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 Clarifier

by dongshuyan in dongshuyan/compass-skills

Deep need-clarification skill. An agent skill from dongshuyan/compass-skills.

MITAuto-check passedAgent Workflows

Install Task Clarifier

skills CLI
$ npx skills add dongshuyan/compass-skills --skill task-clarifier -a claude-code

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

GitHub CLI
$ gh skill install dongshuyan/compass-skills task-clarifier --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/dongshuyan/compass-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/task-clarifier .claude/skills/task-clarifier && 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-clarifier
GitHub stars
751
Token cost
~2.2k tokens
SKILL.md length
1,056 words
Files
3
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Deep need-clarification skill. An agent skill from dongshuyan/compass-skills.

  • Works in 3 steps: Help the user fully understand their own… → Help the AI fully understand the user's… → Show the user that the AI has fully…
  • Explicitly invokes $task-clarifier
  • SKILL.md covers Language Rule, Three Goals (all must be met…, Startup Reads and Clarification Loop, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Task Clarifier is an agent skill from dongshuyan/compass-skills. Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task execution unless explicitly invoked.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `agents/openai.yaml` and `evals/test_trigger_contract.py`).

It sits in Agent Workflows. The repository describes itself as: 司南：个性化 AI 任务总控 Skills 系统 /COMPASS: Personal Alignment Skills OS for AI Agents. The licence is MIT.

When your agent uses it

  • Explicitly invokes $task-clarifier

Example prompts

  • “s needs, and the user confirms the AI”
  • “/task-clarifier”

Requirements

  • Python 3

Workflow steps

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

  1. Help the user fully understand their own needs — including dimensions the user has not yet considered, latent contradictions, and implicit…
  2. Help the AI fully understand the user's needs — completely, specifically, unambiguously; no unconfirmed dimension is filled with a default…
  3. Show the user that the AI has fully understood their needs — present the understanding in an explicitly verifiable form; all inferences…

What it can do on your machine

Read from SKILL.md and the folder at commit 1b2e556. 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

    Ships script files (Python), which the agent can run.

    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 Clarifier loads about 2.2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 1,056 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 dongshuyan/compass-skills at commit 1b2e556, republished under its MIT licence (© dongshuyan). 1,056 words, ~2,204 tokens.

Download SKILL.mdSave it as .claude/skills/task-clarifier/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
task-clarifier
description
Deep need-clarification skill. Use only when the user explicitly invokes $task-clarifier. Once activated, keep asking until all three goals are met: the user fully understands their own needs, the AI fully understands the user's needs, and the user confirms the AI's understanding is correct. Do not intervene in task execution unless explicitly invoked.

Task Clarifier

Language Rule

All output directed at the user — questions, options, recommendations, confirmations, summaries — must be written in the user's language. Detect the user's language from their message. Default to Chinese when unknown. If the user writes Chinese, every word of output must be Chinese. Do not use English in any user-facing output unless the user writes in English.

Three Goals (all must be met before ending)

  1. Help the user fully understand their own needs — including dimensions the user has not yet considered, latent contradictions, and implicit assumptions that materially affect the outcome
  2. Help the AI fully understand the user's needs — completely, specifically, unambiguously; no unconfirmed dimension is filled with a default value
  3. Show the user that the AI has fully understood their needs — present the understanding in an explicitly verifiable form; all inferences listed separately for the user to confirm one by one

Startup Reads

On activation, silently attempt the following best-effort reads. If any source is unavailable, unsupported, or fails, continue without it — do not block the clarification loop.

Use the current agent or harness's native skill mechanism first. This skill must work in Codex, Claude Code, OpenClaw, OpenCode, and other agents that can read a SKILL.md file. Do not assume a specific agent name, skill root, home directory layout, shell, or operating system.

User profile summary — If $user-profile-keeper is available, read its clarification_summary view (low-sensitivity, need-alignment-related preference data only). Prefer the agent's built-in skill invocation, MCP/tool bridge, or documented companion-skill API.

