses the community mcp-atlassian server run via docker run -i --rm, since it isn't available as a simple remote/npx server.
  • Re-running the script is safe: it overwrites existing keys in .env in place and re-registers (mcp remove + mcp add) both MCP servers rather than erroring on duplicates.

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.