agentleFS
Sign inStart free
ivyivy/dotfiles/.claude/skills/label-issue/SKILL.md

label-issue

Skill15 starsChanged 13 months agoISCView on GitHub

Use when labeling GitHub issues or triaging the backlog. Applies the project's label taxonomy from docs/labels.md.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. microsoft/vscode-java-pack★ 355same name
    2. intel/torch-xpu-ops★ 121same name
    3. microsoft/IssueLens★ 0same 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 repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read @docs/labels.md for the full taxonomy.

    line 24
  2. Distinctive:

    When labeling specific issues (1-3), apply immediately after showing the table.

    line 76
  3. Distinctive:

    When labeling all or unlabeled, present the full table first and wait for user confirmation before applying.

    line 78
  4. Distinctive:

    Do NOT remove existing valid labels.

    line 86

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Label Issue

Apply labels to GitHub issues per the taxonomy in docs/labels.md.

Arguments

local /label-issue

Label Reference

Read @docs/labels.md for the full taxonomy. Quick summary:

GroupLabels
Priority (pick one)p0:now, p1:soon, p2:later, p3:someday
Readiness (pick one)for:agent, for:human
Area (pick one)area:claude, area:tmux, area:nvim, area:shell, area:git, area:mise, area:renovate, area:os
Type (optional)type:feature, type:bug, type:chore, type:workflow, type:security, type:test
Status (optional)blocked

Instructions

1. Determine scope

Parse arguments to decide what to label:

  • Issue numbers (#123, #456) — label those specific issues
  • all — triage all open issues
  • unlabeled — find and triage open issues missing labels
  • No arguments — default to unlabeled

2. Fetch issues

# Specific issues
gh issue view 123 --json number,title,body,labels

# All open
gh issue list --state open --json number,title,labels --limit 200

# Unlabeled (filter client-side)
gh issue list --state open --json number,title,body,labels --limit 200
# then filter to issues missing priority OR readiness OR area labels

3. Analyze each issue

For each issue, determine:

  1. Priority — Is it blocking (p0:now)? Wanted soon (p1:soon)? Backlog (p2:later)? Wishlist (p3:someday)?
  2. Readiness — Is the issue fully specified enough for an agent to execute autonomously (for:agent)? Or does it need human judgment, hardware access, or interactive work (for:human)?
  3. Area — What part of the stack does it touch? Match against area labels. Use the issue title prefix as a strong hint (e.g., claude(statusline): → area:claude, tmux: → area:tmux).
  4. Type — If not obvious from context, assign one. Feature requests → type:feature, broken things → type:bug, etc.

4. Present recommendations

For each issue, show the proposed labels in a table:

| # | Title | Priority | Readiness | Area | Type |

When labeling specific issues (1-3), apply immediately after showing the table.

When labeling all or unlabeled, present the full table first and wait for user confirmation before applying.

5. Apply labels

gh issue edit 123 --add-label "p2:later" --add-label "for:agent" --add-label "area:claude" --add-label "type:feature"

Do NOT remove existing valid labels. Only add missing ones.

6. Summary

Report what was labeled:

  • Count of issues labeled
  • Any issues skipped (already fully labeled, or couldn't determine labels)

Examples

/label-issue #203                → label one issue
/label-issue #199 #200 #201     → label specific issues
/label-issue unlabeled           → find and triage unlabeled issues
/label-issue all                 → review and label all open issues
/label-issue                     → same as unlabeled

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free