tools-only/X-Skills - Página 8

add-molab-badge

Add "Open in molab" badge(s) linking to marimo notebooks. Works with READMEs, docs, websites, or any markdown/HTML target.

Idioma do texto original: inglês

agent-skill-creator

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow,…

Idioma do texto original: inglês

databricks-apps

Build apps on Databricks Apps platform. Use when asked to create dashboards, data apps, analytics tools, or visualizations. Invoke BEFORE starting implementation.

Idioma do texto original: inglês

databricks

Databricks CLI operations: auth, profiles, data exploration, and bundles. Contains up-to-date guidelines for Databricks-related CLI tasks.

Idioma do texto original: inglês

review-orchestrator

Orchestrates the full kernel patch review workflow across multiple agents

Idioma do texto original: inglês

design-postgis-tables

Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications

Idioma do texto original: inglês

report-aggregator

Aggregates per-file analysis results and generates review-inline.txt and review-metadata.json

Idioma do texto original: inglês

p1-plugin-validator-pre-commit-output-is-too-noisy

Running `prek --all-files` produces pages of plugin-validator output — every file in the repo gets validated, and pre-existing warnings/errors (broken links, SK006 complexity, missing trigger phrases) for files unrelated to the current change drown out…

Idioma do texto original: inglês

sam-human-escalation-criteria

Define explicit triggers for escalating to human at each stage (not just Discovery). When should agents block and ask vs attempt repair vs fail?

Idioma do texto original: inglês

improve-processes

Process quality methodology for the process-siren agent — use before or during Mermaid conversion when the source process shows ambiguity, missing decisions, undefined actors, vague conditions, or structural weakness. Provides triage sequence, excellence…

Idioma do texto original: inglês

johnw

Write in John Wiegley's authentic voice. Use when drafting technical articles, blog posts, essays, or any written material that should read as if John wrote it himself. Captures patterns from 1,100+ posts spanning 1992-2026 across both technical (newartisans)…

Idioma do texto original: inglês

ra-aid

RA.Aid (pronounced "raid") is a standalone autonomous software development assistant built on LangGraph's agent-based task execution framework. It implements a three-stage architecture (Research,...

Idioma do texto original: inglês

openhands-open-platform-for-cloud-coding-agents

OpenHands is an open-source, model-agnostic platform for building and deploying AI coding agents. It provides a composable Python SDK, CLI, and cloud infrastructure for running agents that write...

Idioma do texto original: inglês

microsoft-graphrag

GraphRAG is a modular graph-based Retrieval-Augmented Generation (RAG) system developed by Microsoft Research. It extracts meaningful, structured data from unstructured text using LLMs to create a...

Idioma do texto original: inglês

copier-astral-python-project-template-with-astral-toolchain

copier-astral is an opinionated Copier template for bootstrapping Python projects using Astral's modern toolchain. It provides batteries-included project scaffolding with linting (ruff), type...

Idioma do texto original: inglês

micro-agent

Micro-Agent is a flexible, extensible Python agent framework designed to provide intelligent agent capabilities as a callable service layer for upstream applications. The "Micro" naming mirrors...

Idioma do texto original: inglês

claude-quickstarts

Claude Quickstarts is the official Anthropic repository of deployable reference applications built on the Claude API. Each project is a self-contained, runnable implementation demonstrating a...

Idioma do texto original: inglês

bifrost-ai-gateway

Bifrost is a high-performance open-source AI gateway written in Go that unifies access to 20+ LLM providers through a single OpenAI-compatible API. Benchmarked at <100 µs overhead per request at 5,000 RPS, it provides automatic failover, adaptive load…

Idioma do texto original: inglês

create-plan

MUST CALL FIRST for multi-step tasks! If user request needs 2+ tool calls (like 'open + search + screenshot'), call create_plan BEFORE any other tool.

Idioma do texto original: chinês

add-new-entry

Workflow and tools for adding new entries from temp.md to the section files. Includes legend format, section reference, code tools, and common pitfalls. USE FOR: Adding new resources to the knowledge base. DO NOT USE FOR: Editing existing entries or…

Idioma do texto original: inglês

lp-agent

Run automated liquidity provision strategies on concentrated liquidity (CLMM) DEXs using Hummingbot API.

Idioma do texto original: inglês

connectors-available

Check which exchanges work from your location and search for tokens with trading rules (min order size, price increment, order types).

