acli
Search, plan, and update Atlassian Jira and Confluence with acli.
Install
npx skills add https://github.com/fmind/dot/tree/main/skills/acli
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install fmind-dot@llmmart
git clone https://github.com/fmind/dot.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole fmind/dot collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Atlassian CLI
Operate Jira and Confluence Cloud via acli. Atlassian ships no acli skill, so this connector owns auth, bounded reads, and write authority.
Workflow
Resolve the account:
acli auth status,login, andswitchmanage OAuth. API tokens are per-service (acli jira auth/acli confluence auth); always pipe tokens on stdin, never in argv: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.txtBound every read: pass JQL limits, explicit
--fields, and--json: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 --jsonExpand selectively: fetch
descriptionorcommentonly when needed. Treat results hitting--limitas partial: check--count, then tighten JQL or pass--paginatebefore claiming completeness.Write with authority: reuse user authority for the target keys, fields, comments, assignments, or bulk scope; ask when consequential scope is missing. Prefer
--generate-json/--from-jsonand file inputs (--description-file,--body-file) over inline multiline args: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.txtVerify by reading back: run
view --jsonafter every write and check the updated fields.
Gotchas
- Bulk flags hit every match:
--jqland--filterontransition,edit, orcommentmutate all matches;--yesskips prompts, never authority. - Confluence pages are read-only in acli 1.3.40: no Confluence search, and
confluence pagesupports onlyview(blogs/spaces support create); use Rovo MCP under the same authority to search or edit pages. - Rovo Dev & MCP:
acli rovodevalready reads.agents/skillsand~/.agents/skills;atlassian/atlassian-mcp-server(DISABLE_TELEMETRY=1 skills add atlassian/atlassian-mcp-server --list, configured via mcp-setup) covers Rovo MCP, notacli.
Documentation
- acli reference
- Releases: acli changelog
- Companion skills: issues (same authority rules for GitHub), gws (Google Workspace), mcp-setup.
Files (dot)
-
SKILL.md 3.1 KB
--- name: acli description: "Search, plan, and update Atlassian Jira and Confluence with acli." license: MIT metadata: kind: connector author: Médéric HURIER (Fmind) source: github.com/fmind/dot/tree/main/skills/acli created: "2026-09-02" updated: "2026-11-10" --- # Atlassian CLI Operate Jira and Confluence Cloud via `acli`. Atlassian ships no `acli` skill, so this connector owns auth, bounded reads, and write authority. ## Workflow 1. **Resolve the account**: `acli auth status`, `login`, and `switch` manage OAuth. API tokens are per-service (`acli jira auth` / `acli confluence auth`); always pipe tokens on stdin, never in argv: ```bash 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 ``` 1. **Bound every read**: pass JQL limits, explicit `--fields`, and `--json`: ```bash 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 ``` 1. **Expand selectively**: fetch `description` or `comment` only when needed. Treat results hitting `--limit` as partial: check `--count`, then tighten JQL or pass `--paginate` before claiming completeness. 1. **Write with authority**: reuse user authority for the target keys, fields, comments, assignments, or bulk scope; ask when consequential scope is missing. Prefer `--generate-json` / `--from-json` and file inputs (`--description-file`, `--body-file`) over inline multiline args: ```bash 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 ``` 1. **Verify by reading back**: run `view --json` after every write and check the updated fields. ## Gotchas - **Bulk flags hit every match**: `--jql` and `--filter` on `transition`, `edit`, or `comment` mutate all matches; `--yes` skips prompts, never authority. - **Confluence pages are read-only in acli 1.3.40**: no Confluence search, and `confluence page` supports only `view` (blogs/spaces support create); use Rovo MCP under the same authority to search or edit pages. - **Rovo Dev & MCP**: `acli rovodev` already reads `.agents/skills` and `~/.agents/skills`; `atlassian/atlassian-mcp-server` (`DISABLE_TELEMETRY=1 skills add atlassian/atlassian-mcp-server --list`, configured via [mcp-setup](../agent-harnesses/references/mcp-setup.md)) covers Rovo MCP, not `acli`. ## Documentation - [acli reference](https://developer.atlassian.com/cloud/acli/reference/commands/) - Releases: [acli changelog](https://developer.atlassian.com/cloud/acli/changelog/) - Companion skills: [issues](../gh/references/issues/GUIDE.md) (same authority rules for GitHub), [gws](../gws/SKILL.md) (Google Workspace), [mcp-setup](../agent-harnesses/references/mcp-setup.md).
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.