New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Task Triage

by suyuan2022 in suyuan2022/suyuan-skill

Task triage with position-based thinking. An agent skill from suyuan2022/suyuan-skill.

MITAuto-check passed

Install Task Triage

skills CLI
$ npx skills add suyuan2022/suyuan-skill --skill task-triage -a claude-code

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

GitHub CLI
$ gh skill install suyuan2022/suyuan-skill task-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/suyuan2022/suyuan-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/task-triage .claude/skills/task-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
task-triage
GitHub stars
308
Token cost
~1.1k tokens
SKILL.md length
558 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Task triage with position-based thinking. An agent skill from suyuan2022/suyuan-skill.

  • Works in 6 steps: Positional Value (Does this make your… → Only-You (Must YOU do this by hand?) → Compound Returns (One-time drain or… → …
  • Evaluating new tasks
  • SKILL.md covers Core Logic, Scoring System (5 positive + 1…, Verdict and Output Format, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Task Triage is an agent skill from suyuan2022/suyuan-skill. Task triage with position-based thinking. 5+1 scoring dimensions (15 max + -3 penalty). Helps you decide whether a task is worth doing, and whether YOU should be the one doing it. Use when evaluating new tasks, prioritizing your backlog, or deciding what to cut.

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.

The repository describes itself as: Claude Code Skills by Suyuan — AI-native productivity tools for real practitioners. The licence is MIT.

When your agent uses it

  • Evaluating new tasks
  • Prioritizing your backlog
  • Deciding what to cut

Example prompts

  • “/task-triage”

Workflow steps

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

  1. Positional Value (Does this make your position stronger?)
  2. Only-You (Must YOU do this by hand?)
  3. Compound Returns (One-time drain or lasting payoff?)
  4. Cost of Not Doing (How bad is it if you cut this?)
  5. Visibility (Can the right people see it?)
  6. Tail Cost (What price do you pay AFTER doing it?)

What it can do on your machine

Read from SKILL.md and the folder at commit 423473d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Task Triage loads about 1.1k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 558 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
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 passed

The automated check found no risky patterns in SKILL.md.

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 suyuan2022/suyuan-skill at commit 423473d, republished under its MIT licence (© suyuan2022). 558 words, ~1,099 tokens.

Download SKILL.mdSave it as .claude/skills/task-triage/SKILL.md (or your agent's skills folder).
name
task-triage
description
Task triage with position-based thinking. 5+1 scoring dimensions (15 max + -3 penalty). Helps you decide whether a task is worth doing, and whether YOU should be the one doing it. Use when evaluating new tasks, prioritizing your backlog, or deciding what to cut.

Task Triage

Your problem isn't a lack of ability — it's too many things on the plate and doing everything yourself. This skill helps you intercept before you take on low-value work, or see clearly what to offload after you already have.

Core Logic

First principle: your time and attention are the scarcest resources. Every low-value task you accept is a high-value task you reject.

  • What determines your value isn't how much you do, but what position you hold (Sun Tzu — positional advantage)
  • Spending time on work anyone could do dilutes your irreplaceability (Adam Smith — market pricing)
  • Working too smoothly and quietly = zero visibility (Drucker — knowledge worker's dilemma)

Scoring System (5 positive + 1 negative dimension)

1. Positional Value (Does this make your position stronger?)
  • 3 — Directly builds or reinforces your decision-making authority, architectural ownership, or irreplaceability
  • 2 — Indirectly related, accumulates capability or relationships needed for your position
  • 1 — Maintenance work — losing points if not done, but no gain if done
  • 0 — Completely unrelated to your core positioning
2. Only-You (Must YOU do this by hand?)
  • 3 — Only you can do it: unique knowledge, unique judgment, unique relationships
  • 2 — You're best, but someone else could reach 70% with some guidance
  • 1 — Anyone could do roughly the same, you're just convenient
  • 0 — Anyone can do it / AI can handle it directly
3. Compound Returns (One-time drain or lasting payoff?)
  • 3 — Do once, benefit for a long time: skill-ification, architecture design, relationship building, workflow creation
  • 2 — Medium-term returns, sustained value for weeks
  • 1 — Short-term one-off, done and forgotten
  • 0 — Pure drain, time spent with nothing to show
4. Cost of Not Doing (How bad is it if you cut this?)
  • 3 — Direct damage: client loss, system crash, missing an irreversible window
  • 2 — Delays other critical items
  • 1 — Some impact but survivable
  • 0 — Nobody notices if you don't do it
5. Visibility (Can the right people see it?)
  • 3 — Output directly perceived by decision-makers / external market
  • 2 — Visible within team, builds professional reputation
  • 1 — Only you and direct collaborators know
  • 0 — Heads-down grind, invisible even when done
Show full SKILL.md (216 more words)Show less
6. Tail Cost (What price do you pay AFTER doing it?)

Opportunity cost: doing A means no time for B. Maintenance cost: you have to keep feeding it. Attention black hole: once you start, you can't stop.

