agentleFS
sabirmgdsabirmgd/terminal-first-goal-loop/skills/jira-manager/SKILL.md

jira-manager

Skill2 starsChanged 2 months agoMITView on GitHub

Retrieve, search, draft, create, update, and link issue-tracker tickets through the available CLI, MCP, or API, with read-only default behavior and explicit write previews.

2 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

10 rules. About 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    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:

    Use this when a task needs ticket context or when a ticket should be drafted or updated from the terminal.

    line 8
  2. Distinctive:

    Do not open the browser unless the task is blocked on an interface gap.

    line 32
  3. Distinctive:

    When searching, return the smallest useful result set.

    line 50
  4. Distinctive:

    When asked to create or update a ticket, first produce a preview with:

    line 54
  5. Distinctive:

    Do not send the write yet unless the current task explicitly authorizes it.

    line 66
  6. Distinctive:

    read the result back

    line 74
  7. Distinctive:

    If the write fails, show the failure plainly.

    line 77
  8. Distinctive:

    Never invent ticket activity or acceptance criteria.

    line 81
  9. Distinctive:

    Never move a ticket, add a comment, or change an assignee without explicit authority.

    line 82
  10. Distinctive:

    If the task describes work discussed in chat, draft the ticket text first instead of creating a vague ticket directly.

    line 84

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Manager

Use this when a task needs ticket context or when a ticket should be drafted or updated from the terminal.

Default mode

Read-only by default.

That means it is always safe to:

  • retrieve one ticket
  • search tickets
  • list comments or linked issues
  • draft ticket text
  • prepare an update payload

External writes need explicit authority.

Interface order

Prefer:

  1. the configured issue-tracker CLI
  2. a scoped MCP tool
  3. a direct API call

Do not open the browser unless the task is blocked on an interface gap.

Read workflow

For read operations, return:

System:
Project or workspace:
Ticket:
Summary:
Status:
Assignee:
Links:
Comments or activity summary:
Evidence:

When searching, return the smallest useful result set. Do not paste the whole board.

Draft workflow

When asked to create or update a ticket, first produce a preview with:

Action:
Target project or ticket:
Proposed title:
Proposed description:
Proposed acceptance criteria:
Proposed links or attachments:
Exact write command or payload:

Do not send the write yet unless the current task explicitly authorizes it.

Write workflow

Once authority is explicit:

  1. resolve the exact project and ticket target
  2. send the smallest required create or update
  3. read the result back
  4. return the new ticket key, status, and proof

If the write fails, show the failure plainly. Do not quietly retry with changed fields.

Rules

  1. Never invent ticket activity or acceptance criteria.
  2. Never move a ticket, add a comment, or change an assignee without explicit authority.
  3. Preserve issue links, dependencies, and external identifiers exactly.
  4. If the task describes work discussed in chat, draft the ticket text first instead of creating a vague ticket directly.

Stop rules

Stop when:

  • the read result is complete
  • the preview is ready for approval
  • the authorized write is confirmed
  • the target system or permission is blocked and the blocker is explicit

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.