Agent skill

Triage

by TalAter in TalAter/annyang

Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

MITAuto-check: notesAI & LLM Engineering

Install Triage

skills CLI
$ npx skills add TalAter/annyang --skill triage -a claude-code

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

GitHub CLI
$ gh skill install TalAter/annyang 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/TalAter/annyang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/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
6.8k
Token cost
~810 tokens
SKILL.md length
415 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

  • Works in 5 steps: If given an issue number: fetch it with… → If asked to list issues: use gh issue… → Read the issue and all comments… → …
  • Tasks that involve Speech recognition and synthesis
  • SKILL.md covers How to post as the bot, Workflow, Closing reasons and Tone, plus 2 more sections
  • Calls gh

What it does

Triage is an agent skill from TalAter/annyang. Triage and close GitHub issues on TalAter/annyang

Its SKILL.md is about 810 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 AI & LLM Engineering, covering Speech recognition and synthesis and Issue triage. It works with GitHub. The repository describes itself as: 💬 Speech recognition for your site. The licence is MIT.

When your agent uses it

  • Tasks that involve Speech recognition and synthesis
  • Tasks that involve Issue triage

Example prompts

  • “/triage”

Requirements

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

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. If given an issue number: fetch it with gh issue view --repo TalAter/annyang --comments (this read-only call can use regular gh)
  2. If asked to list issues: use gh issue list --repo TalAter/annyang (read-only, regular gh is fine). To sort by newest, use -S…
  3. Read the issue and all comments carefully before deciding on an action
  4. Present your proposed comment and action to the user before posting. Wait for approval.
  5. Post using ./scripts/gh-bot once approved

What it can do on your machine

Read from SKILL.md and the folder at commit bcf5fcc. 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:

    • Bash
    • Read
    • Grep
    • Glob
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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 810 tokens when it runs. Until then it costs about 14 tokens; SKILL.md has 415 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~14
When it runs · the whole SKILL.md, loaded when a task matches
~810

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: Bash, Read, Grep, Glob, Agent

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 TalAter/annyang at commit bcf5fcc, republished under its MIT licence (© TalAter). 415 words, ~810 tokens.

Download SKILL.mdSave it as .claude/skills/triage/SKILL.md (or your agent's skills folder).
name
triage
description
Triage and close GitHub issues on TalAter/annyang
allowed-tools
Bash, Read, Grep, Glob, Agent
user-invocable
true
argument-hint
issue-number or "list"

GitHub Issue Triage for TalAter/annyang

You are helping triage and close GitHub issues on the TalAter/annyang repository.

How to post as the bot

All gh commands that interact with issues MUST use the bot script so comments are posted as annyang-triage[bot], not as the repo owner:

bash
./scripts/gh-bot issue comment <number> --repo TalAter/annyang --body "<message>"
./scripts/gh-bot issue close <number> --repo TalAter/annyang
./scripts/gh-bot issue close <number> --repo TalAter/annyang --reason "not planned"

Never use bare gh for issue comments or closes — always use ./scripts/gh-bot.

Workflow

  1. If given an issue number: fetch it with gh issue view <number> --repo TalAter/annyang --comments (this read-only call can use regular gh)
  2. If asked to list issues: use gh issue list --repo TalAter/annyang (read-only, regular gh is fine). To sort by newest, use -S "sort:created-desc". Note: gh issue list has no --sort flag — use the -S search query instead.
  3. Read the issue and all comments carefully before deciding on an action
  4. Present your proposed comment and action to the user before posting. Wait for approval.
  5. Post using ./scripts/gh-bot once approved

Closing reasons

  • gh issue close — default, resolved/completed
  • gh issue close --reason "not planned" — out of scope, won't fix, not a bug

Choose the appropriate reason. Most stale or out-of-scope issues should use "not planned".

Show full SKILL.md (227 more words)Show less

Tone

These are real people who took time to file issues. Be kind, patient, and helpful.

