Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues.

MITAuto-check: notesDevelopment

Install Triage

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill triage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace triage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/productivity/claude-workflow-skills/skills/triage .claude/skills/triage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
triage
GitHub stars
2.8k
Token cost
~1.1k tokens
SKILL.md length
438 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues.

  • Works in 7 steps: Pre-flight check → Fetch all open issues → Classify each issue → …
  • The user says triage issues
  • SKILL.md covers Step 0: Pre-flight check, Step 1: Fetch all open issues, Step 2: Classify each issue and Step 3: Close invalid issues, plus 3 more sections
  • Calls gh, git and bash

What it does

Triage is an agent skill from jeremylongshore/tons-of-skills-marketplace. Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues. Use when the user says triage issues, validate issues, fix issues, or work through the backlog.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Issue triage. It works with GitHub and Git. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • The user says triage issues
  • Validate issues
  • Work through the backlog

Example prompts

  • “Use the triage skill to validate all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then…”
  • “/triage”

Requirements

  • Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash, Edit, Write

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Pre-flight check
  2. Fetch all open issues
  3. Classify each issue
  4. Close invalid issues
  5. Surface complex issues for planning
  6. Fix actionable issues
  7. Promote

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Glob
    • Grep
    • Bash
    • Edit
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Triage loads about 1.1k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 438 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Glob, Grep, Bash, Edit, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 438 words, ~1,142 tokens.

Download SKILL.mdSave it as .claude/skills/triage/SKILL.md (or your agent's skills folder).
name
triage
description
Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues. Use when the user says triage issues, validate issues, fix issues, or work through the backlog.
allowed-tools
Read, Glob, Grep, Bash, Edit, Write
disable-model-invocation
true

Triage

Project: !basename $(git rev-parse --show-toplevel 2>/dev/null) 2>/dev/null || basename $PWD Branch: !git branch --show-current 2>/dev/null || echo "unknown" Open issues: !gh issue list --state open --json number,title --jq '.[] | "#\(.number) \(.title)"' 2>/dev/null || echo "none" Last tag: !git describe --tags --abbrev=0 2>/dev/null || echo "none" Recent commits: !git log --oneline -5 2>/dev/null || echo "none"

Validates every open GitHub issue, closes those that are invalid, surfaces complex ones for planning discussion, then fixes and promotes all remaining actionable issues.

Step 0: Pre-flight check

bash
gh auth status 2>&1 || { echo "ERROR: gh is not authenticated. Run: gh auth login"; exit 1; }

Step 1: Fetch all open issues

bash
gh issue list --state open --limit 100 --json number,title,body,labels,createdAt \
  --jq '.[] | {number, title, labels: [.labels[].name], createdAt, body}'

Read the full body of any issues where context is needed:

bash
gh issue view <number> --json number,title,body,labels,comments

Also read the project files to understand current state before assessing anything:

  • README.md — stated purpose and feature set
  • CLAUDE.md — current status, known decisions, next steps

Step 2: Classify each issue

For every open issue, classify it as one of:

  • Invalid — already fixed, a duplicate, not reproducible, out of scope, or based on a misunderstanding. Evidence must be clear.
  • Complex — valid but requires significant design decisions, breaking changes, or multi-step implementation that warrants planning discussion before proceeding.
  • Actionable — valid, well-scoped, and fixable now without further input.

Build a classification table before taking any action:

#TitleClassificationReason
N...Invalid/Complex/Actionable...

Step 3: Close invalid issues

For each invalid issue, post a closing comment that explains why it is being closed, then close it:

bash
gh issue comment <number> --body "$(cat <<'EOF'
Closing as invalid: <specific reason — already fixed in <commit/PR>, duplicate of #N,
not reproducible because <evidence>, or out of scope because <reason>>.

<If already fixed: reference the commit or PR that resolved it.>
<If duplicate: reference the canonical issue.>
EOF
)"

gh issue close <number> --reason "not planned"

Use --reason "completed" if the issue was already resolved in code.

