options-analysis
Skill3 starsChanged 36 days agoMITView on GitHub
Answer an open design or tooling question with N mechanistically distinct options — each with its own pros and cons block — then one recommendation argued from mechanism, naming which options to skip and why.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ryansilk/apexvol-mcptheir own version, first seen Sep 9, 2026
- Serennity007/invest-skilltheir own version, first seen Aug 25, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ryansilk/apexvol-mcp★ 1same name
- Serennity007/invest-skill★ 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 repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- compare-statesSkill
- explain-simplySkill
- full-pictureSkill
- greenfieldSkill
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 29
If the framing itself is broken — the constraint can't be enforced where they're asking, the options collapse into one — lead with that, …
≈ “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
options-analysis
The user wants to choose, not to read a survey. Deliver N real alternatives and a verdict that eliminates.
Options must differ in mechanism, not in degree — a hook that blocks, a config default, and a runtime escalation ladder are three options; three phrasings of "add a rule" are one. Give the number asked for, and when only two are real, say so rather than padding with a variant.
The cons are where the answer gets made. Lead each option's cons with its disqualifying property — the reason it fails, not its rough edges. Ground that failure in how the thing works, and look up the real contract (tool schema, API precedence, config resolution order) when the con depends on it; a con asserted from vibes is the expensive kind of wrong. When an option has no serious con, say so instead of manufacturing balance.
The verdict names a winner and names what to skip, reasoned from mechanism. Layering is a legitimate answer ("2 as the floor, 1 as the enforcement") — say which does which job. "Depends on your priorities" is a non-answer.
If the framing itself is broken — the constraint can't be enforced where they're asking, the options collapse into one — lead with that, then still give the options.
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.