agentleFS
YassimbaYassimba/loom/skills/ticket-overview/SKILL.md

ticket-overview

Skill9 starsChanged 2 months agoApache-2.0View on GitHub

Read-only Beads/BV ticket guidance. Use when the user asks what's next, wants an open-ticket roadmap, needs the complete issue graph, or asks what a set of tickets is building.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the requested view. If none is specified, ask:

    line 12
  2. Very specific:

    Read its pick with br show <id> --json.

    line 27
  3. Very specific:

    If BV returns nothing, run br ready --json: report an empty list as an empty frontier, epics only as a ready epic frontier, and any …

    line 29
  4. Very specific:

    Use br show <id> --json only when list output truncates important detail or a central ticket's intent is unclear.

    line 45
  5. Very specific:

    Check BV metric status before citing it.

    line 47
  6. Distinctive:

    Keep relation types distinct:

    line 59

≈ “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 Overview

Turn Beads structure into a concise product map. Use reads only; leave the graph unchanged. Never run bare bv because it opens the TUI.

Choose a view

Use the requested view. If none is specified, ask:

  1. Next ticket — preview the next actionable ticket.
  2. Roadmap — map the current open tickets.
  3. Complete graph — map every open and closed ticket.

For named tickets, explain their one-hop dependency neighborhood. When combining Roadmap and Complete graph, show Roadmap first.

Gather evidence

Confirm .beads/ and br exist; views using BV also require bv. Report a missing prerequisite and stop.

Next ticket

  1. Run bv --robot-next.
  2. Read its pick with br show <id> --json.
  3. Skim the affected code enough to ground an approach without starting work.
  4. If BV returns nothing, run br ready --json: report an empty list as an empty frontier, epics only as a ready epic frontier, and any non-epic as a BV discrepancy.

Roadmap and Complete graph

Run:

bv --robot-triage
bv --robot-graph --graph-format=json
bv --robot-plan
bv --robot-insights
br list --json

For Complete graph, also run br list --status closed --json. Roadmap excludes every closed ticket from counts, workstreams, hierarchies, and edges.

Use br show <id> --json only when list output truncates important detail or a central ticket's intent is unclear. For named tickets, start with br show for each ID and expand only when wider context is requested.

Check BV metric status before citing it. Keep literal blocked separate from dependency not_actionable. If the primary critical path is unavailable, use advanced_insights.k_paths and call it BV path analysis. Treat BV plan tracks as scheduling groups, not product workstreams.

Interpret the graph

Derive product workstreams from ticket intent, acceptance criteria, parentage, and dependencies. Give each workstream an outcome. Ensure every in-scope ticket belongs to one primary workstream; show that assignment only when useful.

Explain central tickets as:

why it exists -> what it owns -> what it unlocks

Keep relation types distinct:

  • parent-child: membership; parent above child.
  • blocks: raw BV edges normally point dependent to prerequisite. Confirm one against br show, then draw prerequisite -> unlocked work.
  • related: association; keep outside execution order.

Keep ticket IDs visible and mark states consistently (✓ closed, ○ open, ▶ in progress, ■ blocked). Render roadmap phases as a fenced mermaid timeline and relationships as fenced mermaid flowcharts so both display in chat. In flowcharts, use solid arrows for blocks, hierarchy edges for parent-child, and dotted lines for related; label each relation when its meaning is not obvious.

Write the result

Invoke write-simply and keep BV field names exact.

  • Next ticket: Task, Context, and Approach; then offer to claim and start it via implement.
  • Roadmap: purpose and open-ticket totals, a Mermaid timeline of workstream phases, a Mermaid flowchart of dependencies, bottlenecks, independent tracks, and late or optional work.
  • Complete graph: Roadmap plus Mermaid views of the full parent hierarchy, ungrouped tickets, blocking DAG, and separate related edges. Include every node and blocking edge.
  • Named tickets: brief product context, one-hop Mermaid neighborhood, and the explanation for each ticket.

Report node totals and blocks, parent-child, and related counts for graph views. Label dependency-only BV edge counts as such. Keep the timeline phase-level; use several small flowcharts rather than one dense dependency graph. Attribute computed claims to BV and declared scope to the ticket.

Finish by confirming the selected coverage rule was met and tracker state was unchanged.

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.