fork
Skill2 starsChanged 6 months agoMITView on GitHub
\"Fork and Hack\" — Cloner un projet Open Source existant et le customiser pour son besoin. Plus rapide que tout coder from scratch.
- Deletes or force-pushes
9 other projects use a version of this.
Adopted by
Most recently taken up by
- moxclaw/fork-skilltheir own version, first seen Nov 15, 2026
- bragoatski/fork-for-agentstheir own version, first seen Nov 8, 2026
- alexandrosandre/agentic-engineeringtheir own version, first seen Nov 8, 2026
- jinjan21-lgtm/forktheir own version, first seen Nov 8, 2026
- kgarg2468/better-forktheir own version, first seen Sep 24, 2026
- krishhgg/better-forktheir own version, first seen Sep 24, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- kgarg2468/better-fork★ 4same name
- krishhgg/better-fork★ 4same name
- corygabrielsen/skills★ 1same name
- jinjan21-lgtm/fork★ 1same name
- moxclaw/fork-skill★ 1same name
- niftymonkey/skills★ 1same name
- alexandrosandre/agentic-engineering★ 0same name
- bragoatski/fork-for-agents★ 0same name
- loredotlink/lore-plugin★ 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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apexSkill
- api-genSkill
- assets-pipelineSkill
- brainstormSkill
- debugSkill
- deep-updateSkill
- deploy-checkSkill
- depsSkill
- docs-genSkill
- e2e-testsSkill
- env-setupSkill
- featureSkill
- fixSkill
- meta-promptSkill
- migrateSkill
- onboardSkill
- oneshotSkill
- perfSkill
- prdSkill
- qualitySkill
- refactorSkill
- reviewSkill
- saas-initSkill
- schema-genSkill
- scope-taskSkill
- session-startSkill
- stripeSkill
- ui-auditSkill
- uiSkill
- variationsSkill
The file
Files
Arguments
repo: URL GitHub du repo à forker (ou nom court ex: "shadcn/ui")goal: Ce qu'on veut en faire / les modifications à apporter
Instructions
Phase 1 — Évaluer le Repo
Avant de cloner, vérifier via sous-agents :
Agent WebSearch :
- License compatible ? (MIT, Apache = OK, GPL = attention)
- Dernière activité ? (> 6 mois sans commit = risque)
- Stars / forks / issues ouvertes ?
- Stack compatible avec la nôtre ?
Agent WebFetch (README du repo) :
- Quelles features sont déjà implémentées ?
- Quelles sont les dépendances ?
- Comment le setup ?
Phase 2 — Cloner et Explorer
git clone [repo] [nom-projet]- Lancer
/onboardpour scanner le projet cloné - Lancer
/onboardpour comprendre la structure - Identifier les fichiers à modifier vs ceux à garder tel quel
Phase 3 — Plan de Customisation
Via EnterPlanMode, planifier :
## Ce qu'on garde
- [liste des features/fichiers à conserver]
## Ce qu'on modifie
- [feature] → [modification]
- [UI] → [nouveau design]
## Ce qu'on ajoute
- [nouvelle feature]
- [intégration]
## Ce qu'on supprime
- [feature inutile]
- [pages/routes non nécessaires]Phase 4 — Exécuter
- Supprimer le code inutile d'abord (réduire la surface)
- Rebrander (nom, logo, couleurs, textes)
- Modifier les features existantes
- Ajouter les nouvelles features
- Tester le tout
Phase 5 — Nettoyer
- Supprimer l'historique git du projet original :
rm -rf .git && git init - Mettre à jour le README
- Mettre à jour le
package.json(nom, version, description) - Vérifier les licenses et attributions
/deploy-check
Anti-Patterns
- Ne PAS forker un projet plus complexe que ce qu'on a besoin
- Ne PAS garder du code qu'on ne comprend pas
- Ne PAS ignorer la license
- Préférer les projets avec une architecture propre (plus facile à modifier)
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.

