Top Agent Skills

Diagnoses Redpanda broker and cluster health using debug bundles, metrics endpoints, logs, CPU profiling, and partition/raft checks, with triage playbooks for common failure modes.

Streams Salesforce change data capture and platform events into Redpanda or Kafka using Redpanda Connect's salesforce_cdc input, covering setup, configuration, and operational details.

Diagnose Salesforce Flows that fail to run, produce wrong results, or error out, using debug mode, interview logs, fault emails, and test suites.

Designs bulk-safe, limit-aware Apex transactions to prevent Salesforce governor limit errors, covering SOQL, DML, CPU, heap, and async patterns.

Designs and reviews schedule-triggered flows for recurring automation, covering bounded record selection, idempotent processing, and escalation to Apex when volume is too high.

Guides using the lightning-record-picker base component for single-record selection in LWC, covering display-info, matching-info, graph-QL filters, and accessibility.

Configure and troubleshoot Lead or Case assignment rules in Salesforce, including rule entries, queue vs user assignment, trigger contexts, and round-robin patterns with Apex.

Query healthcare-specific SObjects and use the FHIR R4-aligned Healthcare API, including bundle limits and authentication differences.

Maps FHIR R4 clinical resources (Patient, Observation, Condition, CarePlan, CodeableConcept) to Salesforce Health Cloud objects, including prerequisite configuration and cardinality handling.

Design and deploy Salesforce restriction rules to subtract record access from users, covering eligibility, criteria syntax, metadata shape, and documented enforcement gaps.

Guides Apex exception handling design: catching expected failures, bulk DML semantics, boundary-specific error translation, and logging once at the right layer.

Build, review, or troubleshoot Lightning Web Components that run inside Salesforce Flow screens, covering @api properties, FlowAttributeChangeEvent, validate(), and navigation events.

Configures and troubleshoots Salesforce CPQ Guided Selling, covering Quote Process and ProcessInput setup, field mirroring, search types, and Auto Select Product behavior.

Implements inbound email processing in Apex: parsing messages, creating or updating records, handling attachments, and configuring Email Service routing.

Writes Apex that calls Field Service Lightning scheduling APIs to book, schedule, grade, or optimize service appointments programmatically, including transaction-splitting patterns to avoid callout-DML conflicts.

Configures and troubleshoots Copado Essentials deployment pipelines in Salesforce, covering user stories, branches, promotion paths, conflict resolution, and deployment modes.

Deploy and scale Python AI/ML workloads on Modal's serverless cloud, including GPU compute, web endpoints, scheduled jobs, and persistent storage.

Manages a long-term Markdown knowledge base for software projects, capturing architecture, decisions, and conventions in `.lore/` with commands to init, sync, query, audit, compress, and mirror to platform files.

Automates scientific research workflows from data analysis to publication, orchestrating multiple agents for hypothesis generation, methodology development, computational experiments, and LaTeX paper writing.

Implements a feature phase by phase from a phased JSON or Markdown plan, with configurable unit-test and quality-gate choices per phase, token-budgeted execution, resumable state, and TDD handoff.

Turns a brainstorm document into a structured software requirements specification with actors, features, business rules, and non-functional requirements.

Implements backend source code from BA, TechLead, and PM artifacts, generating files, .env.example, and pr-description.md while enforcing security rules.

Generates an IEEE 830 software requirements specification from raw client input through structured clarification rounds and a review gate.

Genera reportes profesionales en HTML, PDF y Markdown, con tablas, gráficos y conclusiones, para presentar análisis de forma clara y reproducible.

Guides creating clean, reproducible Jupyter notebooks with structured workflows, best practices, and IPython magic for analysis and presentation.

Coordinates startup operations by routing CEO, marketing, sales, launch, and social media tasks to specialized sub-skills, using a project knowledge base and frameworks like OKR and RICE.

Names content by three coordinates: millisecond timestamp, SHA-256 hash, and optional human petname. Verifies content integrity, timestamps events, and maintains a local content store searchable by time, hash, or human words.

Fetches and summarizes the latest ORF news in German, focusing on Austrian and international politics, and generates a themed studio image.

