nutshell
Skill2 starsChanged 3 months agoApache-2.0View on GitHub
Distill anything to its absolute essence — the fewest words that carry the full meaning. Use when user wants a TLDR, asks to summarize, name, or condense something, or mentions "nutshell".
2 other projects use a version of this.
Adopted by
Most recently taken up by
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- Kaagemusha/agent-skillstheir own version, first seen Sep 27, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- PeanutGT/NutsSkills★ 3same name
- Kaagemusha/agent-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 repository16 other files it gives its agents.
- aikido-jiraSkill
- compress-videoSkill
- adr-authoringSkill
- architecture-diagrammingSkill
- raid-loggingSkill
- rfc-authoringSkill
- fixing-accessibilitySkill
- frontend-designSkill
- grill-meSkill
- handoffSkill
- improve-animationsSkill
- improveSkill
- logical-commitsSkill
- pr-dailySkill
- supply-chain-checkSkill
- the-foolSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Use blockquotes (>) for the essence line
- Distinctive: line 34
One answer: Commit to the pick.
- Distinctive: line 35
Analogies only when perfect: If the comparison breaks down on inspection, it misleads.
≈ “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
Nutshell
A lens for finding the essence of anything. Useful when distillation helps — TLDR a concept, name a thing, condense a procedure, find an analogy.
The operation
Study the subject. Find what carries the meaning — what would break if removed. Output only that, in the fewest words, in the register of the domain (technical, business, casual — match the subject).
The aha test: the output must instantly form the correct mental model in the reader's mind. They should go "oh, that's what it is." If they don't, it's not tight enough yet.
Every word earns its place: cut anything that doesn't carry meaning. But never sacrifice meaning for brevity — a short wrong answer is worse than a longer right one.
Output style
Extremely concise. Sacrifice grammar for concision. Practical, elegant. Short, memorable phrasing.
Lead with the subject — the output should stand alone, understandable without seeing the question. Example: "STRV is a Czech-born dev agency that builds apps for Silicon Valley." not "Czech-born dev agency that builds apps for Silicon Valley."
Output should invite reading — like a well-organized student notebook. Visual hierarchy mirrors meaning, white space lets ideas breathe. Form is part of the message: a wall of text repels, a tidy page draws the reader in.
- Bold the subject and key anchor words
- Use blockquotes (
>) for the essence line - Bullets or numbers when content is parallel
- Let white space do work — sections breathe, points separate
Rules
- No questions. Study what was given, find the essence, deliver.
- One answer. Commit to the pick.
- Analogies only when perfect. If the comparison breaks down on inspection, it misleads. A forced analogy is worse than none — say so and fall back to plain distillation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.