Task forest — If $task-forest is available, read the current workspace task list and open todos. Prefer the agent's built-in skill invocation, MCP/tool bridge, or documented companion-skill API.

If direct script execution is the only available integration path, first discover the companion skill directory through the current harness's skill registry or by resolving the repo-local skills/<skill-name>/ directory from this SKILL.md location. Construct file paths by joining path segments with the host language or runtime path utilities so the same logic works on macOS, Linux, and Windows. Use the operating system's available Python launcher (python3, python, or py -3) only after discovery succeeds. Never hard-code paths such as ~/.codex/..., ~/.agents/..., absolute POSIX paths, or Windows drive paths.

The profile summary enriches the phrasing of question options and recommendations to better match the user's communication style and domain background.
The task forest provides context for the global purpose and evolution of the current request, so recommendations align with the real overall goal.
The current user message overrides all profile information. Neither source replaces asking about any dimension.
Do not read the full profile, pending profile, private background, raw evidence, credentials, cookies, tokens, keys, or unrelated private information. Do not write to the profile or task forest.

Clarification Loop

Each round executes the same action:

From the current conversation and readable context, extract the part that most affects the current outcome. Break it into as few questions as possible — covering what is needed for complete and accurate understanding, as few as possible, at most 3 — and provide a recommended answer and options for each question.

Questions cover whichever of the following still affects the outcome:

  • What the user ultimately wants to achieve
  • Why now, and which global purpose this serves
  • What counts as done and done well
  • What is in scope and what is not
  • Time, budget, technology, format, region, permissions, risks, and external effects
  • Which goal wins when multiple goals conflict
  • Who uses, reviews, or is affected by the result
  • Implicit premises the user has not yet recognized that would change the outcome
  • Contradictions, conflicts between goals and constraints, and parts that are infeasible in practice or technically — highest priority, include in the current round as soon as identified

When a fact can be obtained from local evidence, look it up before asking. User decisions must be confirmed by the user; never substitute a default value for a question.

When the user says "up to you / whatever / your call / 你看着办 / 随便 / 你来定", provide a recommended option and ask the user to confirm — do not proceed to execution automatically.

When all three goals are met, enter the confirmation stage. Otherwise keep asking.

High-risk actions — including delete, overwrite, migrate, publish, send, deploy, install, use credentials, elevate permissions, write to remote systems, or change global configuration — require listing the exact actions and waiting for explicit approval before execution, even after the confirmation summary is accepted.

Show full SKILL.md (329 more words)Show less

Question Format

Generate questions and recommended answers that are simple, clear, accurate, complete, and understandable to anyone. Output in the user's language (default Chinese).

Each question follows this layout — reason first, options second, recommendation last:

**Q1. [一句话：这个问题为什么影响结果]**

A) [选项]　B) [选项]　C) [选项]　D) 告诉我你的想法

→ 我的建议：[推荐答案，简洁直接]

When asking multiple questions in one turn, separate each with a blank line and ---:

**Q1. [原因]**

A) …　B) …　C) …　D) 告诉我你的想法

→ 我的建议：…

---

**Q2. [原因]**

A) …　B) …　C) …　D) 告诉我你的想法

→ 我的建议：…

Draw on the communication preferences and domain familiarity in the profile summary (if read), and the global goal context in the task forest (if read), to make options and recommendations more relevant to this user and this task.

Confirmation Stage

Once all three goals are met, output in the user's language (default Chinese):

我的理解如下：
[用自然语言陈述用户的完整需求，3-5 行，具体、准确、不遗漏关键约束]

我的推断（请逐条确认）：
- 我推断 [X]，因为 [具体原因] — 如有偏差请直接纠正
- 我推断 [Y]，因为 [具体原因] — 如有偏差请直接纠正

确认后我会：[下一步动作]
有没有我遗漏的？

If the user corrects any inference → update the understanding, ask at most 1 follow-up question on the corrected point, and output the confirmation summary again.
If the user confirms everything is correct → this skill ends; execution can begin.

No Bypass After Activation

Once this skill is explicitly invoked, no bypass is used, and no safe defaults substitute for asking. Recommended answers help the user choose quickly; they are not automatically written into the requirements.