Deploy static websites to IPFS with a single command using the PinMe CLI, auto-detecting the build directory and returning a preview URL.

Generates structured VGL JSON prompts for Bria's FIBO image generation models, covering text-to-image, editing, inpainting, outpainting, and captioning with a deterministic schema.

Query Google Analytics 4 (GA4) data via the Analytics Data API. Use when you need to pull website analytics like top pages, traffic sources, user counts, sessions, conversions, or any GA4 metrics/dimensions. Supports custom date ranges and filtering.

Enables AI agents to post, reblog, tag, and interact on the moltr social platform via a CLI tool, with feeds, discovery, asks, and profile management.

Converts Markdown files to PDF, DOCX, or HTML with table of contents, custom fonts, Mermaid diagrams, and web article downloading.

Connects agents to the GSTD Grid via MCP tools for autonomous payments, task discovery, and shared knowledge storage.

Manage Jira issues, boards, sprints, and projects via the jira-cli. Search, create, update, and transition issues directly from the command line.

Interact with the Plaid finance platform via a CLI to link institutions, fetch account balances, and query transactions by date range.

Manage Loom video recordings via the Loom API, including listing, retrieving details and transcripts, updating, deleting, and fetching analytics.

Builds a personal knowledge base for capturing and retrieving understanding, with structured namespaces for concepts, tools, patterns, and references.

Registers an AI agent on the Kradleverse platform, checking existing credentials, verifying name availability, and saving the API key locally.

Extracts YouTube video transcripts and produces structured summaries with main points, key arguments, and conclusions.

Operates the PWDEV Flow semantic audit trail: enable, record, query, summarize, or verify JSONL workflow events with integrity checks.

Routes legacy PWDEV Code command intents to their canonical PWDEV Flow skills, preserving history when adopting an existing .planning workspace.

Adversarially verify an implementation against its objective, acceptance criteria, definition of done, and prohibitions using fresh evidence. Use for completion gates, release readiness, or independent verification after implementation and review.

Refactors production code with test coverage using a TDD workflow that applies approved refactorings one at a time, gates each on passing tests, and commits or reverts accordingly.

Generates a comprehensive ONBOARDING.md for a codebase, covering architecture, key files, setup, and common gotchas.

Remove AI writing patterns from prose by cutting filler phrases, breaking formulaic structures, and enforcing active voice and specificity.

Runs a post-launch review of a shipped PRD against its success metrics, interviewing the user on metric movement, assumptions, and decisions, then publishing an outcome-review page to Confluence and updating linked artifacts.

Provides notes and a workflow for opening a brokerage account online from mainland China, including required documents and funding details.

Search the web, scrape pages, crawl sites, and interact with dynamic content via the Firecrawl CLI, returning clean markdown for LLM contexts.

Performs AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter, providing grounded answers with source citations.

Automates bulk pickup from plus.keria.cc.cd by submitting codes to a multipart form, downloading the resulting ZIP, and unpacking it locally with a choice of plus_json or sub2api output bundles.

Ingests music into a LanceDB via ncmdump-rs and sf-cli, searching and downloading from Netease Cloud Music or Bilibili, decrypting local NCM files, and extracting metadata, lyrics, and cover art.

Queues many Codex auth JSON files through a public batch submission API to create pending account-contribution requests for later admin review, with dry-run support and rate-limit handling.

Takes raw whole-genome sequencing FASTQ files or a pre-existing VCF through variant calling, quality control, and polygenic risk score computation using the PGS Catalog.

Authenticate, browse pipelines, samples, and projects, upload data, launch pipeline executions, and check run status on any Flow.bio instance via CLI.

Queries 9 genomic databases in parallel for a given rsID, returning unified GWAS, PheWAS, eQTL, and fine-mapping reports.

Predicts chromatin state across 919 tracks (histone marks, DNase, TF binding) for DNA sequences via the hosted Genomic Intelligence API, producing a report and JSON results.

Drafts a LaTeX paper section by section from an outline, with venue-specific templates and citation management.

Design and implement AWS architectures with best practices for IAM, S3, Lambda, DynamoDB, and serverless deployments.

Provides guidance and best practices for working with Ansible, covering core concepts, patterns, troubleshooting, and deployment strategies.