Claude Skills by vamseeachanta

Sub-skill of discipline-refactor: Verification Checklist.

Audit and consolidate hidden folders in a repository. Identifies duplicates,

Sub-skill of hidden-folder-audit: Best Practices.

Sub-skill of hidden-folder-audit: Common Hidden Folders Reference.

Sub-skill of hidden-folder-audit: Migrate .agent-os to .Codex (+4).

Sub-skill of hidden-folder-audit: Pre-Audit (+6).

Sub-skill of hidden-folder-audit: specs/archive/ (+1).

'Sub-skill of hidden-folder-audit: Step 1: Inventory All Hidden Folders

Sub-skill of hidden-folder-audit: Verify Hidden Folder State (+3).

Sub-skill of hidden-folder-audit: Version Metadata.

Reorganize a repository from flat structure to a module-based 5-layer architecture (src/tests/specs/docs/examples) while preserving git history. Use when restructuring a codebase into modules, migrating import paths, cleaning up hidden folders, consolidating duplicate directories, removing root-level artifacts, or archiving completed plan files. Capabilities: parallel agent spawn strategy, hidden-folder consolidation patterns, benchmark fixture separation, 4-phase atomic commit workflow.

Sub-skill of repo-cleanup: 1. Build Artifacts (+5).

Systematic cleanup of repository clutter including build artifacts, duplicates,

Sub-skill of repo-cleanup: Agent Directories (+4).

Sub-skill of repo-cleanup: Best Practices.

Sub-skill of repo-cleanup: Common Hidden Folders (+2).

Sub-skill of repo-cleanup: Conflict Resolution Patterns (+2).

Sub-skill of repo-cleanup: Folders to DELETE (Confirmed Safe) (+3).

Sub-skill of repo-cleanup: For Tracked Files (Use git rm) (+2).

Sub-skill of repo-cleanup: Gitignore Updates.

Sub-skill of repo-cleanup: List Untracked Files (+3).

Sub-skill of repo-cleanup: Pre-Cleanup (+7).

Sub-skill of repo-cleanup: Progress Tracking Commands (+1).

Sub-skill of repo-cleanup: References to Remove.

Sub-skill of repo-cleanup: Structure Section Updates (+1).

Sub-skill of repo-cleanup: Version Metadata.

Collaborative design refinement through iterative questioning. Use for

Sub-skill of brainstorming: Best Practices.

Sub-skill of brainstorming: Error Handling.

Sub-skill of brainstorming: Metrics.

Legal Sanity Review Workflow — mandatory pre-gate in the cross-review cycle

Reads quota state and recommends optimal Codex/Codex/Gemini allocation

Run quota-aware but spend-forward Codex/Codex/Gemini batches when provider credits are not the bottleneck and the goal is durable plan/review/execution throughput across machines.

Execute Gemini research tasks in efficient batches using hermes router to maximize $20/month quota utilization. Covers toolset config, batch patterns, sandbox pitfalls, and cleanup.

Quick provider/model switching for Hermes CLI — aliases, fallbacks, task routing matrix, and utilization audit pattern.

Build and operate a computable readiness matrix that connects raw-data-to-GTM package stages with Codex/Codex/Gemini dispatch lanes and weekly credit pacing.

Guide AI model selection based on task complexity, cost constraints, and latency requirements

Optimize AI usage efficiency through script-first patterns, batch operations, and input preparation

LLM prompt management and evaluation platform. Version prompts, run A/B

LLM application patterns, prompt optimization techniques, and AI-powered

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

Build production-ready LLM applications with chains, agents, memory,

Conversational data analysis using natural language queries on pandas DataFrames. Use when you want to ask plain-English questions about data, generate charts, explain transformations, or build exploratory analysis interfaces — all powered by an LLM backend. Supports OpenAI, Anthropic, Google Gemini, Azure OpenAI, and local models. Handles single DataFrames (SmartDataframe) and multi-table joins (SmartDatalake).

Comprehensive prompting techniques including chain-of-thought, few-shot,

Class-level provider/session operations for Codex, Codex, Gemini, Hermes, quotas, audit exporters, readiness dispatch, and utilization scorecards.

Refresh provider quota snapshots and generate a weekly Codex/Codex/Gemini utilization scorecard grounded in quota data when available and session-activity fallback when not.

Class-level Codex/Codex/delegate_task agent operations: background execution, stdin/print stalls, plugin IDs, worker patch loops, and fallback routing.

Delegate coding tasks to Codex (Anthropic's CLI agent). Use for building features, refactoring, PR reviews, and iterative coding. Requires the Codex CLI installed.

Fix Codex plugin update failures caused by using the short plugin name instead of the installed plugin id and wrong scope.

Recover delegated Codex print-mode runs that stall silently or produce partial edits in large worktrees.