  • Keep comments to 1-3 sentences. Concise but warm.
  • Never dismissive. Even if the issue is out of scope or a misunderstanding, acknowledge what they were trying to do.
  • Explain "why" when closing. When something is outside annyang's control (browser behavior, platform limitations, third-party APIs), briefly explain why so the user learns something useful.
  • Don't pile on. If the issue was already answered in the comments, just close it — no need to add another comment.
  • Be helpful with links. When pointing to another issue or resource, briefly say why it's relevant.
  • End positively when natural. "Good luck with your project!" or "Hope that helps!" — but only when it fits. Don't force it.
Do NOT
  • Use phrases like "this is a support question, not a bug" — it sounds dismissive
  • Be condescending about the user's level of knowledge
  • Apologize excessively — one brief acknowledgment is enough
  • Write walls of text — if it needs more than 3 sentences, something is wrong
  • Close without a comment unless the issue was already fully answered in existing comments

Formatting

Always render issue numbers as clickable links: [#123](https://github.com/TalAter/annyang/issues/123). This applies everywhere — proposals, summaries, references within comments, conversation text. Never write a bare #123.

After completing actions

Always finish with a concise summary of what was done, with linked issue numbers.

© TalAter, 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 .claude/skills/triage of TalAter/annyang.

Open the folder on GitHubat commit bcf5fcc

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 skillTalAter/annyang6.8k—~810Automated safety check: NotesMIT
AI Project Copilotsun461941-hub/ai-project-copilot100—~3kAutomated safety check: PassMIT
Triaging Issuespytorch/pytorch104k—~4.2kAutomated safety check: PassCustom licence
Vllm Daily PR Issue Trackerascend-ai-coding/awesome-ascend-skills174—~731Automated safety check: PassNone
Issue Triageintel/torch-xpu-ops115—~2.5kAutomated safety check: PassApache-2.0
Vlog Auto Editznyupup/ai-video-editing-skill148—~6.8kAutomated safety check: PassMIT

Similar skills

  • AI Project Copilot

    sun461941-hub/ai-project-copilot

    A skill your agent uses to turn an AI idea or existing repository into a credible open-source product and to run evidence-first repository engineering across codebase discovery, context-efficient…

    100 GitHub stars~3k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Triaging Issues

    pytorch/pytorch

    Triages GitHub issues by routing to oncall teams, applying labels, and closing questions.

    104k GitHub stars~4.2k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Vllm Daily PR Issue Tracker

    ascend-ai-coding/awesome-ascend-skills

    Track daily PRs and Issues from vllm-project/vllm and vllm-project/vllm-ascend, filter by model (DeepSeek/Qwen/GLM/MiniMax/Kimi) and tech topics (PD disaggregation, MTP, quantization, graph mode…

    174 GitHub stars~731 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Issue Triage

    intel/torch-xpu-ops

    Official

    Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops.

    115 GitHub stars~2.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Vlog Auto Edit

    znyupup/ai-video-editing-skill

    AI Agent自动剪辑旅行Vlog的完整工作流。从原始素材到成品视频,系统级只需ffmpeg,其余在Python venv内完成。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所)

    148 GitHub stars~6.8k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed
  • Scholar Open

    joshzyj/open-scholar-skill

    Implement open science practices for a social science study.

    168 GitHub stars~14k tokensUpdated 20 days ago
    Research & ScienceAuto-check passed

Works with

Questions about Triage

What does Triage do?

Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang. Triage is an agent skill from TalAter/annyang.

When should I use Triage?

Triage fits situations like: tasks that involve Speech recognition and synthesis; tasks that involve Issue triage.

How do I install Triage in Claude Code?

Run `npx skills add TalAter/annyang --skill triage -a claude-code`. Or copy the skill folder (.claude/skills/triage in TalAter/annyang) 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 TalAter/annyang --skill triage -a codex`. Or copy the skill folder (.claude/skills/triage in TalAter/annyang) 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 TalAter/annyang --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). Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob, Agent.

Does Triage access the network?

SKILL.md contains no URLs. Its commands use gh, 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 810 tokens (SKILL.md is roughly 3.2k 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: AI Project Copilot (sun461941-hub/ai-project-copilot, 100 stars), Triaging Issues (pytorch/pytorch, 104k stars), Vllm Daily PR Issue Tracker (ascend-ai-coding/awesome-ascend-skills, 174 stars) and Issue Triage (intel/torch-xpu-ops, 115 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Triage?

TalAter (a GitHub user) maintains it in TalAter/annyang, which has 6,817 GitHub stars. The repository was last updated on October 6, 2026.

Source: TalAter/annyang on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.