  • 0 — Clean cut, done is done, no follow-up resources needed
  • -1 — Occasional maintenance/follow-up needed, but manageable
  • -2 — Continuously drains attention, or squeezes out time for higher-value work
  • -3 — Generates more tasks after completion, triggers chain reactions, or creates an attention black hole (scrolling feeds, joining groups — once started, can't stop)

Verdict

ScoreVerdictAction
12-15🔴 Your workPrioritize, do it yourself, make sure the right people see the output
9-11🟡 Worth doingDo it, but think about which parts to delegate
6-8🟢 DelegateHand off to colleagues / AI / outsource, you review at most
0-5⚪ CutSeriously consider not doing it. The courage to say no is rarer than the ability to finish

Output Format

For each task evaluated:

【Task】XXX
Position X | Only-You X | Compound X | Cost X | Visibility X | Tail X → Net XX
Verdict: 🔴/🟡/🟢/⚪
One-liner: (Why this score — key reasoning)
Suggestion: (Do / delegate / cut / how to boost the score)

Score Boosters

If a task scores low but you must do it anyway, think about how to boost the score:

  • Low visibility → Write a recap after completion so decision-makers see it (+visibility)
  • Only-You=0 → Do it this time but teach someone else, so next time you don't have to (+compound)
  • Position=0 → Can you establish a new information node while doing it? (+position)

© suyuan2022, 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 task-triage of suyuan2022/suyuan-skill.

Open the folder on GitHubat commit 423473d

Compare with similar skills

Task 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.

Task Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Triage this skillsuyuan2022/suyuan-skill308—~1.1kAutomated safety check: PassMIT
Triaging Issuespytorch/pytorch104k—~4.2kAutomated safety check: PassCustom licence
Issue Triagepaperclipai/paperclip99k—~1kAutomated safety check: PassMIT
Triagepnpm/pnpm37k—~2.9kAutomated safety check: PassMIT
Herdr Issue Triageherdrdev/herdr43k—~517Automated safety check: PassApache-2.0
RTK Combined Issue and PR Triagertk-ai/rtk83k—~1.6kAutomated safety check: NotesApache-2.0

Similar skills

  • 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

  • Issue Triage

    paperclipai/paperclip

    Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).

    99k GitHub stars~1k tokensUpdated today
    DevelopmentAuto-check passed

  • Triage

    pnpm/pnpm

    Triage an incoming GitHub issue against the pnpm codebase and related open issues, then apply exactly one implementation-readiness label using pnpm's state: taxonomy.

    37k GitHub stars~2.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Herdr Issue Triage

    herdrdev/herdr

    Triages open herdr GitHub issues into a short decision-first Markdown table with a priority light, recommendation, age, reactions and a reason for each.

    43k GitHub stars~517 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • RTK Combined Issue and PR Triage

    rtk-ai/rtk

    Runs issue triage and PR triage in parallel, then cross-analyzes the results to flag duplicate coverage, security gaps, P0 issues with no PR, and PR conflicts.

    83k GitHub stars~1.6k tokensUpdated today
    DevelopmentAuto-check: notes

  • Triage

    TalAter/annyang

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

    6.8k GitHub stars~810 tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check: notes

More from suyuan2022/suyuan-skill

  • Claude Cleanup Audit

    suyuan2022/suyuan-skill

    Audit and safely modify local Claude Code and Claude Desktop cleanup/privacy settings on macOS.

    308 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Claude Cleanup

    suyuan2022/suyuan-skill

    在 macOS 上安全审计、完整备份、清理或重置 Claude Code 与 Claude Desktop 本机状态。适用于清理可再生缓存和日志、轮换本地 ID、重置桌面端登录态、移除应用、继承现有遥测状态、启用最小提示词模式或修改台北时区；不用于规避封禁或平台风控。

    308 GitHub stars~634 tokensUpdated 1 mo ago
    Auto-check: notes

  • Codex Review

    suyuan2022/suyuan-skill

    Dual-model code review via Codex CLI. An agent skill from suyuan2022/suyuan-skill.

    308 GitHub stars~3.5k tokensUpdated 1 mo ago
    Auto-check: warnings

  • Break AI Slop

    suyuan2022/suyuan-skill

    Break AI Slop — force the AI to think like a real expert before doing anything.

    308 GitHub stars~981 tokensUpdated 1 mo ago
    Auto-check passed

  • Whatis

    suyuan2022/suyuan-skill

    What Is This — explain anything as a picture-first HTML page.

    308 GitHub stars~606 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Task Triage

What does Task Triage do?

Task triage with position-based thinking. An agent skill from suyuan2022/suyuan-skill. Task Triage is an agent skill from suyuan2022/suyuan-skill. Task triage with position-based thinking.

When should I use Task Triage?

Task Triage fits situations like: evaluating new tasks; prioritizing your backlog; deciding what to cut.

How do I install Task Triage in Claude Code?

Run `npx skills add suyuan2022/suyuan-skill --skill task-triage -a claude-code`. Or copy the skill folder (task-triage in suyuan2022/suyuan-skill) into .claude/skills/task-triage in your project. Claude Code loads it when a task matches its description.

How do I install Task Triage in Codex?

Run `npx skills add suyuan2022/suyuan-skill --skill task-triage -a codex`. Or copy the skill folder (task-triage in suyuan2022/suyuan-skill) into .agents/skills/task-triage in your project. Codex loads it when a task matches its description.

Can I use Task 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 suyuan2022/suyuan-skill --skill task-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/task-triage, .gemini/skills/task-triage, .github/skills/task-triage and .opencode/skills/task-triage in your project.

What does Task Triage need to run?

SKILL.md names no scripts, command-line tools or credentials: Task Triage is instructions for the agent only.

Does Task Triage access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Task Triage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Task Triage use?

Task 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 Task Triage use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 Task Triage?

Skills that share tags, products or a category with Task Triage: Triaging Issues (pytorch/pytorch, 104k stars), Issue Triage (paperclipai/paperclip, 99k stars), Triage (pnpm/pnpm, 37k stars) and Herdr Issue Triage (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Triage?

suyuan2022 (a GitHub user) maintains it in suyuan2022/suyuan-skill, which has 308 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on August 24, 2026.

Source: suyuan2022/suyuan-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.