Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create Linear tickets or GitHub issues following n8n conventions. Use when the user asks to create a ticket, file a bug, open an issue, or says /create-issue.
.claude/skills/n8n-io-n8n-create-issue/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 234% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 179% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 136% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 184% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 140% | 0% |
Create a Linear ticket or GitHub issue for: $ARGUMENTS
Write all titles and descriptions in ASD-STE100 Simplified Technical English: use short sentences, the active voice, and one instruction for each sentence.
Decide where the issue should be created based on user input:
Verify the Linear MCP is connected before proceeding.
Bug - followed by a description of the symptom (e.g., "Bug - Pin data not updating after workflow edit")Structure the description using markdown headers. Use the appropriate template:
For bugs:
markdown## Description [Clear explanation of the problem] ## Expected [What should happen] ## Actual [What happens instead] ## Attachments [Screenshots, videos, or screen recordings that illustrate the problem] ## Steps to reproduce 1. [Step-by-step reproduction] ## Additional context - n8n version: [version] - Database: [SQLite/PostgreSQL] - Hosting: [cloud/self-hosted]
For features / enhancements:
markdown## Goal [What this adds and why: the user problem it solves] ## Background [Current state and the gap, plus the technical context needed to plan the work: relevant constraints, prior findings, and links to any related investigation.] ## Scope [Concrete list of what changes. Name the files or areas to create or modify and any existing pattern to follow.] ## Acceptance criteria [Testable outcomes, including automated tests.] ## Out of scope [What this explicitly does not cover]
For tech debt:
markdown## Summary [What technical improvement is needed] ## Current state [What the code/system looks like today and why it's problematic] ## Proposed improvement [What the improved state should look like] ## Motivation [Why this matters — maintainability, performance, developer experience, etc.] ## Scope [What is included / excluded from this work]
For spikes / investigations:
markdown## Goal [What question(s) are we trying to answer] ## Context [Why this investigation is needed now] ## Questions 1. [Specific question to resolve] ## Expected output [What deliverable is expected: RFC, PoC, decision document, path matrix, etc.] ## Acceptance criteria [How we know the spike is done: each question answered, deliverable produced]
If the user provides screenshots, videos, or screen recordings:
)Always mention in the description when visual evidence was provided, even if it cannot be directly embedded.
| Value | Level | When to use | |-------|----------|-------------| | 4 | Low | Nice-to-have, no user impact | | 3 | Normal | Default — standard planned work | | 2 | High | Blocks other work or affects users significantly | | 1 | Urgent | Production-breaking, security vulnerability, data loss | | 0 | None | Not yet assessed |
Guardrails:
Guardrails:
Engineering (N8N), AI, NODES, Identity & Access (IAM), Catalysts (CAT), Lifecycle & Governance (LIGO), Cloud Platform, Docs (DOC)NODESAIApply labels from these groups as appropriate:
Type (pick one):
bug — something is brokenfeature — net-new capabilityenhancement — improvement to existing functionalitytech debt — internal quality improvementspike — time-boxed investigationdoc — documentation-only changeArea (pick if applicable):
frontend, backend, performance, testing, infra, DX, Security-TeamSource (pick if applicable):
Internal — created by team membersGitHub — originated from a GitHub issueSentry — originated from error monitoringZammad — originated from supportBucket (pick if applicable):
Credentials, Canvas/Node, RBAC, LangChain nodes, Form Trigger, etc.)Guardrails:
Triage: Pending, Triage: Complete, etc.) — these are managed by triage automationn8n@1.36.0, etc.) — these are managed by release automationdocs-automation labels — these are managed by docs automationOnly set an estimate if the user provides one or explicitly asks for one. Use t-shirt sizes:
| Size | Value | Approximate effort | |------|-------|--------------------| | XS | 1 | ≤ 1 hour | | S | 2 | ≤ 1 day | | M | 3 | 2–3 days | | L | 4 | 3–5 days | | XL | 5 | ≥ 6 days |
title: <title> team: <team name> description: <markdown description> priority: <priority number> state: <status name> labels: [<label names>]
Verify gh CLI is authenticated: gh auth status
The n8n GitHub issue tracker (n8n-io/n8n) is bug-only. Feature requests and questions are redirected to the community forum. Blank issues are disabled — the bug template must be used.
