borghei/Claude-Skills / project-management/execution/issue-triage
issue-triage
VerifiedMove engineering issues and external PRs through a triage state machine and write agent-ready briefs. Use when clearing a triage queue, deciding if a report is real or wanted, or handing an issue to a coding agent.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.4 KB |
| assets/agent_brief_template.md | markdown | 2.1 KB |
| assets/label_scheme_template.md | markdown | 2.7 KB |
| assets/out_of_scope_entry_template.md | markdown | 1.6 KB |
| assets/sample_agent_brief_clean.md | markdown | 2.6 KB |
| assets/sample_agent_briefs.json | config | 2.8 KB |
| assets/sample_triage_history.json | config | 3.7 KB |
| assets/sample_triage_history_clean.json | config | 3.4 KB |
| assets/triage_notes_template.md | markdown | 2.1 KB |
| references/agent-briefs.md | markdown | 10.3 KB |
| references/evidence-and-out-of-scope.md | markdown | 9.2 KB |
| references/state-machine-and-labels.md | markdown | 10.4 KB |
| scripts/agent_brief_linter.py | script | 10.1 KB |
| scripts/triage_state_validator.py | script | 12.6 KB |
assets/triage_notes_template.md
View on GitHub# Triage Notes Templates
Three comment shapes cover almost every triage outcome. Each one records what
is already settled so the next session (or the next maintainer) never re-asks.
## 1. Needs-info notes (state:needs-info)
```markdown
## Triage notes
**Established so far:**
- <fact confirmed from the report, logs, or our own check>
- <what we tried and what happened, e.g. "could not reproduce on 4.2.1 with default config">
**What we need from you:**
1. <one specific question the reporter can answer in a sentence or a paste>
2. <a second question only if it changes the decision>
**What happens next:** once you reply, this goes back into the triage queue.
If there is no reply by <date = nudge window + close window>, it will be closed
as stale; replying reopens it.
```
Questions must be answerable without guessing what we mean. "Please provide
more information" is never acceptable; "Which version does `app --version`
print, and does the crash happen with an empty project?" is.
## 2. Duplicate closure (state:duplicate)
```markdown
Closing as a duplicate of <#canonical>, which tracks the same root cause:
<one sentence naming the shared symptom or concept>. Anything new in this
report (<the extra detail, if any>) has been copied there. Follow
<#canonical> for progress.
```
## 3. Out-of-scope closure (state:out-of-scope)
```markdown
Thanks for the detailed request. This falls outside what the project will
take on: <one-sentence durable reason>. The full reasoning lives in the
out-of-scope register under `<concept-name>`, and this issue has been added
to its prior requests so the decision stays findable.
```
## 4. Already-implemented closure (state:already-implemented)
```markdown
Good news: this already exists. <Where it lives and how to reach it, in user
terms, e.g. "Reports > Export > CSV" or "`app export --csv`">. If it does not
cover your case, reply with what is missing and we will re-triage.
```
Do not add already-implemented items to the out-of-scope register; that
register is only for rejected requests, and mixing the two poisons future
prior-rejection checks.
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 |