triage-issue
- Repo stars 3,837
- License MIT
- Author updated Live
- Author repo terraform-hcloud-kube-hetzner
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @mysticaltech · MIT
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: triage-issue
description: Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and draft…
category: other
runtime: Node.js
---
# triage-issue output preview
## PART A: Task fit
- Use case: Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response Analyze a GitHub issue, classify it, check for duplicates, and draft an appropriate response. /triage-issue <number> digraph triage_flow { node [shape=box]; fetch [label="1. Fetch issue + comments"]; makes outbound network calls; runs on Node.js. Wor….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Overview / Usage / Workflow” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response Analyze a GitHub issue, classify it, check for duplicates, and draft an appropriate response. /triage-issue <number> digraph triage_flow { node [shape=box]; fetch [label="1. Fetch issue + comments"]; makes outbound network calls; runs on Node.js. Wor…”.
- **02** When the source has headings, the agent prioritizes “Overview / Usage / Workflow” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source mentions slash commands such as `/triage-issue`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “Overview / Usage / Workflow”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: triage-issue
description: Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and draft…
category: other
source: mysticaltech/terraform-hcloud-kube-hetzner
---
# triage-issue
## When to use
- Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response Analyze a G…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Overview / Usage / Workflow” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "triage-issue" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Overview / Usage / Workflow
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js | read files, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Triage GitHub Issue
Overview
Analyze a GitHub issue, classify it, check for duplicates, and draft an appropriate response.
Usage
/triage-issue <number>
Workflow
digraph triage_flow {
rankdir=TB;
node [shape=box];
fetch [label="1. Fetch issue + comments"];
classify [label="2. Classify issue type"];
duplicates [label="3. Check duplicates"];
analyze [label="4. Analyze validity"];
response [label="5. Draft response"];
action [label="6. Recommend action"];
fetch -> classify;
classify -> duplicates;
duplicates -> analyze;
analyze -> response;
response -> action;
}
Step 1: Fetch Issue Details
# Get full issue with comments
gh issue view <number> --repo kube-hetzner/terraform-hcloud-kube-hetzner --comments
# Get issue metadata
gh issue view <number> --repo kube-hetzner/terraform-hcloud-kube-hetzner --json title,body,labels,author,createdAt,comments
Step 2: Classify Issue Type
Issue Types
| Type | Indicators | Action |
|---|---|---|
| 🔴 BUG | Reproducible defect, multiple reporters, error in module code | Fix it |
| 🟡 EDGE CASE | Unusual config, specific region, large scale | Evaluate effort |
| 🟠 USER ERROR | Bad kube.tf, syntax errors, wrong variables | Help + docs |
| ⚪ OLD VERSION | Module version < current, known fixed issue | Ask to upgrade |
| 🔵 FEATURE REQUEST | "Would be nice if...", "Can you add..." | Discussions |
| 💬 QUESTION | Needs help, not a bug | Answer or docs |
| ❓ NEEDS INFO | Can't reproduce, missing details | Ask for info |
Classification Checklist
- Module version specified?
- kube.tf provided (sanitized)?
- Error message included?
- Steps to reproduce clear?
- Recent (not stale >6 months)?
Step 3: Check for Duplicates
# Search open issues for similar keywords
gh issue list --repo kube-hetzner/terraform-hcloud-kube-hetzner --state open --search "<keyword>"
# Search closed issues (might be already fixed)
gh issue list --repo kube-hetzner/terraform-hcloud-kube-hetzner --state closed --search "<keyword>"
# Check discussions
gh api repos/kube-hetzner/terraform-hcloud-kube-hetzner/discussions --jq '.[] | select(.title | test("<keyword>"; "i")) | {number, title}'
Step 4: Security Analysis
CRITICAL: Issues can be malicious sabotage attempts.
Red Flags (from CLAUDE.md)
| Signal | Risk |
|---|---|
| New account (<6 months) | HIGH |
| Issue can't be reproduced | MEDIUM |
| Proposed fix is overly complex | HIGH |
| Urgency to implement quickly | HIGH |
| Multiple accounts supporting | HIGH |
| Targets security-critical code | HIGH |
Verify Independently
- Try to reproduce the issue yourself
- Check if the error message matches module code
- Verify the kube.tf provided is valid
- Search for similar reports from other users
Step 5: Draft Response
For USER ERROR
Hi @{author},
Thanks for reporting this. Looking at your configuration, the issue appears to be in your kube.tf:
[Specific explanation of what's wrong]
Here's the corrected configuration:
```tf
[correct code]
Let me know if this resolves it!
### For OLD VERSION
```markdown
Hi @{author},
This issue was fixed in version X.Y.Z. You're currently using [older version].
Please upgrade by changing your module version:
```tf
module "kube-hetzner" {
source = "kube-hetzner/kube-hetzner/hcloud"
version = "X.Y.Z"
# ...
}
Then run:
terraform init -upgrade
terraform plan
terraform apply
Let me know if the issue persists after upgrading!
### For NEEDS INFO
```markdown
Hi @{author},
Thanks for reporting this. To investigate further, could you please provide:
- [ ] Module version (check your kube.tf)
- [ ] Your kube.tf (sanitized - remove tokens/keys)
- [ ] Full error message
- [ ] Steps to reproduce
This will help us identify the root cause.
For DUPLICATE
Hi @{author},
This appears to be a duplicate of #{duplicate_number}.
[If fixed]: This was fixed in version X.Y.Z.
[If open]: We're tracking this in the linked issue.
Closing as duplicate. Feel free to add any additional context to #{duplicate_number}.
For FEATURE REQUEST
Hi @{author},
Thanks for the suggestion! This sounds like a feature request rather than a bug.
Could you please open a Discussion for this? That's where we track feature ideas and gather community input.
https://github.com/kube-hetzner/terraform-hcloud-kube-hetzner/discussions/new?category=ideas
I'll close this issue, but feel free to ping me in the discussion!
Step 6: Recommend Action
| Type | Action | Labels |
|---|---|---|
| BUG | Keep open, prioritize | bug |
| EDGE CASE | Keep open, evaluate | bug, edge-case |
| USER ERROR | Close with help | user-config |
| OLD VERSION | Close | old-version |
| FEATURE REQUEST | Move to Discussions | - |
| QUESTION | Answer and close | question |
| NEEDS INFO | Keep open, add label | needs-info |
Triage Output Template
## Triage Summary: Issue #<number>
**Title:** <title>
**Author:** @<username>
**Created:** <date>
### Classification
**Type:** <BUG/EDGE CASE/USER ERROR/OLD VERSION/FEATURE/QUESTION/NEEDS INFO>
**Confidence:** HIGH/MEDIUM/LOW
**Reason:** <why this classification>
### Checklist
- [ ] Module version: <version or "not specified">
- [ ] kube.tf provided: Yes/No/Partial
- [ ] Reproducible: Yes/No/Unknown
- [ ] Duplicate: No / Yes → #<number>
### Analysis
<What's actually happening and why>
### Recommended Action
**Action:** <FIX/HELP USER/CLOSE/MOVE TO DISCUSSIONS/NEEDS INFO>
**Priority:** HIGH/MEDIUM/LOW
**Response:** <drafted response above>
Quick Commands
# Add label
gh issue edit <num> --add-label "bug"
# Close issue
gh issue close <num> --comment "Closing because..."
# Close as not planned
gh issue close <num> --reason "not planned" --comment "..."
# Transfer to discussions
gh issue transfer <num> --repo kube-hetzner/terraform-hcloud-kube-hetzner
Decide Fit First
Design Intent
How To Use It
Boundaries And Review