GitHub
X/Twitter via bird CLI. Use when user mentions Twitter, X, tweeting, posting, reading tweets, or wants to check their feed. Includes /twitter-digest for curated feed filtering. (user)
Skills IA Bases de données
Découvrez les skills Bases de données, comparez leurs dépôts et consultez leurs instructions.
Catégories: Bases de données
Bases de données Effacer les filtres
Explorer
GitHub
evergreen
Principles for creating evergreen notes - atomic, lasting insights that compound over time. Use when discussing note quality, what makes a good evergreen note, or the "only what was explored" principle. Tool-ag...
GitHub
shipany-page-builder
Create new dynamic pages from a short spec (keywords, route/path, reference content).
GitHub
docs-writer
Writes and maintains project documentation in markdown
GitHub
code-search
Searches code for patterns, keywords, function names, or text
GitHub
blog-ops
Operations for managing the blog, including creating posts, updating snapshots, and verifying deployments.
GitHub
file-finder
Quickly finds files by name or pattern in the codebase
GitHub
deps
Checks and manages project dependencies
GitHub
runner
Runs project commands like test, build, lint, and dev server
GitHub
code-quality
Reviews code for best practices, refactoring opportunities, complexity, and dead code
GitHub
env-check
Verifies environment setup, configs, and system requirements
GitHub
git-helper
Performs git operations like status, diff, log, and branch management
GitHub
git-worktree-guide
Git worktree management with the `wt` script for simplified create, list, switch, and delete operations. Includes comprehensive guidance on best practices and troubleshooting.
GitHub
codebase-conventions
Load when starting work in 10x-Mapmaster or when unsure about project standards. Covers file organization, naming conventions, type constraints, SQL style, and project-specific limits (200-char descriptions, an...
GitHub
edge-functions
Use when working with Deno edge functions, LLM integration, or embedding generation. Load for Deno.serve patterns, Zod request validation, OpenRouter LLM calls, and error handling. Covers function structure, CO...
GitHub
task-planning
Use after proposal approval to break work into 2-5 minute tasks with exact file paths and code examples. Each task must be completable by an agent with zero context. Do NOT use before proposal is approved.
GitHub
openspec-apply
Use when implementing an APPROVED OpenSpec change. Read tasks.md and follow EXACTLY. Do not deviate, add features, or skip tasks. Use with test-tdd for each code task.
GitHub
maplibre-camera
Use when implementing map camera animations (flyTo, easeTo, jumpTo), handling zoom transitions, or managing bearing/pitch. Load for useMapCamera composable patterns, preventing camera feedback loops, promise-ba...
GitHub
postgres-vectors
Use when working with embeddings, semantic similarity, vector search, or the operators. Load for pgvector queries, HNSW index creation, embedding storage, or similarity calculations. Covers distance operato...
GitHub
maplibre-layers
Use when adding map layers, managing GeoJSON sources, styling markers, or handling layer interactions. Load for layer registration patterns, markRaw usage, MglGeoJsonSource components, data-driven styling, and...
GitHub
config-tuning
Use when you notice a pattern that should be in the config. Analyzes current setup, researches best practices, and proposes specific config changes. Also use when asked to improve agent behavior or workflows.
GitHub
openspec-propose
Use when adding features, changing behavior, or modifying architecture. Creates change proposal with specs and tasks. ALWAYS ask for approval before proceeding to implementation. Do NOT use for bug fixes or tri...
GitHub
brainstorming
Use when request is vague, complex, or needs design exploration BEFORE implementation. Ask questions one at a time. Do NOT use for clear, mechanical tasks. Output: design ready for OpenSpec proposal.
GitHub
executing-tasks
Use when working through any task checklist (not just OpenSpec). Complete one task, verify, mark done, then next. No skipping, no adding, no reordering.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.