build-with-dhiraj/ai-workflow-framework-portability-kit

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

End-to-end pipeline for feeding YouTube channels into the "Connecting Dots" second brain (Dhiraj's JoVE knowledge system): enumerate → pre-flight gate → Apify transcribe → connectyoutube (filter→NER→index→related→[[JoVE]]) → LanceDB queryable → Pinecone archive. Use when the user wants to ingest YouTube…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude Code

Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Runs a question, idea, or decision through 5 AI advisors who answer independently, peer-review each other anonymously, and get synthesized into one verdict by a chairman. Adapted from Karpathy's LLM Council. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Build LLM eval suites, run prompt regression tests, score AI outputs with deepeval. Triggers on "eval this prompt", "build eval suite", "hallucination check".

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex needs its repo

Design and operate loop-engineered agent systems in Claude Code and Cursor. Use for loop engineering, harness design, Ralph loops, /loop, /goal, agent hub, self-improving agents, SKILL.md optimization, or choosing installable loop tooling from the research corpus.

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

End-to-end playbook for moving a full developer + Claude Code environment from one Mac to another under the SAME Claude login — covers both the OLD-Mac backup side and the NEW-Mac restore side. Trigger this whenever the user is getting a new Mac/MacBook, replacing, selling, returning, or factory-resetting their…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Audit and clean the local agent skills directory for necessity and redundancy. Primary governance skill for the library.

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Decides whether new information should be stored in the Obsidian vault (RAM — mutable, evolving content) or in Pinecone (HD — immutable, archive-shaped content) for D Rage's JoVE knowledge system. Apply BEFORE creating any new artifact in the JoVE vault, BEFORE upserting anything to Pinecone, or BEFORE running…

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Migrate test files from as type assertions to @total-typescript/shoehorn. Triggers on "shoehorn", "replace as in tests", or partial test data needs.

build-with-dhiraj/ai-workflow-framework-portability-kit

Skill Claude CodeCodex

Deep, tool-verified Mixpanel expertise for the JoVE org, covering how to actually build and audit dashboards, funnels, Insights queries, and tracking plans through the Mixpanel MCP (Get-Business-Context, Run-Query, Create-Dashboard, Create-Metric, Get-Events, Get-Report, etc). Every claim here was checked against the…