AI & ML

sontek Skill

Draft a post-meeting follow-up email in John Anderson's voice as Founder of Drape — the CI Brain, a CI reliability platform — grounded in the actual meeting notes from Google Docs (Google Drive). Use when sending a follow-up after a call or meeting; pulls the notes doc so the email is specific, not boilerplate. Applies a Win Without Pitching posture and the Four Conversations model. Family: sales-email-draft / sales-email-prospect / sales-email-followup / sales-email-reply.

zate Skill

Run a security assessment using deterministic static analysis tools with LLM-powered triage

zate Bundle

Generate diagrams using Mermaid syntax -- the most LLM-friendly text-based diagram format. Use when the diagram-router selects Mermaid, or when diagrams will live in GitHub/GitLab markdown, documentation, or when quick generation with broad diagram type coverage is needed. Renders natively on major platforms.

arcblock Bundle

Discover and safely route work inside a compatible web or content workspace. Use when an agent enters through a voice session, local directory, MCP resource, AFS mount, or fresh checkout and must identify project instructions, authoritative facts, local skills, content storage, locale rules, and validation gates before drafting, editing, or handing off work.

rafaelramosdf Bundle

Guia para criar servidores MCP (Model Context Protocol) de alta qualidade que permitem que LLMs interajam com serviços externos através de ferramentas bem projetadas. Use ao construir servidores MCP para integrar APIs ou serviços externos, seja em Python (FastMCP) ou Node/TypeScript (MCP SDK).

rafaelramosdf Bundle

Aplica as cores e tipografia oficiais da marca Anthropic a qualquer tipo de artefato que possa se beneficiar da aparência e sensação da Anthropic. Use quando cores da marca ou diretrizes de estilo, formatação visual ou padrões de design da empresa se aplicarem.

ed3dai Skill

Use to decide what kind of generic agent you should use

ed3dai Skill

Use when the user wants to review a Claude Code session for quality — analyzes the current session (or a specified transcript path) for prompting effectiveness, agent performance, and environment gaps, producing actionable recommendations

ed3dai Bundle

Use when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a final Summarizer subagent with task tracking and failure recovery

zate Skill

This skill should be used when building, creating, or modifying any CLI tool or command-line application in any language or framework. The convention is language-agnostic. Reference implementations for Go (Cobra), Python (Click), Rust (Clap), Node (Commander) included but the pattern applies to any CLI framework (argparse, Thor, Picocli, Commander, etc.). Provides the --agent-help convention: structured, token-minimal help output that LLM agents can parse efficiently. Use when adding help text, designing CLI command structure, creating a new command-line tool, adding subcommands, implementing --help, or making CLI tools usable by AI agents.

snits Skill

Use only for a current operative request that explicitly invokes /roborev-fix, or a direct Agent Hook instruction; do not invoke from literal syntax in quoted, pasted, or historical text

snits Skill

Use when creating an evaluator or judge prompt for agent outputs — a rubric, scoring scheme, quality score, acceptance criteria for a generate-critique-revise loop, or a Workflow verify stage. Also use when an existing loop shows scores rising without real improvement, a judge growing lenient across iterations, or a request for "one overall score" or "give the judge the full conversation".

closedloop-technologies Bundle

Run You.com Research API or You.com MCP-backed deep research with explicit research_effort and cost controls. Use when a task needs You.com research, ARI-style workflows, finance research options, or benchmark comparison.

closedloop-technologies Bundle

Run OpenAI deep research models through the Responses API with explicit effort, model, cost, and output controls. Use when launching citation-backed OpenAI research runs, smoke-testing OpenAI provider behavior, or capturing reproducible benchmark output.

closedloop-technologies Bundle

Run Hugging Face Smolagents as a code-as-action deep research agent with optional web search and model backends. Use when a benchmark needs explicit intermediate tool actions, code execution, or an open-source agent framework.

truchot Bundle

Expert intégration IA/ML dans applications web - LLMs, RAG, vector databases, embeddings. Utilise ce skill quand: (1) intégration API OpenAI/Claude/Mistral, (2) mise en place RAG, (3) vector databases, (4) prompt engineering, (5) fine-tuning, (6) ML ops et déploiement modèles.

closedloop-technologies Skill

Recombine proven parts of multiple evaluated attempts into a coherent follow-up attempt. Use when ClimbHill attempt comparison reveals complementary partial wins.

closedloop-technologies Bundle

Run GPT Researcher as a self-hosted open-source deep research framework using an LLM plus a search provider. Use when a task needs inspectable local report generation, configurable retrievers, or comparison against commercial research APIs.

closedloop-technologies Skill

Analyze ClimbHill runs, attempts, lineage, costs, failures, and recurring constraints. Use for experiment-history diagnosis and evidence-backed follow-up proposals.

