sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Write and maintain Architecture Decision Records (ADRs) for the atlas project. Covers ADR format, where to store them, when to create one, and examples based on past decisions. Use when making a significant technical decision that should be recorded for future maintainers.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Add a new MCP tool to the atlas-fs or atlas-rag server. Covers tool definition, handler function, parameter schema, and register call. Use when implementing a new feature that needs to be exposed as an MCP tool.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Build the portable RAG bundle: clone docs, chunk, embed, package tarball. Use when the task involves building a bundle locally (atlas-build), smoke testing a bundle (atlas-smoke), or adding a new publication.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Manage CI bundle releases: manual dispatch, tag naming, monitoring the build-bundle workflow, promoting a release, and rolling back. Use when releasing a new bundle, debugging a CI failure, or rolling back to a previous bundle.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Aggressive optimization patterns for atlas. Overrides standard Python defaults with zero-dep, startup-time, and memory-efficient alternatives. Honed for a project that runs a read-only parquet-backed RAG bundle loaded into numpy at startup and queried via MCP. Use when making any code change — these patterns take…
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Evaluate RAG quality: run Precision@10 and MRR against a bundle, interpret the scores, and compare CI-built vs locally-built bundles. Use when assessing bundle quality, comparing backends, or investigating a regressed search result.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Enforce consistent Python code style across the project. Covers import ordering, string quoting, naming conventions, docstring format, and recommended linter setup. Use when writing new code, reviewing PRs for style, or configuring a linter.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Python observability patterns including structured logging, metrics, and distributed tracing. Use when adding logging, implementing metrics collection, setting up tracing, or debugging production systems.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Python resilience patterns including automatic retries, exponential backoff, timeouts, and fault-tolerant decorators. Use when adding retry logic, implementing timeouts, building fault-tolerant services, or handling transient failures.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Test conventions for the atlas project: pytest setup, fixture patterns, mocking external dependencies, and smoke test patterns. Use when writing new tests, setting up test infrastructure, or debugging a test failure.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Enforce consistent type hint usage across the atlas project. Covers annotation style, from future import annotations, Literal and Protocol patterns, TYPECHECKING for optional dependencies, and recommended type checker config. Use when writing or reviewing type annotations.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Patterns for keeping READMEs accurate as code evolves. Focused on structural consistency, not prose style. Use when editing a README with ASCII tree diagrams, version callouts, config examples, or cross-document line ranges. Avoids generic "write clearly" advice — targets the concrete rot patterns that accumulate in…
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
sagar-shirwalkar/servicenow-atlas
Agent Codex
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
sagar-shirwalkar/servicenow-atlas
Agent Codex
Compare two outputs WITHOUT knowing which skill produced them.
sagar-shirwalkar/servicenow-atlas
Agent Codex
Evaluate expectations against an execution transcript and outputs.
sagar-shirwalkar/servicenow-atlas
Skill Claude CodeCodex
Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.
sagar-shirwalkar/collibra-atlas
Skill Claude CodeCodex
Compact the current conversation into a handoff document for another agent to pick up. Use when the conversation grows large, at task completion, or before context compaction. Branches: write-handoff (create a new handoff), read-handoff (load the latest).
sagar-shirwalkar/collibra-atlas
Skill Claude CodeCodex
Build a local-first AI knowledge layer (Atlas) for any markdown documentation corpus via two MCP servers (filesystem + RAG). Use when the user wants to create an Atlas system for a new documentation source - e.g., build an Atlas for Kubernetes docs, create a knowledge layer for OpenStack docs, set up dual MCP servers…
sagar-shirwalkar/collibra-atlas
Skill Claude CodeCodex
Review a diff, pull request, or code change for correctness, security, performance, and maintainability. Use when asked to review code, check a PR, audit a change, or vet a contribution.
sagar-shirwalkar/collibra-atlas
Skill Claude CodeCodex
Navigate and understand Collibra's LLM-friendly documentation structure. Use when the user asks about Collibra docs organization, needs to find specific pages, wants to understand the llms.txt structure, or plans to build an Atlas for Collibra docs. Branches: explore-structure (map the doc index), find-pages (locate…