agentleFS
ehnruizehnruiz/claude-skills/skills/ticket-digest/SKILL.md

ticket-digest

Skill3 starsChanged 30 days agoMITView on GitHub

Turn a batch of tickets created or updated in a time window into one short, paste-ready message, one line per ticket, flagging the ones that need a decision. Use when the user asks what they filed today or this week, wants a recap or roundup for a product owner or team channel, or after filing three or more tickets in one sitting.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Add the bracket only when it applies: an open question someone must answer, a named reviewer, or ready for estimation.

    line 20

≈ “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

Ticket digest

One message instead of a stream of notifications, readable in thirty seconds.

Steps

  1. Collect. By default, tickets the current user created today, across projects. Widen or narrow the window, project, epic or author as the user asks; for "updated" rather than "created", add the assignee. Fetch titles, types, statuses and parents only. If a title is too vague to summarize, say so; that is a title worth fixing.
  2. Group by parent epic, then by a title prefix if the team uses one, then by project. Add headings only when there is more than one group.
  3. One line per ticket:

    KEY  Type  What it does, in twelve words or fewer  [needs: decision | review | estimate]

    Add the bracket only when it applies: an open question someone must answer, a named reviewer, or ready for estimation.

  4. Up to three sentences of context, and only ones that change what the reader does: why the batch exists, what you are asking for and by when, overlap you spotted with older tickets.
  5. Output plain text ready to paste, with group headings in bold and nothing else formatted, under 150 words for up to ten tickets.

This skill writes the message. The user posts it.

Example

New backlog items, Sep 15

**Media delivery audit** (WEB-120, epic)
WEB-121  Task  Measure PDF sizes and bandwidth
WEB-122  Task  Find pages still serving raw MP4 files
WEB-123  Task  Standardize video transformations  [needs: decision]

**Search**
WEB-130  Bug   Product pages drop structured data when descriptions contain links

Four items from the bandwidth review. WEB-123 needs a call on per-site presets before Thursday; the rest are ready to estimate.

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.