AI & ML

frankxai-ai-architect-academy Bundle

Build autonomous AI agents using Claude Agent SDK with computer use, tool calling, MCP integration, and production best practices

iamjcabalejo Bundle

Apply PostgreSQL best practices for schema design, indexing, transactions, vector search (pgvector), and RAG pipelines. Use when designing schemas, writing queries, optimizing performance, implementing semantic search, or building RAG applications with PostgreSQL. Use with database-expert for query optimization and DBA-level tuning.

iamjcabalejo Skill

Write reliable Playwright E2E tests with Page Object Model, stable selectors, and proper waits. Use when creating or maintaining E2E tests with e2e-runner.

iamjcabalejo Skill

Orchestrate the compounding development cycle (Plan → Code → Review/Test → Plan) with strict phase rules and automatic mode switching (ASK → PLAN → AGENT). Use when running project-manager command, delegating to implementation/review agents, or ensuring handoffs follow the rule’s Mode transition guide.

matheusallvarenga Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

robbyt Bundle

This skill should be used when working with SwiftData — @Model definitions, @Query, @Relationship, ModelContext, ModelContainer, schema migration, Swift 6 concurrency, performance optimization, or architecture review. Also triggers on: "SwiftData audit", "@Model issues", "SwiftData crashes", "predicate problems", "background context patterns", "N+1 queries", "SwiftData vs SQLiteData vs GRDB", "CloudKit sync with SwiftData", "SwiftData migration fails", or "SwiftData migration diagnostics". Covers auditing existing code, writing new SwiftData code, migration debugging, and architecture review.

iamjcabalejo Skill

Writes high-quality skills, agent definitions, and workflows for AI to follow. Use when asked to create or refine technical skills, agent workflows, automation instructions, or SKILL.md/agent.md content that must follow strict rules, styles, coding patterns, and philosophy for maximum reliability and clarity.

abivan-tech Skill

Durable project-memory rules for `.agent-memory/` plus session-memory boundaries.

abivan-tech Skill

Multi-Model Code Review: consensus-based analysis patterns, consolidation methodology, conflict resolution, and false positive triage.

roasbeef Skill

Turns an observed agent misbehavior, or a correction the user just gave, into a durable fix: a hook that makes the behavior impossible, a CLAUDE.md rule, a change to the skill that was running, or a new reusable skill. Picks the narrowest home that removes the failure mode, checks for an existing rule to tighten before adding one, and keeps CLAUDE.md from bloating. Invoked via /codify when an agent goes off the rails on something the user does not want repeated.

roasbeef Skill

On-demand consultation of a higher-tier model (Opus 4.8 or Fable 5) from a cheaper executor session. Emulates the native advisor-tool pattern in Claude Code: keep the main loop on a cheap model (Sonnet 5) and call the expensive model rarely, via a focused consultation packet, for a plan/decision/'what am I missing' — not for code. Use when the executor is stuck, before committing to a plan, after repeated failed attempts at the same fix, or before a risky/irreversible change. Invoked via /advisor or when the executor recognizes a consult checkpoint.

arcasilesgroup Bundle

Reasons about trust boundaries, authentication, data, dependencies, skills and supply chain, runs the scanners this repository already pins, and reports PASS, FAIL or INCOMPLETE with the command behind each one. Trigger for "threat model this", "is this auth safe", "review the trust boundary", "audit these dependencies", "can this skill be made to do something else". Not for judging a diff on its merits — use /ai-review, whose security lens does that. Not for accepting a risk — use `ai-eng accept`, which needs a named person, a reason and an expiry. It replaces neither the guards nor CI, and it never declares compliance with anything.

arcasilesgroup Bundle

Turns a plan — one written here, one pasted from a chat, one another agent produced — into the review surface the human actually reads: the plan's own Markdown, carrying visual blocks the renderer turns into diagrams, file maps, decision tables and open questions, handed over as one page whose link opens in the browser. Trigger for "make this plan visual", "I want to see the plan before I approve it", "turn this pasted plan into something reviewable". Not for writing the tasks themselves — use /ai-plan, which owns what the plan says. Not for judging what a change did — use /ai-visual-recap.

samuelgursky Skill

Tightening one long single-take recording — talking-head, screencast, tutorial, podcast video — by removing dead air in the DaVinci Resolve MCP. Apply when asked to tighten a recording, remove silences or dead air, cut the pauses out of a long take, or turn a raw one-take recording into a first cut. The subtractive counterpart to resolve-rough-cut, which selects shots from many clips; this skill removes time from one clip.

harivansh-afk Skill

Interactive planning agent. Designs verification specs through Q&A with the human. Uses Oracle for complex planning. Hands off to orchestrator for execution.

abivan-tech Skill

Review routing, independent post-implementation review gates, multi-model escalation, and targeted optimization follow-up.

abivan-tech Skill

Model Kotlin persistence code correctly for Spring Data JPA and Hibernate. Covers entity design, identity and equality, uniqueness constraints, relationships, fetch plans, and common ORM (Object-Relational Mapping) traps specific to Kotlin. Use when creating or reviewing JPA (Java Persistence API) entities, diagnosing N+1 or LazyInitializationException, placing indexes and uniqueness rules, or preventing Kotlin-specific bugs such as data class entities and broken equals/hashCode.

clyra-ai Bundle

Run a profile-driven evidence-based OSS/product readiness audit across product model, onboarding, architecture, DX, security, release readiness, and market wedge.

