Structure systems around asynchronous, event-based communication to decouple producers and consumers for improved scalability and resilience. Use when building loosely coupled systems with asynchronous message-based communication.

Use when generating branded QR codes for ProductTank SF events - speaker LinkedIn profiles, sponsor websites, or Slack join links. Handles single/bulk generation, correct logo mapping, GDrive upload, and mandatory test-scanning.

Create new event scraping scripts for websites. Use when adding a new event source to the Asheville Event Feed. ALWAYS start by detecting the CMS/platform and trying known API endpoints first. Browser scraping is NOT supported (Vercel limitation). Handles API-based, HTML/JSON-LD, and hybrid patterns with comprehensive testing workflows.

Record domain events and dispatch to inbox handlers for side effects, audit trails, and activity feeds. Use when building activity logs, syncing external services, or decoupling event creation from processing. Triggers on event recording, audit trails, activity feeds, or inbox patterns.

Event-driven design conventions: event envelope, naming, versioning, schema evolution rules, idempotency, ordering/partitioning, retry and dead-letter handling

Use when spec and code diverge - AI analyzes mismatches, recommends update spec vs fix code with reasoning, handles evolution with user control or auto-updates

Review French articles and translate them to English. Use when the user asks to review, check, or translate KB articles.

Search for relevant code snippets, examples, and documentation from billions of GitHub repositories, documentation pages, and Stack Overflow posts. Use this skill when coding tasks require real working code examples, API usage patterns, framework setup instructions, or library implementation details to eliminate hallucinations and provide accurate, token-efficient context.

Retrieve and extract content from URLs with AI-powered summarization and structured data extraction. Use for scraping web pages, extracting specific information, summarizing articles, or crawling websites with subpages.

Process CSV data files by cleaning, transforming, and analyzing them. Use this when users need to work with CSV files, clean data, or perform basic data analysis tasks.

- **Name**: Franklin - Orient Task Force - Rolling Presentation

Provides three production-ready ML training examples (sentiment classification, text generation, RedAI trade classifier) with complete training scripts, deployment configs, and datasets. Use when user needs example projects, reference implementations, starter templates, or wants to see working code for sentiment analysis, text generation, or financial trade classification.

Tests marketplace visibility configurations and catalog tiers (preview catalog only)

Analyze mock data and examples for cultural assumptions, understanding what they communicate about who the product is for. Use when reviewing test data, documentation, or seed data.

A skill for generating Excalidraw-format diagrams from natural language descriptions. This skill helps create visual representations of processes, systems, relationships, and ideas without manual draw

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.

Analyze messy and unstructured Excel files to identify data quality issues, detect format inconsistencies, find missing values, and generate comprehensive analysis reports. Use when Claude needs to work with Excel files (.xlsx, .xls) for data quality assessment, structure analysis, or when users request data auditing, cleaning recommendations, or statistical summaries of spreadsheet data.

Create or resume an execution plan - a design document that a coding agent can follow to deliver a working feature or system change

shannon-execution-verifier

Use to systematically validate documents, stories, or processes against defined checklists. Ensures quality and completeness.

Execute one feature (FEAT-XXX) at a time using docs/forge/ideas/<IDEA_ID>/latest/tasks.md as the source of truth. Creates a short workspace checklist and tracks progress so reruns continue automatically.

<objective>

The ONLY way to interact with existing projects. Load when user references ANY project by name, ID, or number. Includes: continue, resume, status, progress, check, review, work on [existing project]. NEVER read project files directly.

Execute approved task specifications sequentially with TDD, comprehensive testing, and validation. This skill should be used for implementing tasks from approved specs with full audit trail.

This skill should be used when executing tasks from ai-state/active/tasks.yaml sequentially. It loads tasks, gathers context, implements features with phase-appropriate testing, updates task status in tasks.yaml, organizes tests into ai-state/regressions/ folders, and logs all operations to operations.log. Use after write-plan creates tasks.yaml or when resuming development work.

>

Complete development lifecycle for GitHub/local issues - branch, implement, test, PR, merge with quality gates

Execute a discrete GitHub issue from a detailed plan file (gi_*.md). Use when implementing a specific, well-defined task with an existing implementation plan in doc/plans/issues/. Handles status tracking, verification, and issue lifecycle.

Verification, drift detection, and snapshot logic for executing-plans

Autonomously execute exploratory implementation of one approach from spike definition, working independently until natural stop. Use when partner provides spike definition and assigns you an approach number to explore in isolation, when comparing multiple implementation alternatives, or when evaluating technical feasibility before committing to an approach

Execute tasks from both GitHub issues and Basic Memory artifacts using unified workflow - supports intelligent source detection and dual-channel status management

Handle common execution failures with specialized recovery strategies. Fix syntax errors, import/dependency issues, path/file problems, permission denial, and connection timeouts. Use proactively when encountering errors or as automatic recovery mechanism.

<purpose>

Implement approved plans into production-ready code. Use when user wants to build, implement, code, or execute an approved plan. Activates when user says 'let's build', 'implement this', 'start coding', or 'execute the plan'.

Creates hands-on student exercises and practice activities for learning prompt engineering. Use when the user asks to create student activities, practice exercises, or hands-on learning tasks. Generates exercises with examples, solutions, and differentiation.

Designs deliberate practice exercises applying evidence-based learning strategies like retrieval practice, spaced repetition, and interleaving. Activate when educators need varied exercise types (fill-in-blank, debug-this, build-from-scratch, extend-code, AI-collaborative) targeting learning objectives with appropriate difficulty progression. Creates exercise sets that apply cognitive science principles to maximize retention and skill development. Use when designing practice activities for Python concepts, creating homework assignments, generating problem sets, or evaluating exercise quality.

Break a high-level backlog item into executable sub-items

Working expectations and documentation practices. Use when capturing learnings or understanding how to work with this codebase.

Analyze GRPO training runs for learning dynamics and pipeline performance. Use when diagnosing training issues, reviewing Elo progression, checking throughput, or updating experiment results.

Generates a rigorous experiment design given a hypothesis. Use when asked to design experiments, plan experiments, create an experimental setup, or figure out how to test a research hypothesis. Covers controls, baselines, ablations, metrics, statistical tests, and compute estimates.

Comprehensive guide to A/B testing, multivariate testing, statistical significance, and experiment analysis for data-driven product decisions

>

Do experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling. Use when behavior is uncertain, contested, or performance-sensitive.

Design YAML expertise file structures for agent experts. Use when creating mental models for domain-specific agents, defining expertise schema, or structuring knowledge for Act-Learn-Reuse workflows.

Explain all bluera-base plugin functionality in human-readable format

Explain how code works in detail. Use when trying to understand unfamiliar code, complex logic, or system architecture.

Develop working exploits using pwntools. Includes exploit template and common patterns.

Exploit researcher persona specializing in attack surface analysis, exploit scenario generation, and vulnerability chaining

Interactive code review through conversation. HOUSTON guides review, spawns specialized agents, and helps create Beads for issues found.