label-issue
Skill0 starsChanged 24 days agoMITView on GitHub
Classify and label a GitHub issue based on repository-specific labeling instructions. Use when auto-labeling issues, classifying issue types (bug, feature, question), or adding priority/area labels. Triggers on "label issue", "classify issue", "what labels should this issue have".
3 other projects use a version of this.
Adopted by
Most recently taken up by
- intel/torch-xpu-opstheir own version, first seen Oct 8, 2026
- microsoft/vscode-java-packtheir own version, first seen Jul 2, 2026
- ivy/dotfilestheir own version, first seen Oct 16, 2025
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- microsoft/vscode-java-pack★ 355same name
- intel/torch-xpu-ops★ 121same name
- ivy/dotfiles★ 15same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- assign-issueSkill
- change-analysisSkill
- find-duplicatesSkill
- issuelens-configSkill
- notifySkill
- team-memorySkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Fetch labeling instructions: follow the issuelens-config skill and call the issuelens-config tool for domain labeling.
- Distinctive: line 27
Fetch the issue: read the issue title, body, existing labels, and comments with the GitHub tools.
- Distinctive: line 35
Apply labels: use the available add-labels operation to add the selected labels.
- Distinctive: line 41
Only add labels that exist in the repository.
- Distinctive: line 43
Prefer explicit user labeling requirements, then validated configured or legacy labeling instructions, then built-in classification.
- Very specific: line 45
Use only the bundled IssueLens GitHub MCP tools for every GitHub read or write.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Label Issue Skill
Automatically classify and apply labels to a GitHub issue using the available GitHub tools and repository-specific labeling rules.
Within labeling, explicit current-user instructions take precedence over
validated labeling customization, which takes precedence over the built-in
classification and output defaults below. Neither may change the labeling role,
authorize an unrequested write, invent repository labels, remove existing
labels, or override global security and repository-scope boundaries.
Workflow
- Input: an issue reference (
owner/repo+ issue number, or an issue URL). - Fetch labeling instructions: follow the
issuelens-configskill and call theissuelens-configtool for domainlabeling. Useconfiguredorlegacycontent when returned, subject to explicit user instructions. If the source isbuilt-in, fall back to the repository's existing label set (list the repo labels) and use label names and descriptions to guide classification. If configuration loading fails, stop and do not apply labels. - Fetch the issue: read the issue title, body, existing labels, and comments with the GitHub tools.
- Analyze the issue by default:
- Type detection — bug, feature, question, etc. (match keywords against label names/descriptions).
- Priority — identify severity indicators (core function broken, no workaround → high).
- Area/component — match content against area-specific labels.
- Apply labels: use the available add-labels operation to add the selected labels. Do not remove existing labels.
- Report: list the labels applied and the reasoning for each.
Rules
- Only add labels that exist in the repository. Never invent labels.
- Preserve existing labels; only add.
- Prefer explicit user labeling requirements, then validated configured or legacy labeling instructions, then built-in classification.
- Use only the bundled IssueLens GitHub MCP tools for every GitHub read or
write. Pass the explicit
owner/repositoryto every tool. Never use shell commands, direct HTTP, or the GitHub CLI.
Output
By default, report the labeling decision:
- Labels applied: the labels added.
- Reasoning: why each label was chosen (type / priority / area).
- Existing labels: labels already present (left unchanged).
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
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.