rampstackco/claude-skills / skills/backlog-triage
backlog-triage
VerifiedTurn an inbox of raw requests (bug reports, feature asks, support escalations, feedback, incident follow-ups) into a ranked, deduplicated backlog where every item at the top meets the definition of ready, with recorded scores, merge links, and a written reason for every park and decline. Use this skill whenever the user wants to triage incoming work, groom or prune a backlog, merge duplicate tickets, score or rank requests, decide what the team works on next, or run a weekly triage session. Triggers on triage, groom the backlog, backlog grooming, prioritize the backlog, dedupe tickets, duplicate tickets, what should we work on next, inbox of bugs, feature requests pile, rank these, is this ready, backlog is too big, stale tickets, severity vs frequency. Also triggers when the user pastes a list of raw requests or bug reports and asks what to do with them, even if they never say the word triage.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 355 B |
| SKILL.md | skill md | 11.6 KB |
| references/aging-policy-guide.md | markdown | 3.3 KB |
| references/example-triage-session.md | markdown | 7.0 KB |
| references/intake-template.md | markdown | 3.2 KB |
| references/scoring-template.md | markdown | 3.4 KB |
| references/triage-checklist.md | markdown | 3.4 KB |
references/triage-checklist.md
View on GitHub# Triage Session Checklist
The runbook for the weekly triage session. Timebox: 45 to 60 minutes. Run it in the same slot every week so reporters know when their item will be looked at.
---
## Before the session (triage lead, 15 to 30 minutes)
- [ ] Pull every item received since the last session
- [ ] Pull every item past its aging threshold
- [ ] Pull every parked item whose review date has arrived
- [ ] Pull every "question sent" item that got an answer
- [ ] Write intake records for anything missing one
- [ ] Do a first dedupe pass: search by symptom, area, and wording; propose merges
- [ ] Mark each item with a likely type and the inputs still missing
- [ ] Check the current backlog size against the ceiling
- [ ] Share the list with attendees at least a few hours ahead
---
## Attendees
| Role | Why they are there |
|---|---|
| Triage lead (PM or BA) | Runs the session, owns the outcome, writes the decisions down |
| Engineer | Effort, feasibility, and "is this already fixed?" |
| Support or customer-facing lead | Frequency, reporter context, who is waiting on what |
| Designer (when the top of the queue is user-facing) | Whether a story is shaped enough to be ready |
Keep it to four or five people. Triage with ten attendees becomes a roadmap debate.
---
## Agenda
| Minutes | Step | Done when |
|---|---|---|
| 0 to 5 | Confirm proposed merges | Each merge accepted or split, reporter counts updated |
| 5 to 15 | Classify | Every item has a type, or a question for the reporter |
| 15 to 35 | Score | Every classified item has a score with inputs on the record |
| 35 to 45 | Rank and promote | Top-N ranked; each item in it passed its definition of ready |
| 45 to 50 | Park and decline | Every remaining item has a state, a reason, and a date where needed |
| 50 to 55 | Aging | Stale items closed or re-scored; backlog size checked against the ceiling |
| 55 to 60 | Assign follow-ups | Reporter replies and missing-field fixes have owners |
If the session runs out of time, stop at the step you are on. Carry the remainder to the top of next week's list. Do not skip the definition of ready to finish on time.
---
## During the session: rules
- [ ] No item is promoted without its type's definition-of-ready checklist from `ticket-authoring`
- [ ] No score is accepted without its inputs written on the item
- [ ] No item is parked without a reason and a review date
- [ ] No item is declined without a written reason
- [ ] Reporter count changes only through merges
- [ ] Disagreements on rank are settled by inputs, not by seniority. If inputs are missing, the item is "unscored," not ranked by argument.
---
## After the session (triage lead, within two working days)
- [ ] Post the triage summary (ranked top-N, merges, parks, declines, questions)
- [ ] Reply to every reporter whose item was merged, parked, or declined
- [ ] Send question-back messages for items that could not be classified or scored
- [ ] Hand promoted items to their owners, or fill remaining fields with `ticket-authoring`
- [ ] Update the backlog size count
---
## Signs the session is not working
- The same items appear every week with no state change
- The top-N changes completely each week (scoring inputs are not stable)
- Nothing is ever declined
- Engineers pull items from the top and immediately ask clarifying questions
- Reporters chase updates in direct messages because nobody replies after triage
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |