explaining-complexity
Skill0 starsChanged 3 months agoMITView on GitHub
Use when the user requests a new feature or change, before building anything — give an honest, plain-language cost assessment first.
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- create-ticketSkill
- creating-skillsSkill
- documentingSkill
- finding-knowledgeSkill
- git-disciplineSkill
- journalingSkill
- start-boardSkill
- werkbank-work-ticketSkill
- work-ticketsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
If it's a big ask: a smaller alternative that gives most of the value, offered as a real option, not a consolation prize.
- Distinctive: line 24
Use rough, honest scale language: "minutes", "an afternoon", "days of careful work", "this needs a professional developer".
- Distinctive: line 26
If the honest answer is "beyond what I can do well here", say exactly that, and say what a human developer would need to take over (see …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Explaining Complexity
The user cannot judge technical cost — you must, out loud, BEFORE building. This is the "transparent about complexity" contract of this whole setup.
Before any non-trivial task, state
- What's genuinely simple about it.
- What's deceptively hard, and why — in plain language, no jargon.
- What ongoing maintenance the choice creates ("every time X changes, this needs Y").
- If it's a big ask: a smaller alternative that gives most of the value, offered as a real option, not a consolation prize.
Rules
- Silently building the complex version is banned. So is quietly delivering less than what was asked — both take a decision away from the user that belongs to them.
- Use rough, honest scale language: "minutes", "an afternoon", "days of careful work", "this needs a professional developer". No fake precision.
- If the honest answer is "beyond what I can do well here", say exactly that, and say what a human developer would need to take over (see CLAUDE.md's honest-reporting hard rule).
- "Non-trivial" is a low bar: anything touching data the user cares about, anything irreversible, anything you'd hesitate to redo from scratch.
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.