GitHub issues must follow the bug report template structure:
markdown### Bug Description [Clear explanation of the bug] ### Steps to Reproduce 1. [Step 1] 2. [Step 2] 3. [Step 3] ### Expected Behavior [What should happen] ### Debug Info [If available — output from Help > About n8n > Copy debug information] ### Operating System [e.g., macOS 14.2, Ubuntu 22.04] ### n8n Version [e.g., 1.72.1] ### Node.js Version [e.g., 20.11.0] ### Database SQLite / PostgreSQL ### Execution Mode main / queue ### Hosting n8n cloud / self hosted
Guardrails:
closed:incomplete-templateDo not manually apply labels when creating GitHub issues. The triage automation handles labeling:
triage:pending is auto-appliedstatus:in-linear is auto-applied when syncedn8n-io/n8n)gh:bash gh issue create --repo n8n-io/n8n --title "<title>" --body "$(cat <<'EOF' <body content> EOF )"
When both a Linear ticket and GitHub issue exist for the same problem:
https://linear.app/n8n/issue/<TICKET-ID> in the GitHub issue bodyIf the user creates one and mentions the other exists, offer to add the cross-link.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 9,464 | 10,763 | +14% | 1 | 1 | 0% | 1,388 | 4,636 | +234% | 0 | 0 | — |
case-02 | fail→fail | 11,741 | 9,839 | -16% | 1 | 1 | 0% | 1,847 | 3,428 | +86% | 0 | 0 | — |
case-03 | fail→pass | 10,862 | 17,132 | +58% | 1 | 1 | 0% | 1,757 | 4,907 | +179% | 0 | 0 | — |
case-04 | pass→fail | 7,432 | 25,113 | +238% | 1 | 1 | 0% | 1,362 | 7,697 | +465% | 0 | 0 | — |
case-05 | pass→pass | 7,872 | 22,660 | +188% | 1 | 1 | 0% | 1,257 | 5,389 | +329% | 0 | 0 | — |
case-06 | fail→fail | 8,736 | 19,080 | +118% | 1 | 1 | 0% | 1,167 | 6,147 | +427% | 0 | 0 | — |
case-07 | fail→pass | 14,488 | 11,047 | -24% | 1 | 1 | 0% | 2,014 | 4,753 | +136% | 0 | 0 | — |
case-08 | fail→pass | 11,686 | 16,793 | +44% | 1 | 1 | 0% | 1,702 | 4,838 | +184% | 0 | 0 | — |
case-09 | fail→pass | 13,021 | 6,551 | -50% | 1 | 1 | 0% | 1,630 | 3,915 | +140% | 0 | 0 | — |
case-10 | fail→pass | 12,186 | 7,125 | -42% | 1 | 1 | 0% | 1,032 | 4,059 | +293% | 0 | 0 | — |
case-11 | fail→pass | 11,266 | 10,369 | -8% | 1 | 1 | 0% | 1,618 | 4,898 | +203% | 0 | 0 | — |
case-12 | fail→fail | 7,939 | 11,316 | +43% | 1 | 1 | 0% | 1,012 | 5,028 | +397% | 0 | 0 | — |
case-13 | pass→pass | 10,724 | 7,585 | -29% | 1 | 1 | 0% | 1,496 | 4,043 | +170% | 0 | 0 | — |
case-14 | pass→pass | 7,928 | 6,249 | -21% | 1 | 1 | 0% | 1,242 | 3,878 | +212% | 0 | 0 | — |
case-15 | pass→pass | 9,227 | 14,844 | +61% | 1 | 1 | 0% | 1,354 | 4,922 | +264% | 0 | 0 | — |
case-16 | fail→fail | 7,562 | 17,710 | +134% | 1 | 1 | 0% | 1,110 | 5,997 | +440% | 0 | 0 | — |
case-17 | pass→pass | 12,424 | 8,384 | -33% | 1 | 1 | 0% | 1,602 | 4,192 | +162% | 0 | 0 | — |
case-18 | fail→pass | 8,182 | 23,234 | +184% | 1 | 1 | 0% | 754 | 5,232 | +594% | 0 | 0 | — |
case-19 | fail→pass | 5,962 | 12,184 | +104% | 1 | 1 | 0% | 905 | 5,149 | +469% | 0 | 0 | — |
case-20 | pass→pass | 6,117 | 4,383 | -28% | 1 | 1 | 0% | 810 | 3,474 | +329% | 0 | 0 | — |
case-21 | pass→pass | 7,059 | 3,960 | -44% | 1 | 1 | 0% | 932 | 3,451 | +270% | 0 | 0 | — |
case-22 | fail→pass | 8,290 | 6,151 | -26% | 1 | 1 | 0% | 1,345 | 3,804 | +183% | 0 | 0 | — |
case-23 | pass→pass | 18,645 | 12,020 | -36% | 1 | 1 | 0% | 3,453 | 5,369 | +55% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +39 percentage points is the difference between those two pass rates over the 22 comparable cases. 4 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.