ariegoldkin/claude-forge
53 skills
$npx skills add ariegoldkin/claude-forgeSkillInstalls
agent-browserHeadless browser automation via the agent-browser CLI — snapshot + @ref workflow, ~200-400 tokens/interaction vs Playwright MCP.agent-loopsAgentic workflow patterns — ReAct agents, plan-and-execute, self-correcting validation, sliding-window memory, and replanning.agentationVisual feedback tool for AI agents \u2014 CSS selector capture, DOM context, QA bug reports, and UI reviewai-native-developmentBuild AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows (ReAct, multi-agent, Opus 4.5), LLM integration, prompt…architecture-decision-recordArchitecture Decision Records — Nygard templates, context/decision/consequences, lifecycle, and trade-off evaluation.archive-handoffsArchive old handoff files to maintain a clean continuity directory. Use when handoffs accumulate.archive-ledgerArchive old ledger sections to reduce file size. Use when ledger exceeds 500 lines.atlassian-integrationJira and Confluence integration via MCP (28 tools). Create/update/transition issues, manage Confluence pages, JQL/CQL queries, sprint planning, and URL…audit-skillAudit a SKILL.md against the repo's Skill Authoring Rules and emit candidate flags for human review — CSO compliance, >150-line progressive-disclosure review,…auto-researchAutonomous goal-driven orchestrator. Classifies a natural-language goal, routes it to the right etk/ctk skill, confirms the plan, and executes.brainstormingRefine ideas into actionable designs via Socratic questioning (simple mode) or parallel multi-agent analysis (--deep).cavemanUltra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy.check-maintenanceCheck continuity system health and file integrity. Use for periodic maintenance checks.cmuxDrive the cmux native macOS terminal app (third-party, manaflow-ai/cmux) from its CLI or Unix socket — workspaces, panes, surfaces, WKWebView browser…coaching-conversation-patternsAI coaching & conversational support — empathetic interactions, safety guardrails, motivational interviewing, SMART goals, crisis handling.continuity-managementMulti-session state preservation and context management. Covers save-state, create-handoff, resume-session, check-maintenance, archive, metrics, and setup.continuity-metricsView session status and continuity metrics. Use to check current session state.coverGenerate, execute, and heal test suites across unit, integration, and E2E tiers.create-handoffEnd session properly by creating a handoff document. Use when finishing work or before long breaks.development-pipelineGuided 6-phase development pipeline: Gate, Design, Hypothesize, Plan, Build (TDD), Verify.doctorCross-plugin system diagnostics for the claude-forge ecosystem.embeddingsText embeddings for semantic search and similarity. Covers model selection (OpenAI text-embedding-3, nomic-embed), chunking strategies, batch processing,…evidence-verificationEvidence-based verification — test results, coverage metrics, build artifacts, deployment health checks before marking tasks done.experimentAutonomous metric-driven iteration loop. Modify code, measure a metric, keep improvements, discard regressions via git rollback.fix-bugObservation-driven debugging loop (OHAOI): Observe, Hypothesize, Act, Iterate. Investigates root cause before fixing.function-callingLLM function calling and tool use patterns. Covers JSON tool schemas (strict mode), execution loops, structured output with Pydantic, parallel tool calls, and…golden-datasetGolden dataset curation, backup/restore, validation with schema checks, duplicate detection, and coverage analysishipaa-compliance-checkerHIPAA compliance validation — health data handling, API security, data privacy, and security gap identification.investigate-sentryInvestigate and triage Sentry issues with structured analysis.langfuse-observabilityLLM observability with Langfuse — tracing, evaluation, prompt versioning, cost tracking, and LLM-as-judge scoringlanggraphLangGraph workflow patterns for stateful multi-step LLM workflows.llm-patternsLLM application patterns for evaluation, streaming, and testing.multi-agent-orchestrationMulti-agent fan-out/fan-in workflows — supervisor delegation, conflict resolution, and parallel research pipeline synthesisnotebooklmGoogle NotebookLM programmatic access — create notebooks, manage sources (URLs, PDFs, YouTube, Drive), generate audio/video/slides/quizzes, and chat with…ollama-localLocal LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction.pgvector-search(Aspirational) Production hybrid search with PGVector + BM25 using Reciprocal Rank Fusion, metadata filtering, and performance optimization for semantic…prepare-prAuthor a standardized, structured MR/PR description — Background (need / before / after / related flows), High-Level Design (API/Infra/Schema/UI/Data change…prompt-cachingProvider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for…quality-gatesComplexity assessment and quality gates for task planning — 1-5 scoring, information gathering, escalation triggers.rag-retrievalRAG pipeline patterns for grounded LLM responses. Covers basic retrieval, citations, hybrid search (semantic + keyword with RRF), context window management,…resume-sessionLoad previous context from handoffs and ledger. Use when starting a new session or returning after a break.review-mrComprehensive MR/PR review with quality checks, domain-aware parallel agents, structured confidence scoring, evidence gating, composite grading, and YAML+MD…salesforce-integration-patternsSalesforce CRM integration — bidirectional sync, case management, webhooks, bulk operations, SOQL queriessave-stateUpdate project ledger with current state. Use periodically to preserve context before compaction.scope-checkEnumerate ticket acceptance criteria before code changes — fetches ticket via Jira/GitHub MCP, extracts AC bullets/sub-tasks/checkboxes, emits a checklist to…semantic-cachingRedis semantic caching for LLM apps — vector similarity matching, multi-level cache, TTL strategies, cache warmingsetup-context-monitorConfigure the StatusLine-based context percentage monitor. Use when setting up context window warnings for the first time.setup-continuityInitialize the continuity system for a new project. Use when setting up continuity for the first time.setup-pre-commitSet up Husky pre-commit hooks with lint-staged (Prettier or Biome), type checking, and tests in the current repo.streaming-api-patternsReal-time streaming with SSE, WebSockets, ReadableStream — backpressure, reconnection, and LLM streaming patternstool-wrapper-patternsPatterns for CLI tool wrapper skills — auto-context, setup verification, output budgeting, error enrichment.verifyRun tests, linting, and type checking with structured evidence collection. Auto-detects project stack (Node, Python, Rust).zoom-outForce a higher-abstraction explanation of the current code region — modules, callers, glossary vocab.