lazy
Skill1 starsChanged 26 days agoMITView on GitHub
Shortcut — lazy senior dev mode: do it directly with the simplest working solution (YAGNI, stdlib first, no unrequested abstractions), no ticket/review/QA. Use as /noskill:lazy followed by the request
3 other projects use a version of this.
Adopted by
Most recently taken up by
- noahseger/agent-skillstheir own version, first seen Nov 4, 2026
- rizukirr/vibekittheir own version, first seen Jul 31, 2026
- PatriotAgenticLLC/better_claude_skillztheir own version, first seen Jul 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- rizukirr/vibekit★ 20same name
- noahseger/agent-skills★ 8same name
- PatriotAgenticLLC/better_claude_skillz★ 3same 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 repository11 other files it gives its agents.
- coding-standardsSkill
- debug-assistantSkill
- erp-requirementsSkill
- feature-flowSkill
- kantorSkill
- prd-writerSkill
- project-profileSkill
- task-breakdownSkill
- ticket-implementationSkill
- ticket-workflowSkill
- tiketSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Do the following request directly in this session — without ticket, agents, review, or QA:
- Distinctive: line 13
Stop at the first step that solves the problem.
- Distinctive: line 14
Does it need building?: If the request can be met without new code (existing config, existing behavior), do that.
- Very specific: line 15
Already in the codebase?: Before writing anything, grep the concept (e.g.
- Distinctive: line 16
Standard library or framework feature?: Use it.
- Distinctive: line 17
Dependency already installed?: Use it. Don't add new dependencies.
- Distinctive: line 23
No unrequested abstractions, interfaces, factories, wrappers, config, options, parameters, or "for later" code.
- Very specific: line 29
If the request turns out to touch new business rules, database schema, more than ~5 files, or several repos, don't silently continue.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Do the following request directly in this session — without ticket, agents, review, or QA:
$ARGUMENTS
How to think
Stop at the first step that solves the problem. Step 2 must never be skipped, even if the solution is a single stdlib line:
- Does it need building? If the request can be met without new code (existing config, existing behavior), do that.
- Already in the codebase? Before writing anything, grep the concept (e.g.
clamp|limit|min|maxfor value bounds,format|currencyfor money formatting) in helper/lib/utils folders. If a helper exists for it, reuse it. - Standard library or framework feature? Use it.
- Dependency already installed? Use it. Don't add new dependencies.
- Write minimal code that is correct.
Rules
- Smallest possible diff: touch only files that need it. No refactor, rename, reformat, or "fixing things while I'm here".
- No unrequested abstractions, interfaces, factories, wrappers, config, options, parameters, or "for later" code. Two or three similar lines beat a new helper used once.
- Not cut: input validation that prevents corrupt data, error handling that's actually needed, and security.
- Evidence is still required: run the relevant test or command. If business logic has no test, add one small test (positive and negative in one file). Without evidence, don't claim done.
When to stop
If the request turns out to touch new business rules, database schema, more than ~5 files, or several repos, don't silently continue. Stop and suggest /noskill:tiket fix (one ticket with review and verification).
Report (max ~8 lines)
- Files changed
- Keywords grepped and helpers reused (or "tidak ada")
- Why this is the simplest way (one sentence)
- Test/command result
- What wasn't checked, if anything
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.