nutshell
Skill3 starsChanged 18 days agoApache-2.0View on GitHub
Use at the start of every software engineering task (building, fixing, reviewing, planning, refactoring, shipping), together with any more specific skill that applies. Holds the always-on baseline rules and picks which engineering skill to load next.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Kaagemusha/agent-skillstheir own version, first seen Sep 27, 2026
- strvcom/frontend-skillstheir own version, first seen Aug 3, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- strvcom/frontend-skills★ 2same 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.
- CLAUDE.mdCLAUDE.md
- clarifySkill
- code-reviewSkill
- debugSkill
- designSkill
- exam-prepSkill
- fresh-eyesSkill
- music-studioSkill
- planSkill
- repo-mapSkill
- shipSkill
- simplifySkill
- specSkill
- tddSkill
- verifySkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 14
Core rule: If there is even a small chance a skill applies, read it before you act.
- Distinctive: line 17
Think before coding: If the request is ambiguous, ask.
- Distinctive: line 52
If a skill has a checklist, track each item.
- Very specific: line 53
If two skills apply, process skills (clarify, debug) come before implementation skills (tdd, design).
≈ “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 — the nuts-engineering router
Core rule: If there is even a small chance a skill applies, read it before you act. Skills are cheap to read and expensive to skip.
Baseline (always on)
- Think before coding. If the request is ambiguous, ask. State assumptions before acting on them.
- Simplest thing that works. Build only what was asked. No speculative features, options, or abstractions.
- Surgical changes. Touch only what the task needs. Match the surrounding style. Mention unrelated problems instead of fixing them silently.
- Goal-driven. Define what "done" looks like before starting, and never claim done without evidence (
verify).
Which skill when
| Situation | Skill |
| Need to find where things live in an unfamiliar or large repo | repo-map |
| Request is vague, new feature idea, "I want to build X" | clarify |
| Requirements are clear, need acceptance criteria | spec |
| Work has more than ~3 steps or touches several files | plan |
| About to write implementation code (feature or bugfix) | tdd |
| Bug, failing test, error message, unexpected behavior | debug |
| About to say "done", "fixed", "passing", or open a PR | verify |
| Reviewing a diff, or received review feedback | code-review |
| New module, API, data model, or architectural choice | design |
| Code works but feels too complex, or after a feature lands | simplify |
| Committing, opening a PR, finishing a branch | ship |
| Spec, plan, or risky decision about to be handed over or committed | fresh-eyes |
| Creating or editing a skill | writing-skills |
The default flow
clarify → spec → plan → tdd ⇄ debug → verify → code-review → ship
repo-map / design / simplify / fresh-eyes can be called at any pointSmall tasks skip early steps: a one-line fix goes straight to tdd → verify. A typo needs no skill at all.
Rules
- The user's explicit instructions override any skill.
- Announce which skill you are using in one short line, then follow it.
- If a skill has a checklist, track each item; do not skip silently.
- If two skills apply, process skills (
clarify,debug) come before implementation skills (tdd,design).
Red flags — you are about to skip a skill
| Thought | Reality |
| "This is simple, I'll just do it" | Simple tasks are where unchecked assumptions hide. Check the table. |
| "I'll read the skill after I look around" | The skill tells you how to look around. |
| "I remember what that skill says" | Skills change. Read the current version. |
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.