Examples

Example 1: Unformed needs + contradiction detection

User: $task-clarifier 帮我写个爬虫，要快，把100万条历史数据全抓完

Round 1 (identify contradiction + highest-impact decision):

Q1. "快"和"100万条全部抓完"之间存在冲突：完整抓取百万级数据通常耗时较长，且可能触发速率限制或封禁。你更看重哪个？这决定了整体技术策略。

A) 完整性优先（接受耗时，分批完成）　B) 速度优先（接受部分数据缺失）　C) 有具体 deadline（请告诉我时间）　D) 告诉我你的想法

→ 我的建议：完整性优先，用分批 + 限速策略保证全量，避免封禁。

User: 完整性优先，3天内跑完

Round 2 (acceptance criteria):

Q1. 你如何判断"抓完了"？这决定了数据完整性的验收方式和补抓策略。

A) 条数达到100万即可　B) 需要与某个基准数据对比验证　C) 告诉我你的想法

→ 我的建议：以实际抓取条数为主标准，同时记录失败条目以便补抓。

[All three goals met → enter confirmation stage]

Example 2: Profile-assisted phrasing

Context: Profile summary shows the user prefers Chinese, structured expression, and evidence-first reasoning.

User: $task-clarifier 帮我研究这个工具值不值得用

Round 1 (evaluation criteria + output form):

Q1. "值不值得用"需要先确定判断标准；成本、稳定性、安全性、迁移成本会导向不同结论。这决定了评估的维度和深度。

A) 快速判断能不能用　B) 深度评估长期采用成本　C) 和替代方案对比　D) 告诉我你的想法

→ 我的建议：按"是否解决当前问题、迁移成本、可验证风险"三项评估，优先使用官方文档和本地证据，输出结构化对比。

Example 3: Task forest global context

Context: Task forest shows global task is "Python 2→3 full migration"; current subtask is "auth module migration".

User: $task-clarifier 帮我把 auth.py 的 print 语句改成 print 函数

Round 1 (scope + global goal context):

Q1. 这个修改属于 Python 2→3 迁移任务的一部分。auth.py 中还可能存在其他兼容性问题（unicode 字符串、整数除法、异常语法等）。这次范围如何定？这决定是否需要反复修改同一个文件。

A) 只改 print 语句　B) 一并处理 auth.py 所有 Python 2→3 差异　C) 告诉我你的想法

→ 我的建议：选 B，一并处理，加快整体迁移进度。

Example 4: Confirmation summary format
我的理解如下：
你需要用 Python 编写一个爬虫，抓取目标网站的100万条历史数据。
完整性优先，接受分批 + 限速策略，3天内完成。
验收标准：实际抓取条数达到100万条，记录失败条目以便补抓。

我的推断（请逐条确认）：
- 我推断目标网站公开可访问（无需登录），因为你未提及账号或认证信息 — 如有偏差请直接纠正
- 我推断数据存储在本地数据库，因为百万级数据量通常不适合纯文件存储 — 如有偏差请直接纠正
- 我推断这是一次性历史全量抓取，不需要实时增量更新 — 如有偏差请直接纠正

确认后我会：生成爬虫代码框架（含分批 + 限速逻辑、失败条目记录）。
有没有我遗漏的？

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

Files

SKILL.md and 2 other files in skills/task-clarifier of dongshuyan/compass-skills.

  • SKILL.md
  • agents/openai.yaml
  • evals/test_trigger_contract.py

Open the folder on GitHubat commit 1b2e556

Compare with similar skills

Task Clarifier 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 Clarifier compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Clarifier this skilldongshuyan/compass-skills751—~2.2kAutomated safety check: PassMIT
Unbrowseunbrowse-ai/unbrowse778—~3.3kAutomated safety check: PassMIT
Project ButlerJamesShi96/project-butler373—~3.9kAutomated safety check: PassMIT
Gemini SkillWJZ-P/gemini-skill832—~1.1kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
Fleet Manager for Agent Sessionsasgeirtj/system_prompts_leaks69k—~2.5kAutomated safety check: PassCC0-1.0

Similar skills

  • Unbrowse

    unbrowse-ai/unbrowse

    Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser.