Step 4: Surface complex issues for planning

Stop and present complex issues to the user before proceeding. Format clearly:


Complex issues — planning needed before proceeding:

For each complex issue:

  • #N: <title>
    • Why it's complex: <design decision, breaking change, or scope concern>
    • Options to consider: <brief list of approaches>
    • Suggested next step: defer to backlog / spike / discuss now

Wait for the user's direction on each complex issue before moving to Step 5. If running non-interactively (no terminal), stop here and output the complex issues report.

bash
if [ ! -t 0 ]; then
  echo "Non-interactive mode: stopping after complex issue report. Review and re-run interactively."
  exit 0
fi
Show full SKILL.md (144 more words)Show less

Step 5: Fix actionable issues

Work through each actionable issue. For each one:

  1. Read the relevant source files before making any changes.

  2. Implement the fix — prefer the minimal correct change; don't refactor beyond the scope of the issue.

  3. Verify the fix with any available linting or syntax checks:

    bash
    bash -n <script.sh>        # syntax check for shell scripts
    markdownlint '**/*.md'     # markdown linting
  4. Stage the change:

    bash
    git add -u

Record each fix with its issue number so the commit and PR can reference them.

Step 6: Promote

Once all actionable issues are fixed, run:

text
/promote

The promote skill will commit, push, create and merge a PR (referencing fixed issue numbers via Closes #N in the commit message), tag a release, and clean up.

When composing the commit message for the promote step, include Closes #N for every issue fixed in Step 5.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/productivity/claude-workflow-skills/skills/triage of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Triage this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.1kAutomated safety check: NotesMIT
Pre-Release PR Triagejamiepine/voicebox57k—~3.1kAutomated safety check: PassMIT
TiXL Ticket Processortixl3d/tixl5.1k—~2.6kAutomated safety check: PassMIT
RTK Issue Triagertk-ai/rtk83k—~3kAutomated safety check: NotesApache-2.0
PR Triagertk-ai/rtk83k—~2.5kAutomated safety check: NotesApache-2.0
Read-Only GitHub Triagecode-yeongyu/oh-my-openagent70k—~4.3kAutomated safety check: PassCustom licence

Similar skills

  • Pre-Release PR Triage

    jamiepine/voicebox

    Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.

    57k GitHub stars~3.1k tokensUpdated 4 days ago
    DevelopmentAuto-check passed
  • Works through the In progress column of the TiXL road-map board unattended, turning simple tickets into git stashes and writing plans for the rest under .agentic/Plans.

    5.1k GitHub stars~2.6k tokensUpdated today
    DevelopmentAuto-check passed
  • Audits open GitHub issues, categorizes them, flags duplicates and linked PRs in three phases, with optional deep analysis and comments posted only after validation.

    83k GitHub stars~3k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • PR Triage

    rtk-ai/rtk

    Audits a repository's open pull requests, deep-reviews chosen ones and drafts review comments that are only posted after you approve them.

    83k GitHub stars~2.5k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Read-Only GitHub Triage

    code-yeongyu/oh-my-openagent

    Fans out one background subagent per open GitHub issue or pull request to write an evidence-backed report, never commenting, closing or merging anything.

    70k GitHub stars~4.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Setup Matt Pocock Skills

    vinvcn/mattpocock-skills-zh-CN

    为此仓库配置 engineering skills:设置其 issue tracker、triage labels 词汇与 domain docs 布局。在首次使用其他 engineering skills 前运行一次。

    4.7k GitHub stars~1.1k tokensUpdated 3 days ago
    DevelopmentAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Triage

What does Triage do?

Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues. Triage is an agent skill from jeremylongshore/tons-of-skills-marketplace. Validates all open GitHub issues, closes invalid ones with documentation, flags complex ones for planning discussion, then fixes and promotes remaining issues.

When should I use Triage?

Triage fits situations like: the user says triage issues; validate issues; work through the backlog.

How do I install Triage in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill triage -a claude-code`. Or copy the skill folder (plugins/productivity/claude-workflow-skills/skills/triage in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/triage in your project. Claude Code loads it when a task matches its description.

How do I install Triage in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill triage -a codex`. Or copy the skill folder (plugins/productivity/claude-workflow-skills/skills/triage in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/triage in your project. Codex loads it when a task matches its description.

Can I use Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/triage, .gemini/skills/triage, .github/skills/triage and .opencode/skills/triage in your project.

What does Triage need to run?

Going by SKILL.md and its folder, Triage needs the command-line tools its instructions call (gh, git and bash). Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash, Edit, Write.

Does Triage access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Triage safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Triage use?

Triage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Triage use?

About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Triage?

Skills that share tags, products or a category with Triage: Pre-Release PR Triage (jamiepine/voicebox, 57k stars), TiXL Ticket Processor (tixl3d/tixl, 5.1k stars), RTK Issue Triage (rtk-ai/rtk, 83k stars) and PR Triage (rtk-ai/rtk, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Triage?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.