clyra-ai Bundle

Analyze Codex/agent review comments on one or more PRs, triage what should be implemented, and provide a clear implementation recommendation list for the user.

roasbeef Skill

Design and review CLIs for AI agent consumption. Covers machine-readable output, input hardening against hallucinations, schema introspection, context window discipline, dry-run safety rails, and skill file packaging. Use when building new CLIs, adding agent support to existing CLIs, reviewing CLI designs for agent compatibility, or wrapping APIs as CLI tools. Triggers: agent CLI, CLI for agents, machine-readable CLI, agent-first CLI, CLI agent DX.

roasbeef Skill

This skill provides agent mail management via the Subtrate command center. Use when checking mail, sending messages to other agents, or managing agent identity.

roasbeef Bundle

Expensive planner (Opus 4.8 / Fable 5) decomposes a task into independent work items, a fleet of cheap Sonnet 5 (or Haiku 4.5) workers executes them in parallel via a Workflow, and the planner synthesizes the results. Emulates the native orchestrator pattern in Claude Code: keep the expensive model scarce (one planning pass, one synthesis pass) and the cheap model abundant (N parallel workers). Prefers a deterministic dynamic workflow when available; falls back to in-instance Task dispatch. Use when the user types /orchestrate or asks to decompose, fan out, or parallelize a task across independent workers.

roasbeef Skill

Final adversarial audit of finished work by one top-tier model (Fable 5 or Opus 4.8), in a single report-only pass across three axes: verify the load-bearing invariants (especially any you could NOT run locally), simplify without losing properties, and hunt for live variants of the bug shapes just fixed. You then verify each finding and act. Use as the closing gate on a substantive or risky change before calling it done, especially when part of it (a systest, a migration, a concurrency path) can't be validated locally. Distinct from /advisor (decision consult), /review-loop (multi-agent fix loop), and /variant-analysis (single-pattern sweep). Invoke via /advisor-review or after finishing hard-to-verify work.

gar-ai Bundle

Port HuggingFace models to Candle with correct tensor naming. Use when debugging weight loading errors or matmul issues.

helius-labs Bundle

Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using the Helius blog, SIMDs, and Agave/Firedancer source code.

helius-labs Bundle

Build Solana applications with Helius infrastructure. Covers transaction sending (Sender), asset/NFT queries (DAS API), real-time streaming (WebSockets, Laserstream), event pipelines (webhooks), priority fees, wallet analysis, and agent onboarding.

helius-labs Bundle

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, the DFlow Agent CLI for autonomous trading, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.

helius-labs Bundle

Build Solana trading applications combining DFlow trading APIs with Helius infrastructure. Covers spot swaps (imperative and declarative), prediction markets, real-time market streaming, Proof KYC, the DFlow Agent CLI for autonomous trading, transaction submission via Sender, fee optimization, shred-level streaming via LaserStream, and wallet intelligence.

harvard-lil Bundle

Helps someone create a new pedagogical AI skill from scratch. Triggers when the user wants to write a SKILL.md, build a new skill for the Legal Ed Skills Hub, design an AI-assisted learning experience, or turn a teaching approach into an agent skill. No technical expertise required.

harvard-lil Bundle

Reviews and evaluates an existing SKILL.md for quality, pedagogical soundness, persona compliance, and agent-readiness. Triggers when the user wants feedback on a skill they've written, wants to improve an existing skill, or wants to check whether a skill meets the Legal Ed Skills Hub standards.

harvard-lil Bundle

Always-on assistant for creating, reviewing, and testing pedagogical AI skills for the Legal Ed Skills Hub. Triggers on writing new skills, reviewing skill quality, evaluating skill pedagogy, testing skills against rubrics, defining evaluation criteria, or any task related to building and improving agent skills for legal education.

constructive-io Bundle

All search strategies — tsvector full-text, BM25, trigram, pgvector semantic, PostGIS spatial, unified composite search, and RAG patterns. Use when asked to 'add search', 'full-text search', 'tsvector', 'BM25', 'trigram', 'pgvector', 'PostGIS', 'unified search', 'searchScore', 'unifiedSearch', 'semantic search', 'vector search', 'spatial search', 'RAG search', or when working with Search* blueprint nodes or graphile-search adapters.

constructive-io Bundle

Multi-tenancy, memberships, invites, entity types, entity-scoped storage, agent modules, and namespace modules. Use when asked to 'create entity types', 'add channels/teams/data rooms', 'provision entity storage', 'entity-scoped buckets', 'agent_module', 'namespace_module', 'invite users', 'profile assignment', 'memberships', 'multi-tenancy', 'org-scope', 'app-scope', or when working with entity_types in blueprints.

evolv3-ai Skill

Speeds up pi_agent_rust development and verification workflows. Use when editing providers, tools, sessions, extensions, installer/uninstaller logic, or triaging regressions in this repo.

constructive-io Skill

Constructive platform architecture: core model, platform baseline, endpoint map, control plane vs data plane tokens, provisioning flow, data-module/policy pairing, and Authz policy types. Load for the platform mental model before schema or provisioning decisions.

constructive-io Bundle

Model Constructive application data through the SDK: tables, fields, relations, constraints, indexes, enums, views, identity columns, temporal and exclusion constraints, and database provisioning inputs. Use when creating or changing a schema, defining keys and referential actions, configuring view security, or working with metaschema operations.