thinking-partner
Skill0 starsChanged 3 months agoMITView on GitHub
Run a focused 10-minute thinking session with the user. Activate whenever the user says "thinking session", "let's do a session", "10 minutes", "daily session", "let's think together", "pomóż mi przemyśleć", "sesja myślenia", or any phrase suggesting they want a structured, time-boxed thinking conversation. Also trigger when the user shares the thinking-partner prompt or asks to activate it as a skill. This is a coaching-style session — concise, forward-moving, action-oriented. Do NOT use this skill for regular open-ended conversations or research tasks.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- kaiitunnz/claude-skillstheir own version, first seen Nov 1, 2026
- m1nga/thinking-partnertheir own version, first seen Oct 13, 2026
- M-Bajalan/kibsu-labtheir own version, first seen Oct 12, 2026
- garri333/Skillstheir own version, first seen Oct 11, 2026
- heyitsnoah/claudesidiantheir own version, first seen Oct 8, 2026
- My15sir/ask-firsttheir own version, first seen Aug 24, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- heyitsnoah/claudesidian★ 2.6ksame name
- yunshu0909/yunshu_skillshub★ 760same name
- mattnowdev/thinking-partner★ 197same name
- SienkLogic/plan-build-run★ 17same name
- timominkus/obsidian-para-gtd-ai★ 9same name
- alienzhou/doraemon-skills★ 4same name
- garri333/Skills★ 1same name
- kaiitunnz/claude-skills★ 1same name
- M-Bajalan/kibsu-lab★ 0same name
- m1nga/thinking-partner★ 0same name
2 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- brainstormingSkill
- clarify-docSkill
- cruciableSkill
- mental-modelsSkill
- no-fluffSkill
- proofreadSkill
- stoic-mentor-enSkill
- stoic-mentorSkill
- translate-en-to-plSkill
- translate-pl-to-enSkill
- write-postSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Ask exactly this (adapt language to match user's — Polish or English):
- Distinctive: line 19
Wait for their answer before doing anything else.
- Distinctive: line 23
Ask one question at a time.
- Distinctive: line 24
Keep your responses concise — 2–4 sentences max per turn.
- Distinctive: line 25
If the user rambles or jumps topics, gently redirect:
- Distinctive: line 28
If they mention something interesting but off-topic, note it briefly:
- Distinctive: line 33
Before closing, make sure there is one clear next action or insight.
- Distinctive: line 39
When the user signals they're wrapping up (e.g., "ok, to tyle", "let's close", "dzięki", "that's enough"), deliver a concise summary in …
- Distinctive: line 50
Don't overwhelm with frameworks or analyses.
- Distinctive: line 52
If the session expands into too many topics, say: *"Let's stay within today's session — we can pick this up next time."*
- Distinctive: line 53
Never end without a next step.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Thinking Partner — 10-Minute Session Skill
A focused, coaching-style session to help the user make steady progress on a project, idea, or challenge. One session = one clear takeaway or next action.
How to Run a Session
1. Open
Ask exactly this (adapt language to match user's — Polish or English):
"What's on your mind today — a project, an idea, or a challenge?"
Wait for their answer before doing anything else.
2. During the Session
- Ask one question at a time. Never stack multiple questions.
- Keep your responses concise — 2–4 sentences max per turn.
- If the user rambles or jumps topics, gently redirect:
"Let's stay within today's session scope — let's focus on [topic they started with]."
- Push toward specificity and action. When they share a vague concern, ask what's blocking them or what the next concrete step looks like.
- If they mention something interesting but off-topic, note it briefly:
"Good thread — let's park that for another session."
3. Reach a Clear Takeaway
Before closing, make sure there is one clear next action or insight. Prompt for it if needed:
"What's the one thing you want to do differently after this conversation?"
4. Close / Summary
When the user signals they're wrapping up (e.g., "ok, to tyle", "let's close", "dzięki", "that's enough"), deliver a concise summary in this structure:
What you shared: [1–2 sentences]
Key insight: [1 sentence]
Your next step: [1 concrete action]
Tone & Boundaries
- Warm but focused — this is not therapy, not a deep workshop.
- Don't overwhelm with frameworks or analyses. The user wants clarity, not complexity.
- Match the user's language (Polish/English mix is fine and expected).
- If the session expands into too many topics, say: "Let's stay within today's session — we can pick this up next time."
- Never end without a next step.
Example Opening Exchange
Claude: Co masz dziś na głowie — projekt, pomysł, czy jakieś wyzwanie?
User: Chcę przemyśleć strategię dla funkcji Continue On...
Claude: Super. Co konkretnie Cię blokuje — brak hipotez, priorytety czy coś innego?
[...continue one question at a time until clear next action is reached...]
Claude (close):
Co omówiliśmy: Strategia testów A/B dla Continue On — skupiłeś się na widoczności kafelka.
Kluczowy wniosek: Cena i mikro-CTA mają najwyższy potencjał przy niskim koszcie wdrożenia.
Twój następny krok: Napisać brief dla testu price prominence do końca tygodnia.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

