dk-breadcrumb-creator
A kit for building with AI agents — not just the orchestration, but also the engineering patterns around it.
★ 22
⑂ 0
Browse and Install AI Agent Skills
Parcourez et installez des milliers de compétences pour AI Agents dans le répertoire Killer-Skills. Compatible avec Claude Code, Windsurf, Cursor et plus.
This directory brings installable AI Agent skills into one place so you can filter by search, category, topic, and official source, then install them directly into Claude Code, Cursor, Windsurf, and other supported environments.
LIVE
4170
Compétences Disponibles
Directory Recovery Priorities
Organic recovery should flow through fewer, stronger, first-party entry points instead of a flat bulk-skill corpus.
P0 hub
Collections Hub
Curated collection pages carry clearer topical scope, stronger first-party framing, and safer canonical signals than bulk skill listings.
P0 guide
Installation Docs
Installation docs prove the site offers first-party setup guidance, not just discovery wrappers.
P0 collection
Agent Workflow Building Tools
A workflow-first collection that explains why related skills belong together and what job they solve.
P1 collection
Top Claude Code Skills
A platform-specific collection for one of the clearest demand clusters in the product ecosystem.
P1 collection
Top Windsurf Skills
A platform collection that turns IDE demand into a stronger curated hub.
P1 collection
Gemini Workflow Tools to Install First
A Gemini-specific collection that turns compatibility research into a curated install path for real delivery teams.
P1 collection
Python Workflow Tools to Install First
A Python engineering collection built for teams choosing installable workflow helpers instead of browsing raw packages.
P1 collection
TypeScript Workflow Tools to Install First
A typed-development collection that helps product teams shortlist TypeScript workflow tools with clear next steps.
4170 compétences disponibles
plugins-guide
Best practices for working with plugins in the kcosr/assistant repository.
★ 22
⑂ 0
monitoring
Surveillance des tâches Hawk : processus de surveillance des tâches en cours ou terminées dans le cloud
★ 22
⑂ 0
styling
Esposter UnoCSS Attributify Mode styling conventions — prop-based attributes for all static styles, flex not d-flex, class only for dynamic or Vuetify-specific utilities. Apply when writing .vue or .scss files.
★ 22
⑂ 0
gastown-operator
Kubernetes operator for Gas Town multi-agent orchestration. OpenShift-native, FIPS-compliant.
★ 22
⑂ 0
github-issue-triage
For humans, a language is a tool for expression. For AIs, it's a substrate for reasoning.
★ 22
⑂ 0
animate
Design engineering skill for AI Agents — build interfaces with craft-level quality
★ 22
⑂ 0
Benchmark Manager
Le Gestionnaire de Benchmark est un outil pour gérer les évaluations AILANG
★ 21
⑂ 0
update-dependencies
Update project dependencies to their latest compatible versions with verification. Use when the user asks to update, upgrade, or bump dependencies.
★ 21
⑂ 0
vue-best-practices
Comprehensive Vue 3 development best practices, TypeScript configuration, tooling troubleshooting, testing patterns, and composition API gotchas. Covers vue-tsc, Volar, Vite configuration, Vue Router typing, component testing, reactivity patterns, and SFC features. Use when working with Vue 3 + TypeScript projects, debugging build errors, writing tests, or following best practices.
★ 21
⑂ 0
debug-stuck-eval
Debug stuck Hawk/Inspect AI evaluations. Use when user mentions stuck eval, eval not progressing, eval hanging, samples not completing, eval set frozen, runner stuck, 500 errors in eval, retry loop, eval timeout, or asks why an evaluation isnt finishing.
★ 21
⑂ 0