agentleFS
Sign inStart free
fmindfmind/dotfiles/skills/acli/SKILL.md

acli

Skill13 starsChanged 4 days agoMITView on GitHub

Search, plan, and update Atlassian Jira and Confluence with acli.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use acli for Jira and Confluence Cloud from the shell.

    line 15
  2. Very specific:

    Resolve the account: use acli auth status, acli auth login, and acli auth switch for OAuth accounts.

    line 19
  3. Very specific:

    Expand content selectively: add description or comment when the requested work needs them.

    line 34

“Common” is measured: kept by at least 6 in 10 of the 4 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

Atlassian CLI

Use acli for Jira and Confluence Cloud from the shell. Atlassian publishes no skill for acli itself, so this skill owns authentication, bounded reads, and the write boundary.

Workflow

  1. Resolve the account: use acli auth status, acli auth login, and acli auth switch for OAuth accounts. API-token authentication is per service: acli jira auth and acli confluence auth each provide login, status, and switch; pipe the token on stdin, never as an argument.

    acli jira auth login --site <site>.atlassian.net --email <email> --token < token.txt
acli confluence auth login --site <site>.atlassian.net --email <email> --token < token.txt

  2. Bound every read: JQL with a limit and explicit fields, JSON for anything a tool parses.

    acli jira workitem search --jql 'project = TEAM AND status != Done' --fields key,summary,status --limit 50 --json
acli jira workitem view TEAM-123 --fields summary,status --json
acli confluence page view --id <page-id> --body-format storage --json
  3. Expand content selectively: add description or comment when the requested work needs them. Treat a search that reaches its --limit as partial: check the total with --count, then narrow the JQL or use --paginate before claiming completeness.

  4. Write with authority: reuse existing authority for the requested keys, fields, and effects; ask only when consequential scope is missing. Comments, assignments, and bulk operations must be included in that authority. Prefer --generate-json then --from-json for reproducible creations, and pass multiline text through files (--description-file, comment create --body-file) instead of inline arguments.

    acli jira workitem create --project TEAM --type Task --summary "<summary>" --description-file description.txt --json
acli jira workitem transition --key TEAM-123 --status "In Progress"
acli jira workitem comment create --key TEAM-123 --body-file comment.txt
  5. Verify by reading back: view --json after every mutation and compare the requested fields.

Gotchas

  • Bulk flags hit every match: --jql and --filter on transition, edit, or comment act on every match; on transition and edit, --yes skips the prompt, not the authority rule.
  • Confluence pages are read-only: acli 1.3.40 has no Confluence search, and confluence page offers only view (blogs and spaces can be created); search or edit pages through the Rovo MCP server under the same authority.
  • Rovo Dev: acli rovodev is Atlassian's coding agent, not configured here; it reads .agents/skills and ~/.agents/skills, so this catalog is available there without copies.
  • MCP: atlassian/atlassian-mcp-server publishes skills for the Rovo MCP server (DISABLE_TELEMETRY=1 skills add atlassian/atlassian-mcp-server --list), configured per mcp-setup; none covers acli.

Documentation

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