Menu
O SkillsMP coletou 44 skills de firstbatchxyz/kai. Abra uma skill para revisar a origem e os detalhes.
Mostrando 40 de 44 skills coletadas.
Inspect and analyze codebases using pygount for LOC counting, language breakdown, and code-vs-comment ratios. Use when asked to check lines of code, repo size, language composition, or codebase stats.
Idioma do texto original: inglês
Set up GitHub authentication for the agent using git (universally available) or the gh CLI. Covers HTTPS tokens, SSH keys, credential helpers, and gh auth — with a detection flow to pick the right method automatically.
Idioma do texto original: inglês
Production-grade PR review with execution-verified suggestions. Reads repository conventions, history, and security surfaces before reviewing. For every suggested fix, attempts to compile and test it in the sandbox — the comment includes proof. Modelled on…
Idioma do texto original: inglês
Create, manage, triage, and close GitHub issues. Search existing issues, add labels, assign people, and link to PRs. Works with gh CLI or falls back to git + GitHub REST API via curl.
Idioma do texto original: inglês
Open and manage GitHub pull requests through Kai MCP tools — propose changes, monitor CI, iterate on failures, and merge. No git tokens are shared to the sandbox; every GitHub operation goes through the backend via the workspace's GitHub App installation.
Idioma do texto original: inglês
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
Idioma do texto original: inglês
One-time repository onboarding for PR review — builds a RepoProfile (conventions, hot files, security surfaces, nit catalogue, test command) stored as workspace learnings. Re-runs automatically when the profile is stale (>30 days or >30% of files changed).
Idioma do texto original: inglês
Manage AWS services for ML workflows including S3, ECR, SageMaker, and EC2
Idioma do texto original: inglês
Browse, download, and deploy models, datasets, and spaces on HuggingFace Hub
Idioma do texto original: inglês
Define, deploy, and inspect Modal — serverless GPU functions, endpoints, volumes, and existing workspace deployments; also the default GPU runtime for Kai evaluators
Idioma do texto original: inglês
Manage GPU pods, deploy serverless endpoints, and run inference workloads on RunPod
Idioma do texto original: inglês
Track experiments, log metrics and artifacts, and compare runs with Weights & Biases
Idioma do texto original: inglês
Write, test, and upload custom evaluators for code optimization — the fitness functions that drive optimization quality, including the Modal-first GPU evaluator pattern
Idioma do texto original: inglês
Get the LLM models for evolutions from the workspace agent subscription tier config
Idioma do texto original: inglês
Full code optimization workflow - from analyzing code to running optimization and reviewing results
Idioma do texto original: inglês
Produce or update the workspace brief — load context, identify focus repo + user lean, cross-reference activity into Kai-relevant action items, synthesize, save
Idioma do texto original: inglês
Daily autonomous work cycle — check workspace state, propose tasks, execute approved work, save a dashboard briefing
Idioma do texto original: inglês
Seed Kai's memory on a fresh local install — infer who the user is and what the project(s) are from the workspace + git (single repo or a multi-repo parent dir), ask only what can't be inferred, and commit durable facts via the memory tool so future sessions…
Idioma do texto original: inglês
Kai joins the team — onboards through GitHub data (repos, team, recent PRs, branches, conventions), then publishes an initial briefing with proposed action items
Idioma do texto original: inglês
Analyze AWS costs, find waste, and recommend optimizations using read-only MCP tools
Idioma do texto original: inglês
Monitor and analyze AWS infrastructure performance using read-only MCP tools
Idioma do texto original: inglês
Set up automated recurring code audits and optimization monitoring with cron jobs
Idioma do texto original: inglês
How to use Kai platform tools — LOAD THIS FIRST before running any audit, optimization, or repo management operation
Idioma do texto original: inglês
Monitor Railway projects, diagnose deployment failures, and audit infrastructure using read-only MCP tools
Idioma do texto original: inglês
Analyze Vercel serverless functions, identify expensive code, and optimize it via Kai Evolve
Idioma do texto original: inglês
Autonomous periodic codebase hygiene — find structural problems (redundant helpers, dead code, incomplete features, premature abstractions, inconsistent patterns) and propose focused fixes as GitHub issues
Idioma do texto original: inglês
Fast, opinionated first-pass assessment of a connected repo — stats, security surface, code health, architecture, AI code smell — delivered as a severity-ranked report with actionable follow-ons
Idioma do texto original: inglês
Research and explain Kai outputs - find academic papers, benchmarks, and prior art that explain WHY results work
Idioma do texto original: inglês
Full code audit workflow - from adding a repo to reviewing vulnerabilities and filing issues
Idioma do texto original: inglês
Run a local kai-security audit with the security_scan plugin tool and act on the findings (local-first, no cloud backend)
Idioma do texto original: inglês
Detect codebase patterns — commit velocity anomalies, codebase drift, and dependency risks — and persist them as workspace learnings
Idioma do texto original: inglês
Prioritize and explain security vulnerabilities found by Kai scans with research context
Idioma do texto original: inglês
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Idioma do texto original: inglês
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Kai Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool…
Idioma do texto original: inglês
Edit PDFs with natural-language instructions using the nano-pdf CLI. Modify text, fix typos, update titles, and make content changes to specific pages without manual editing.
Idioma do texto original: inglês
Extract text from PDFs and scanned documents. Use web_extract for remote URLs, pymupdf for local text-based PDFs, marker-pdf for OCR/scanned docs. For DOCX use python-docx, for PPTX see the powerpoint skill.
Idioma do texto original: inglês
Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.
Idioma do texto original: inglês
Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Use the Python DDGS library or CLI to search, then web_extract for full content.
Idioma do texto original: inglês
Query Polymarket prediction market data — search markets, get prices, orderbooks, and price history. Read-only via public REST APIs, no API key needed.
Idioma do texto original: inglês
Use when completing tasks, implementing major features, or before merging. Validates work meets requirements through systematic review process.
Idioma do texto original: inglês