big-change
Skill1 starsChanged 3 months agoNo licenceView on GitHub
Like /improve, but every change is BIG — bold, ambitious, high-impact rewrites and redesigns rather than small safe tweaks. Sweeps the codebase FILE BY FILE in a fixed sorted order — big change to file 1 finished fully, then file 2, 3, 4… until every file is reached — and deliberately does NOT jump around following dependencies (if file 1 depends on file 4, it still improves file 1 now and gets to file 4 in order). Each file's change is made fully and proven better before moving on. Every big change must be REAL working functional code — comments, placeholders, TODOs, dummy/mock logic, API-key/stub placeholders, dead scaffolding and cosmetic churn do NOT count as big changes and are never used to mark a file done. Invoked as "big-change" for the full file-by-file sweep, or "big-change N" (e.g. "big-change 5") to stop after N files. Use whenever the user invokes /big-change or says "make big changes", "go big", "don't hold back", "make crazy-good large changes", "rewrite this properly", or "improve all the files and make big changes". The ambitious, large-scope sibling of [[improve]] — same measure-and-keep-only-what-wins discipline, much larger unit of change, applied one file at a time in order.
- Reads credentials
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.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
In this repository73 other files it gives its agents.
- backupSkill
- behindSkill
- bug-huntSkill
- build-it-newSkill
- carefulSkill
- checklistSkill
- cleanupSkill
- continueSkill
- controlSkill
- create-videoSkill
- decideSkill
- documentateSkill
- dont-stop-till-completeSkill
- dont-use-skills-rnSkill
- find-the-virusSkill
- fixSkill
- flutter-designSkill
- full-controlSkill
- full-implementSkill
- full-speedSkill
- full-stopSkill
- improve-designSkill
- improvement-ideasSkill
- improve-performanceSkill
- improveSkill
- inventSkill
- just-do-itSkill
- laptop-modeSkill
- later-ideasSkill
- learnSkill
- legit-projectSkill
- limit-refreshSkill
- loopSkill
- make-it-make-senseSkill
- mapSkill
- maskSkill
- missingSkill
- new-featuresSkill
- no-internetSkill
- no-talkSkill
- no-waitingSkill
- optimizeSkill
- pauseSkill
- placeholder-replacerSkill
- play-sound-when-doneSkill
- portSkill
- protectSkill
- quick-cleanupSkill
- quick-documentateSkill
- quick-fixSkill
- quick-improveSkill
- quick-mapSkill
- read-skills-againSkill
- researchSkill
- reverse-engineerSkill
- save-usageSkill
- selfmadeSkill
- shutdown-when-doneSkill
- sickSkill
- smoothenerSkill
- The first 60 shown.
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.