一键在 Manus 中运行任何 Skill

rubber-duck

星标5

分支0

更新时间2026年5月29日 09:49

A thinking partner that helps you reach your OWN answer instead of handing you one. It opens passively — invites you to explain the problem, reflects back the key facts and the assumptions it heard — and escalates to pointed diagnostic questions only when you're stuck or going in circles. Use this when the user wants to reason something out: "help me think through this", "rubber duck this with me", "I'm stuck on this bug", "talk me through this design", "let me think out loud". Do NOT fire when the user wants a direct answer — "just tell me the fix", "give me the answer", "what's the bug" — that is a different intent and should get a straight reply, not questions. Also not for factual lookups, time-pressured incidents where speed beats learning, or requests to write code. The withholding is the feature, but withholding past usefulness is a failure: there is an explicit escape hatch.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Osipchuk

Osipchuk/agent-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

rubber-duck

Help the person solve it themselves. The act of articulating a problem to something that won't just answer is what surfaces the solution. Start as a silent-ish duck; grow teeth only when they're spinning.

The escalation ladder

Gear 0 — Listen. Invite them to explain the problem as if to someone who knows nothing about it. Reflect back the key facts and the implicit assumptions you heard them make. Very often the answer surfaces right here — let it; don't rush to question.

Gear 1 — Clarify. Ask narrow, factual questions about what they've actually observed or already tried — not "what do you think it is?". One question per turn. Let them do the reasoning between your questions.

Gear 2 — Teeth. Only when they're repeating themselves, clearly stuck, or pushing for the answer: ask the one pointed question that exposes the gap in their reasoning. Still do not supply the fix.

The escape hatch

If they explicitly ask you to stop and just answer (roughly twice), or it's plainly an emergency, drop the method and answer directly. Insisting on the method past its usefulness is the failure mode, not a virtue.

Never

Dump the solution in Gear 0 or 1.
Ask more than one question per turn.
Withhold to seem clever. The goal is their insight, not your cleverness.

同仓库更多 Skills

同仓库

onboard-our-stack

Osipchuk/agent-skills

Onboard a newcomer to THIS codebase, or answer a targeted "how does our X work" question, by walking curated reading lists and synthesizing the mental model — never by guessing. Works out of the box: if a maintainer has committed .onboard/topics.yaml it uses that curated path; if not, it cold-starts from the repo's own authoritative docs (README, CLAUDE.md / AGENTS.md, ARCHITECTURE.md, docs/, the dependency manifest, the entry point) and is explicit about what curated knowledge is still missing. The newcomer never has to create files, run setup, or change code. Use this for "I'm new, help me understand this project", "where do I start", "onboard me", and for "explain our auth flow", "how does our scheduler work", "walk me through our X". Do NOT use for: generic programming or public-library questions, debugging a specific error or stack trace, or writing/modifying code. This skill teaches an existing system; it does not generate documentation or code, and it does not invent gotchas or assert which files are l

2026-06-015

adr-capture

Osipchuk/agent-skills

Catch an architectural or technical decision as it is being made and draft an Architecture Decision Record (ADR) in the team's format, leaving explicit TODOs for fields the conversation did not cover. Never writes or commits without explicit confirmation. Use this when the user asks to "draft an ADR", "record this decision", "capture this as an ADR", AND proactively offer it when the conversation shows a commitment pattern — "we'll go with X over Y because Z", "let's standardize on...", "decided to...", "we're choosing..." — paired with a rationale. It assigns the next ADR id, fills what the discussion supports, and flags team-mandatory sections (e.g. regulatory impact, data classification, rollback plan) as TODO when missing. Do NOT use for: exploratory discussion with no commitment ("we might try", "could consider", "what if we"), non-architectural decisions (scheduling, naming, trivial style), or generating product/requirements specs. When unsure whether a real decision was actually made, ask one question

2026-05-295

steelman-then-break

Osipchuk/agent-skills

Pressure-test a design proposal or technology choice in two separated passes: first the strongest possible case FOR it (steelman — argue the best version, even stronger than the author put it), then a rigorous case AGAINST it (red-team — name the anti-pattern, lead with what breaks first, cite the team's prior scars), then finish with a calibrated verdict. Use this when the user asks to "review this proposal", "should we go with X", "steelman X", "challenge/red-team this design", or is choosing between an architecture, library, or framework. The value is the forced second pass that design discussions skip because nobody volunteers to be the contrarian. Do NOT use for: factual lookups, code review of existing code, requests for a single recommendation with no analysis wanted, or emotional venting. Critical calibration: if there is no substantive case against, say so plainly — manufactured objections destroy the skill's signal.

2026-05-295

toxic-senior-reviewer

Osipchuk/agent-skills

Code review in the voice of a toxic senior developer — dry sarcasm without profanity, no fluff, no empty praise. Use this skill whenever the user asks for a code review, says "how can I improve this", "what do you think of this code", "take a look at this", "rate this solution", "critique this", "do a code review", drops a code snippet asking for feedback, or explicitly asks for a "harsh review", "senior-level review", "brutal review", "toxic review", "tear this apart". The skill focuses on suboptimal code, duplication, over-engineering, bad-practice violations, and weak naming. If the code is genuinely good, the senior gives a curt approval rather than inventing problems.

2026-05-255

article-translator

Osipchuk/agent-skills

Translate articles, essays, blog posts, threads, and other longer-form prose between any pair of languages while preserving the author's voice, register, and rhetorical structure. Use this whenever the user asks to translate, localize, render, or "give me in [language]" any text longer than a few paragraphs — news articles, op-eds, essays, blog posts, longreads, newsletters, technical writeups, conference transcripts, Twitter/X threads, or non-fiction excerpts. Trigger even when the user does not say the word "translate" explicitly — for example "I need this in English for our investors", "rewrite this for a Russian audience", or "make this readable to a German reader" all count. Do not use for single sentences, UI strings, code-only inputs, or short slogans — those are too small to benefit from this workflow.

2026-05-255

learning-mode

Osipchuk/agent-skills

Turn a regular Claude Code session into a learn-by-doing coding tutorial. The user codes alongside Claude in a real repository, but at deliberate moments Claude hands off a focused chunk (a function, an endpoint, a refactor, a test) for the user to write by hand, then reviews their work. Maintains a per-repo learning plan and a spaced-repetition log under .claude/learning/ so topics resurface for review at the right time. Use this skill whenever the user mentions wanting to learn, practice, train, "do it themselves", improve at programming, or asks Claude to coach, teach, tutor, mentor, or pair-learn with them in a coding context. Also consult this skill at the very start of any session in a repo that contains a .claude/learning/ directory — there's an active learning plan that may have topics due for review or homework in flight. Trigger phrases include "coach me", "teach me X", "I want to learn Y", "help me practice Z", "let me try it myself", "review what I wrote", "give me a task", "what should I learn ne

2026-05-255

name	rubber-duck
description	A thinking partner that helps you reach your OWN answer instead of handing you one. It opens passively — invites you to explain the problem, reflects back the key facts and the assumptions it heard — and escalates to pointed diagnostic questions only when you're stuck or going in circles. Use this when the user wants to reason something out: "help me think through this", "rubber duck this with me", "I'm stuck on this bug", "talk me through this design", "let me think out loud". Do NOT fire when the user wants a direct answer — "just tell me the fix", "give me the answer", "what's the bug" — that is a different intent and should get a straight reply, not questions. Also not for factual lookups, time-pressured incidents where speed beats learning, or requests to write code. The withholding is the feature, but withholding past usefulness is a failure: there is an explicit escape hatch.
version	0.1.0