Idioma do texto original: inglês

4-report-assembler

Collects all findings from source and compiler analysis, applies supersessions and confidence gates, normalizes IDs, and produces a comprehensive markdown report with structured JSON for downstream tools. Supports dual-mode invocation: interim (findings.json…

Idioma do texto original: inglês

5-poc-generator

Crafts bespoke proof-of-concept programs demonstrating that zeroize-audit findings are exploitable. Reads source code and finding details to generate tailored PoCs — each PoC is individually written, not templated. Each PoC exits 0 if the secret persists or 1…

Idioma do texto original: inglês

2-source-analyzer

Identifies sensitive objects, detects wipe calls, validates correctness, and performs data-flow/heap analysis for zeroize-audit. Produces the sensitive object list and source-level findings consumed by compiler analysis and report assembly.

Idioma do texto original: inglês

3-tu-compiler-analyzer

Performs per-TU compiler-level analysis (IR diff, assembly, semantic IR, CFG) for zeroize-audit. One instance runs per translation unit, enabling parallel execution across TUs.

Idioma do texto original: inglês

3b-rust-compiler-analyzer

Performs crate-level MIR and LLVM IR analysis for Rust in zeroize-audit. A single instance runs per crate (unlike 3-tu-compiler-analyzer which runs one per C/C++ TU). Detects dead-store elimination of wipes, stack retention, and other compiler-level…

Idioma do texto original: inglês

0-preflight

Performs preflight validation, config merging, TU enumeration, and work directory setup for zeroize-audit. Produces merged-config.yaml, preflight.json, and orchestrator-state.json.

Idioma do texto original: inglês

5c-poc-verifier

Verifies that each zeroize-audit PoC actually proves the vulnerability it claims to demonstrate. Reads PoC source code, finding details, and original source to check alignment between the PoC and the finding. Produces poc_verification.json consumed by the…

Idioma do texto original: inglês

2b-rust-source-analyzer

Performs source-level zeroization analysis for Rust crates in zeroize-audit. Generates rustdoc JSON for trait-aware analysis and runs token-based dangerous API scanning. Produces sensitive objects and source findings consumed by rust-compiler-analyzer and…

Idioma do texto original: inglês

deep-research-main

This skill should be used when a user requests deep research on any topic. Example queries include "/deep-research", "deep research on", "리서치해줘", "딥리서치", "심층 연구", "[주제]에 대해 리서치해줘".

Idioma do texto original: inglês

deep-research-query

This skill should be used when a user wants to build a structured research query interactively before starting deep research. Example queries include "/deep-research query", "리서치 쿼리 만들어줘", "research query builder", "structured research query", "쿼리 빌더".

Idioma do texto original: inglês

interview-openspec

Create OpenSpec artifacts (proposal, specs, design, tasks) through Socratic interview. Use when starting a new OpenSpec change that needs structured requirements elicitation.

Idioma do texto original: inglês

gemini

Send work to Gemini CLI in headless mode. Use when the user wants to run prompts, pipe content, or parse output through `gemini -p`.

Idioma do texto original: inglês

codex

Send work to Codex CLI in non-interactive mode. Use when the user wants to run prompts, pipe content, or parse output through `codex exec`.

Idioma do texto original: inglês

iterate-pr

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Idioma do texto original: inglês

sports-news

Sports news via RSS/Atom feeds and Google News. Fetch headlines, search by query, filter by date. Covers football news, transfer rumors, match reports, and any sport via Google News. Use when: user asks for recent news, headlines, transfer rumors, or articles…

Idioma do texto original: inglês

tennis-data

ATP and WTA tennis data via ESPN public endpoints — tournament scores, season calendars, player rankings, player profiles, and news. Zero config, no API keys. Use when: user asks about tennis scores, match results, tournament draws, ATP/WTA rankings, tennis…

Idioma do texto original: inglês

nhl-data

NHL data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, injuries, transactions, futures, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about NHL scores, standings, team…

Idioma do texto original: inglês

mlb-data

MLB data via ESPN public endpoints — scores, standings, rosters, schedules, game summaries, play-by-play, win probability, injuries, transactions, depth charts, team/player stats, leaders, and news. Zero config, no API keys. Use when: user asks about MLB…

Idioma do texto original: inglês