minds
Skill2 starsChanged 41 days agoMITView on GitHub
Index of the think-like pack: lists every great mind available, what each one makes the agent do, and which to pick for a given problem. Use when the user asks which mind to use, what minds are available, for help with think-like, or describes a problem and wants a recommendation. Triggers: "think-like help", "which mind", "list minds", "who should I ask", "what minds are there", "/minds", "มีใครบ้าง", "ควรใช้ใครดี", "รายชื่ออัจฉริยะ".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- itamarmeirovichai-source/claude-skillstheir own version, first seen Sep 29, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- itamarmeirovichai-source/claude-skills★ 0same name
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 repository25 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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 18
When the user describes a problem, recommend one to three minds from the table and say why in one line each.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
think-like: the minds
Each mind is a skill that changes how the agent works: what it checks, in what order, and what it
must produce. Invoke one by name ("think like Ohno", /think-like:ohno) or let the agent pick it
up from the task. For important decisions use several at once with /think-like:council.
When the user describes a problem, recommend one to three minds from the table and say why in one line each. Answer in the user's language.
Understand and debug
| Mind | Makes the agent… | Use for |
| feynman | explain in plain words, find the gap in understanding, test a prediction | confusing code, unexplained fixes |
| polya | write down unknown, data and condition; solve a simpler case; look back | being stuck after failed fixes |
| ohno | collect evidence, ask why until an actionable cause, add a countermeasure | incidents, bugs that come back |
| shannon | transform the problem six ways to find a new approach; separate signal from noise | no obvious approach, noisy alerts |
Correctness and design
| Mind | Makes the agent… | Use for |
| dijkstra | state contracts and invariants, argue correctness before testing | algorithms, money, concurrency |
| liskov | write the caller's contract, check every implementation can substitute | interfaces, inheritance, adapters |
| ousterhout | find shallow modules and leaked knowledge, design it twice | module and API design |
| hickey | find complected concerns, push effects to the edges, prefer values | state, data models, tool choices |
| knuth | size the problem, analyze candidates, optimize only the critical part | algorithms, "is this fast enough" |
| einstein | list assumptions, run thought experiments at the limits | distributed systems, time, scale |
| tesla | build and run the whole system in the head before coding | multi-part features, migrations |
Build and ship
| Mind | Makes the agent… | Use for |
| beck | work in red, green, refactor steps; tidy first | implementing behavior safely |
| fowler | name the smells, apply catalog refactorings in small steps | messy code, cleanup |
| torvalds | read the diff, remove special cases, never break existing users | code review, public interfaces |
| carmack | set a budget, measure, remove work, re-measure | performance |
| brooks | separate essential from accidental, count communication paths | estimates, staffing, rewrites |
Decide
| Mind | Makes the agent… | Use for |
| musk | question each requirement's owner, delete, simplify, speed up, then automate | bloated specs and processes |
| bezos | write the press release first, sort one-way and two-way doors | product decisions, slow decisions |
| munger | invert, follow incentives, run a bias checklist | risky or expensive choices |
| kahneman | start from the outside view, run a pre-mortem, give ranges | estimates, confident plans |
| turing | turn a vague question into a pass/fail procedure | specs, acceptance criteria, evals |
| socrates | ask the few questions that define the real requirement | ambiguous requests |
| hopper | make costs concrete, demo instead of debate | convincing stakeholders |
Tools
| Skill | What it does |
| council | 3–5 minds review one decision and a synthesis names the trade-offs |
| mind-maker | build a new mind skill from sources you provide |
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.