agentleFS
TylerAkinsTylerAkins/ai-agent-skills/skills/jira-tickets/SKILL.md

jira-tickets

Skill1 starsChanged 33 days agoMITView on GitHub

Read Jira issues into sourced requirements and unresolved decisions, or draft, create, and edit concise Jira descriptions and status comments. Use when a Jira key or URL is supplied for work, or Jira writing is requested. Preserve explicit ADF formatting for interactive acceptance criteria, code marks, and mentions.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read anti-ai-writing before drafting human-facing text.

    line 12
  2. Distinctive:

    Follow its ADF construction, code-token audit, task-list, repo-card, mention lookup, and read-back procedure without substituting Markdown …

    line 22
  3. Distinctive:

    If both modes apply, establish sourced requirements through intake first, then apply the writing rules to the authorized draft or write.

    line 24
  4. Distinctive:

    If no available interface meets those requirements, keep the draft local.

    line 35
  5. Distinctive:

    After an authorized write, read the issue back as ADF and verify the required formatting.

    line 47

≈ “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

Jira Tickets

Read anti-ai-writing before drafting human-facing text. Select the requested operation; reading an issue does not authorize Jira writes. Preserve prior authorization within its scope.

Choose the applicable mode, not every mode in sequence:

  • For understanding, planning, or starting work from an issue, read issue intake. This mode is read-only.
  • For descriptions, issue creation or edits, comments, and mentions, read the full writing and ADF rules before preparing the payload. Follow its ADF construction, code-token audit, task-list, repo-card, mention lookup, and read-back procedure without substituting Markdown conversion.
  • If both modes apply, establish sourced requirements through intake first, then apply the writing rules to the authorized draft or write.

Perform Jira operations

  1. Discover the available interfaces before acting. Check configured MCP tools and installed CLI executables, inspect actual schemas or command help, and verify authentication. Resolve the site from the supplied URL or verified account configuration; do not guess cloud IDs, command names, or parameter contracts.
  2. Select MCP or CLI only after confirming it supports the requested operation. For writes, it must accept the required ADF and support the required ADF read-back. If no available interface meets those requirements, keep the draft local; for intake, use supplied issue content rather than guessing or degrading formatting. For intake-only work, complete the read-only intake procedure, report its results, and stop. Steps 3–6 apply only to drafting or authorized writing.
  3. Prepare complete text, destinations, and ADF payloads before any required approval. Drafting alone does not authorize issue creation, edits, transitions, or work logs.
  4. For external comments and status updates, obtain approval of the exact text and destinations under anti-ai-writing. Retain approval for unchanged approved drafts.
  5. Perform only authorized writes, using the complete ADF payload. When editing, preserve unrelated existing content, attributes, and completed task states; the writing reference's TODO examples apply to newly created criteria.
  6. After an authorized write, read the issue back as ADF and verify the required formatting. If a code token is plain text, fix it within the approved scope and repeat the read-back. If read-back is unavailable, report the write as unverified; if a defect remains, report it as incomplete. Structural checks or rendered Markdown do not prove Jira retained interactive checkboxes, code marks, or mentions.

Report actual outcomes and formatting limits.

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.