data-analysis
173
deep-research
Multi-model deep research with comparative assessment (OpenAI + Perplexity + Gemini). Queries 3 deep research providers in parallel and produces a comparative synthesis.
juanandresgs
data-ai
запрос активен
Поиск skills
Найдите подходящую возможность для вашего агента.
Популярные запросы
Результаты
53,183
skills, соответствующие запросу
Страница
888
из 2660
Запрос
ai
ищите по названию, тегу или описанию
automation-tools
173
dockerfile-generator
Create, generate, or write Dockerfiles and multi-stage Docker images. Containerize apps.
akin-ozer
tools
cli-tools
173
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (`@clack/prompts` and `@clack/core`). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.
pass-agent
tools
data-engineering
172
pipeline
End-to-end processing pipeline that chains the full 6R sequence: seed, reduce, reflect, reweave, verify. Runs per-item or in batch mode. Three depth levels control thoroughness vs. speed. The orchestrator for all processing skills. Triggers on: "pipeline", "process", "full pipeline", "6R"
Miosa-osa
data-ai
framework-internals
172
optimize-protocol
Autonomous framework engineer — reads VibeHQ post-run analysis, understands root causes of multi-agent coordination failures, then designs and implements real code changes (new features, refactors, architectural improvements) to fix them. Not parameter tuning — actual engineering.
0x0funky
development
mobile
172
firebase-swift-best-practices
Expert patterns for Firebase (Auth, Firestore, Cloud Functions) using modern Swift Concurrency (Actors, Async/Await) and Observation (@Observable).
FirebaseExtended
development
scripting
172
unity-development
Use for Unity Editor automation through UniCli in projects where `unicli` is available: running `unicli exec`/`unicli eval`, editing files under `Assets/` or `Packages/`, compiling Unity code, running EditMode/PlayMode tests, and creating or modifying GameObjects, scenes, prefabs, assets, packages, build settings, or project settings. Follow required safeguards such as `AssetDatabase.Import` after file changes and `Compile` verification after C# edits.
yucchiy
development
scripting
172
unity-development
Use for Unity Editor automation through UniCli in projects where `unicli` is available: running `unicli exec`/`unicli eval`, editing files under `Assets/` or `Packages/`, compiling Unity code, running EditMode/PlayMode tests, and creating or modifying GameObjects, scenes, prefabs, assets, packages, build settings, or project settings. Follow required safeguards such as `AssetDatabase.Import` after file changes and `Compile` verification after C# edits.
yucchiy
development
education
172
judge-prompt
Design binary pass/fail LLM-as-Judge evaluators. Structured prompt engineering for evaluation: criteria definition, rubric construction, few-shot calibration, and bias mitigation. Produces a ready-to-deploy judge prompt with scoring instructions. Triggers on: "judge prompt", "llm judge", "evaluator prompt", "scoring prompt", "grading rubric"
Miosa-osa
documentation
bioinformatics
172
self-consistency
Sample multiple paths, select most consistent - +17.9% on GSM8K
Miosa-osa
research
lab-tools
172
validate-evaluator
Calibrate LLM-as-Judge evaluators against human labels. Computes TPR, TNR, precision, recall, F1, and Cohen's kappa. Detects systematic biases and recommends prompt corrections. Produces a calibration report with confidence intervals. Triggers on: "validate evaluator", "calibrate judge", "judge accuracy", "evaluator validation", "judge metrics"
Miosa-osa
research
scientific-computing
172
reduce
Extract atomic insights from raw source material. Takes articles, transcripts, meeting notes, or any unstructured input and produces structured claims with provenance metadata. The foundational extraction step of the 6R processing pipeline. Triggers on: "extract", "reduce", "distill", "summarize source"
Miosa-osa
research
automation-tools
172
deps-update-playbook
Guides dependency updates in `kaizen-design-system`
cultureamp
tools
automation-tools
172
autoresearch
Autonomous iterative improvement loop. Agent modifies code, verifies against metrics, keeps improvements or reverts failures, and repeats. Uses git as memory — each change is committed, measured, and kept or discarded. Runs until a target metric is hit or max iterations reached. Triggers on: "autoresearch", "auto improve", "iterative improvement", "autonomous loop", "hill climb"
Miosa-osa
tools
data-analysis
171
prod-dashboard
Daily consolidation dashboard — reads outputs from all routines (morning, linear, github, community, strategy, meetings, metrics) and generates a unified HTML dashboard. Trigger when user says 'dashboard', 'generate dashboard', 'overview', 'consolidation', or 'general panel'.
EvolutionAPI
data-ai
sql-databases
171
data-write-query
Escreve SQL otimizado para o stack Evolution (PostgreSQL primário) com boas práticas. Use quando precisar traduzir uma necessidade de dados em SQL, construir uma query com múltiplas CTEs, joins e agregações, otimizar uma query contra tabelas grandes, ou obter sintaxe específica para consultas no banco do Evo CRM, Evo AI, ou qualquer serviço do stack Evolution. Dialetos secundários disponíveis: Snowflake, BigQuery, MySQL, DuckDB.
EvolutionAPI
databases
mobile
171
chromium-debug-use
Attach to a user's already-open Chromium-family browser for live inspection and light interaction after explicit local approval
marcusquinn
development
package-distribution
171
release
Prepare a Kora release PR. Bumps Rust crate versions (kora-lib + kora-cli), optionally bumps the TypeScript SDK, generates CHANGELOG, and opens a PR against main. Use when the user says 'prepare a release', 'cut a release', or 'release version X.Y.Z'.
solana-foundation
development
scripting
171
create-routine
Create a new automated routine (ADW) for the scheduler. Guides the user through defining what the routine does, the type (AI or systematic), the schedule, and generates the Python script + Makefile target. Use when the user says 'create a routine', 'add a routine', 'automate this', 'schedule this task', 'new ADW', 'I want this to run automatically', or wants to turn any manual task into a scheduled automation.
EvolutionAPI
development