Extract 2–12 epics (depending on complexity) for an idea using concept_summary.md as the semantic anchor (writes to ideas/<IDEA_ID>/runs and updates ideas/<IDEA_ID>/latest)

epic-initializer

Epic and task structure patterns for SpecFlux. Use when breaking PRDs into epics and tasks. Epics should be self-contained with clear acceptance criteria.

Guide on testing with Vitest and Playwright for Epic Stack

Validate epics_backlog.md for an idea against concept_summary.md (writes report to ideas/<IDEA_ID>/runs and updates ideas/<IDEA_ID>/latest; optional patch if allowed)

Epistemological tracking system for managing facts, conclusions, and provenance chains with Git integrity and semantic search. Integrates with Quarto for visual provenance analysis. Use when analyzing data from multiple sources, conducting research, working with metrics/surveys, making data-driven conclusions, or tracking complex findings. Triggers on data analysis (analyze data, metrics, survey, research, findings, insights), conclusions (conclude, recommend, decide, infer), quantitative work (percentage, trend, correlation, statistic), source attribution (according to, based on, from source), or any epistemological tracking. Skip for trivial calculations.

Discipline epistemique stricte pour eliminer les derives cognitives de Claude. Activation SYSTEMATIQUE sur TOUTES les conversations. Impose: (1) Zero invention/supposition, (2) Honnetete absolue, (3) Vision holistique avec relecture du contexte, (4) Questions plutot que suppositions, (5) Remise en contexte perpetuelle avec checkpoints structures, (6) Documentation incrementielle sans doublons, (7) Vigilance workflow/CI-CD/securite, (8) TODO/plan obligatoire avant tout travail, (9) Documentation FR/EN scholar style signee Julien GELEE, (10) Zero credentials/API keys/donnees sensibles en clair. Posture ingenieur generaliste specialise IA.

Run EPUBCheck and Ace accessibility validation. Use before final EPUB packaging or distribution to ensure publication readiness.

Expert in EqualizerAPO configuration file format, parsing, and generation. Use when implementing EAPO config import/export, adding support for new filter types, or debugging config file issues.

Use when you have validated symmetry groups and need to design neural network architecture that respects those symmetries. Invoke when user mentions equivariant layers, G-CNN, e3nn, steerable networks, building symmetry into model, or needs architecture recommendations for specific symmetry groups. Provides architecture patterns and implementation guidance.

Intelligent agent for interpreting vague ERPNext development requests and producing concrete technical specifications. Use when receiving unclear requirements like 'make invoice auto-calculate', 'add approval workflow', 'sync with external system'. Triggers: user gives vague requirement, need to clarify scope, translate business need to technical spec, determine which ERPNext mechanisms to use, create implementation plan.

Implementation workflows and decision trees for Frappe hooks.py configuration. Use when determining HOW to implement doc_events, scheduler_events, override hooks, permission hooks, extend_bootinfo, fixtures, and asset includes. Covers V16 extend_doctype_class. Triggers: how do I hook, which hook to use, doc_events vs controller, override doctype, extend doctype class, permission hook, scheduler job, cron task, fixtures export.

Implementation workflows and decision trees for Jinja templates in ERPNext/Frappe. Use when determining HOW to implement Print Formats, Email Templates, Portal Pages, or custom Jinja methods. Covers template type selection, context variables, styling, and V16 Chrome PDF rendering. Triggers: create print format, email template, portal page, custom jinja filter, print format styling, pdf template, invoice template, report template.

Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience. Masters error correlation, cascade prevention, and automated recovery strategies across multi-agent systems with focus on minimizing impact and learning from failures.

Context-aware debugging that learns from past solutions. When an error occurs:

Use when user needs complex error pattern analysis, distributed system debugging, error correlation, root cause discovery, or predictive error prevention across microservices.

Advanced error analysis and pattern detection specialist for identifying, analyzing, and preventing software errors

>

Expert in error handling, Error Boundaries, Sentry integration, logging strategies, error recovery, user-friendly error UI, and debugging tools

A guide to using ERT (Emacs Lisp Regression Testing) for testing Emacs Lisp code.

Use when stuck in circles and want to hand off to another agent (Codex CLI) with full context

Defining clear ownership models and escalation procedures to ensure incidents are handled by the right people at the right time.

Adapt escape room games for global markets (English, Korean, Japanese) with cultural considerations, efficient translation workflows, and language-agnostic design strategies. Handles multilingual template creation, cultural adaptation, and localization testing. Use when preparing games for international audiences or implementing multi-language support.

Use when eSLint configuration including config files, extends, plugins, and environment setup.

Use when custom ESLint rules and plugins including rule development, AST traversal, and publishing.

Use when eSLint built-in rules including rule configuration, severity levels, and disabling strategies.

ESP32 Integrated Development Framework documentation. Covers I2S, GPIO, FreeRTOS, peripherals, and ESP32S3-specific APIs.

Designs and implements Extract, Transform, Load pipelines for data processing

eval-recipes-runner

EvalKit is a conversational evaluation framework for AI agents that guides you through creating robust evaluations using the Strands Evals SDK. Through natural conversation, you can plan evaluations, generate test data, execute evaluations, and analyze results.

Measure model performance on test datasets. Use when assessing accuracy, precision, recall, and other metrics.

Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.

Two-stage paper screening - abstract scoring then deep dive for specific data extraction

Evaluate RAG systems with hit rate, MRR, faithfulness metrics and compare retrieval strategies. Use when testing retrieval quality, generating evaluation datasets, comparing embeddings or retrievers, A/B testing, or measuring production RAG performance.

Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.

Build systematic evaluation frameworks for LLM applications.

Comprehensive EVE Online project management and ESI integration toolkit. Use when updating, auditing, or integrating ESI into EVE Online projects like EVE_Rebellion, EVE_Gatekeeper, EVE_Ships, or any EVE-related development. Triggers on project updates, ESI integration, compliance checking, asset management, or multi-project coordination.

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.

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

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.

Web research using Exa AI search engine. Use when: user needs web search, finding articles, research papers, news, company info, or similar content. Triggers on: 'search for', 'find articles about', 'research', 'what's the latest on', 'find companies like', 'similar to [url]'.

Process exam/test paper documents from DOCX format into structured markdown. Use when Claude needs to: (1) Extract exam content from Word documents (.docx), (2) Analyze images in exam papers using vision tools, (3) Convert questions to structured markdown with proper image references, (4) Understand question context to match images with appropriate questions, (5) Create organized exam output with YAML frontmatter and sections

Example custom Skill demonstrating template generation and best practices. Use this as a reference when creating your own custom Skills.

When the user has an Excel file with incomplete data that needs to be populated by searching for and extracting specific information from external sources. This skill is triggered by requests to fill missing columns in spreadsheets, batch data enrichment tasks, or when working with structured data that requires additional research to complete. It handles Excel file discovery, reading existing data, writing new data to specific cells, and maintaining data integrity across multiple rows.

Import Excel data into RVT projects. Update element parameters, create schedules, and sync external data sources.

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

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>