closedloop-technologies Skill

Ground implementation decisions in recorded ClimbHill resources and cited prior work. Use when code changes should trace back to research, guidance, postmortems, or experiment evidence.

closedloop-technologies Skill

Classify proposed paths and enforce denied or approval-required ClimbHill policy before edits. Use when work may touch tests, CI, infrastructure, secrets, or other protected surfaces.

closedloop-technologies Skill

Coordinate independent, bounded coding attempts against one goal and compare them after policy and evaluation checks. Use for parallel ClimbHill improvement attempts.

closedloop-technologies Skill

Produce evidence-backed run and attempt reports with evaluations, costs, risks, and promotion recommendations. Use at the end of a ClimbHill run or attempt attempt.

closedloop-technologies Skill

Sample successful and failed historical ClimbHill Attempts before planning new work. Use when prior Runs may contain reusable approaches or known failure modes.

closedloop-technologies Skill

Review policy, evaluations, cost, lineage, and risk before recording a human promotion or rejection decision. Use when a ClimbHill attempt is ready for disposition.

closedloop-technologies Skill

Convert evidence-backed ClimbHill experiment findings into reviewable GitHub issue proposals. Use after experiment-tree analysis identifies actionable repository improvements.

closedloop-technologies Skill

Prepare a repository for controlled recursive optimization by defining goals, agent guidance, policies, evaluations, resources, and protected surfaces. Use when a codebase lacks ClimbHill support files.

closedloop-technologies Skill

Prepare a repository with goals, agent guidance, policies, evaluations, resources, and protected surfaces for controlled optimization. Use when setting up or auditing ClimbHill support files.

snits Skill

Use when creating or iterating on a design in a claude.ai/design project via the claude-design MCP server, before calling any mcp__claude-design__ tools.

snits Bundle

Expert guidance for designing, implementing, migrating, and debugging SwiftData persistence in Swift and SwiftUI apps. Use when working with @Model schemas, @Relationship/@Attribute rules, Query or FetchDescriptor data access, ModelContainer/ModelContext configuration, CloudKit sync, SchemaMigrationPlan/history APIs, ModelActor concurrency isolation, or Core Data to SwiftData adoption/coexistence.

ikram-alam Bundle

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.

openaec-foundation-erpnext-anthropic-claude-development-skil Bundle

Use when debugging Frappe errors, using bench console for live inspection, analyzing tracebacks, or reading Frappe log files. Prevents wasted debugging time from ignoring log context, misreading tracebacks, and not using bench console effectively. Covers bench console, frappe.logger, error log DocType, traceback analysis, common error patterns, log file locations, pdb/debugger integration, VS Code DAP, profiling, Frappe Recorder, mariadb diagnostics. Keywords: debug, bench console, traceback, error log, frappe.logger, pdb, debugging, log analysis, inspect, VS Code, DAP, profiling, recorder, mariadb, monitor, ERPNext error, how to debug, find the bug, what went wrong, stack trace, error message..

openaec-foundation-erpnext-anthropic-claude-development-skil Bundle

Use when migrating a Frappe app between major versions, detecting breaking API changes, or resolving post-migration errors. Prevents failed migrations from undetected deprecated APIs, removed methods, and changed function signatures. Covers breaking change detection v14-v15-v16, deprecated API mapping, migration checklist, common migration errors, automatic fix suggestions. Keywords: migration, version upgrade, breaking changes, deprecated API, v14, v15, v16, migrate, compatibility, upgrade ERPNext, version change breaks, after update errors, deprecated method..

openaec-foundation-erpnext-anthropic-claude-development-skil Bundle

Use when designing multi-app Frappe architectures, deciding whether to split functionality into separate apps, or implementing cross-app communication patterns. Prevents monolithic app sprawl, circular dependencies between apps, and broken override chains. Covers multi-app architecture decisions, app dependency management, cross-app hooks, override patterns, when to split vs extend, shared DocType strategies. Keywords: architecture, multi-app, app splitting, cross-app, dependencies, override, extend, monolith, modular, how to structure frappe apps, when to split apps, app design, multi-app planning..

truchot Bundle

Expert Expérience Client pour transformer les livrables internes en communications client de qualité. Utilise ce skill quand: (1) un livrable doit être transmis au client, (2) rédaction d'emails ou rapports orientés client, (3) traduction du jargon technique en langage business, (4) suivi et fidélisation client, (5) validation de la qualité des communications sortantes, (6) accompagnement du client à chaque phase du projet.

ikram-alam Bundle

Design and implement memory architectures for agent systems. Use when building agents that need to persist state across sessions, maintain entity consistency, or reason over structured knowledge.