    778 GitHub stars~3.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

  • Project Butler

    JamesShi96/project-butler

    Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status…

    373 GitHub stars~3.9k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Gemini Skill

    WJZ-P/gemini-skill

    通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。

    832 GitHub stars~1.1k tokensUpdated 20 days ago
    Agent WorkflowsAuto-check passed

  • agtx One-Shot Project Runner

    fynnfluegge/agtx

    Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed

  • Fleet Manager for Agent Sessions

    asgeirtj/system_prompts_leaks

    Shows one digest of coding-agent sessions across your connected machines and lets you open, read, steer, approve, stop and close them, over Herdr, tmux or MSP.

    69k GitHub stars~2.5k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • WebGPT

    Nhahan/WebGPT

    Hands bounded tasks from Codex to a signed-in ChatGPT web session at a chosen reasoning level, or opens a terminal chat in your project that you control.

    117 GitHub stars~1.4k tokensUpdated 15 days ago
    Agent WorkflowsAuto-check passed

More from dongshuyan/compass-skills

All 9 skills in this repo

  • Task Forest

    dongshuyan/compass-skills

    Maintains a repo-local task forest or task DAG for the current workspace.

    751 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Run History Skill Builder

    dongshuyan/compass-skills

    Turn a completed task, browser flow, artifact pipeline, failure-recovery trace, or repeatedly refined workflow into a new reusable skill package or a reviewed skill-design plan.

    751 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • Run History Skill Upgrader

    dongshuyan/compass-skills

    Use real run evidence, validation failures, source drift, platform drift, and user feedback to plan and, only after explicit approval, apply structural upgrades to an existing skill.

    751 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Session Handoff Prompt

    dongshuyan/compass-skills

    Create a concise continuation prompt that a fresh agent session can paste in to resume a long or degraded session.

    751 GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • User Profile Keeper

    dongshuyan/compass-skills

    Local user-profile maintenance skill for Codex, Claude Code, OpenClaw, OpenCode, and other agent harnesses.

    751 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Assess Interview Candidate

    dongshuyan/compass-skills

    根据候选人简历与岗位要求生成可审计的后台评估、简明的候选人介绍、按岗位重要性排列的简历疑点、12–18 道可直接照读的面试题，以及支持重点标记和本机保存的离线 HTML。用于招聘方准备结构化面试、核验岗位能力和记录回答。不要用于求职者模拟面试、私人背景调查、心理或人格诊断、从敏感属性推断表现，或自动录用、淘汰、排序候选人。

    751 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Task Clarifier

What does Task Clarifier do?

Deep need-clarification skill. An agent skill from dongshuyan/compass-skills. Task Clarifier is an agent skill from dongshuyan/compass-skills. Deep need-clarification skill.

When should I use Task Clarifier?

Task Clarifier fits situations like: explicitly invokes $task-clarifier.

How do I install Task Clarifier in Claude Code?

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

How do I install Task Clarifier in Codex?

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

Can I use Task Clarifier 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 dongshuyan/compass-skills --skill task-clarifier -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-clarifier, .gemini/skills/task-clarifier, .github/skills/task-clarifier and .opencode/skills/task-clarifier in your project.

What does Task Clarifier need to run?

Going by SKILL.md and its folder, Task Clarifier needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Task Clarifier 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 Clarifier 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 Clarifier use?

Task Clarifier 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 Clarifier use?

About 2.2k tokens (SKILL.md is roughly 8.8k 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 Clarifier?

Skills that share tags, products or a category with Task Clarifier: Unbrowse (unbrowse-ai/unbrowse, 778 stars), Project Butler (JamesShi96/project-butler, 373 stars), Gemini Skill (WJZ-P/gemini-skill, 832 stars) and agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Clarifier?

dongshuyan (a GitHub user) maintains it in dongshuyan/compass-skills, which has 751 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on August 26, 2026.

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