GoogilyBoogily

56 mods across 1 repository, 2 stars between them.

docs-audit

02

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Audit skills, commands, and agents against the project's docs/ standards (templates.md, best-practices.md, audit-checklists.md). Auto-detects artifact type. Supports single artifact path or batch mode (--all, --type skill|command|agent).

2 3mo ago A 57 tokens original MIT

ai-sdk-expert

05

GoogilyBoogily/googilyboogily-claude-power-tools

Agent

Expert in Vercel AI SDK v5 handling streaming, model integration, tool calling, hooks, and production patterns. Use PROACTIVELY when user mentions AI SDK, streaming responses, useChat, useCompletion, streamText, generateText, generateObject, provider integration (@ai-sdk/), tool calling with Zod schemas, or AI…

2 3mo ago A 77 tokens original MIT

llm-architect

06

GoogilyBoogily/googilyboogily-claude-power-tools

Agent

LLM system architecture specialist. Use PROACTIVELY for RAG pipeline design, prompt engineering architecture, model serving infrastructure, fine-tuning strategies, and LLM application patterns.

2 3mo ago A 41 tokens original MIT

architecture-docs

08

GoogilyBoogily/googilyboogily-claude-power-tools

Plugin Claude Code

ADR, HLD, and LLD pipeline with discuss → research → gather → generate → audit phases, D-XX decision tracking, context isolation, parallel code and web research, interactive issue resolution, goal-backward verification, and cross-session state persistence.

2 3mo ago A tokens not measured original MIT

adr-discuss

09

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Identify gray areas and capture key decisions before writing an Architecture Decision Record. Scouts the codebase, surfaces 3-5 concrete decision points that would change the outcome, and guides the user through each. Outputs a numbered decisions file that feeds into adr-gather and adr-generate.

2 3mo ago A 60 tokens original MIT

adr-generate

10

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Generate an Architecture Decision Record from a gathered context file. Runs with clean context — reads the context file and produces a complete MADR 4.0.0 document. Non-interactive.

2 3mo ago A 42 tokens original MIT

arch-pipeline

11

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Run the full architecture documentation pipeline: ADR discuss → research → gather → generate → audit → HLD(s) discuss → research → gather → generate → audit → LLD(s) discuss → research → gather → generate → audit. Supports 1:N HLDs per ADR and 1:M LLDs per HLD. Each phase runs with clean context isolation. Persists…

2 3mo ago A 95 tokens original MIT

arch-research

12

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Standalone research phase that investigates the implications of architecture decisions. Reads a decisions file from a discuss phase, dispatches parallel code and web research focused on those decisions, and produces a structured RESEARCH.md with comparison tables, 'don't hand-roll' warnings, and confidence-tiered…

2 3mo ago A 60 tokens original MIT

audit-adr

13

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Audit an Architecture Decision Record for MADR 4.0.0 compliance, source integrity, completeness, and internal consistency. Walks through each issue interactively with resolution options including parallel code + web research.

2 3mo ago A 46 tokens original MIT

audit-hld

14

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Audit a High Level Design document for template compliance, source integrity, ADR alignment, architectural completeness, and context fidelity. Walks through each issue interactively with resolution options including parallel code + web research.

2 3mo ago A 44 tokens original MIT

audit-lld

15

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Audit a Low Level Design document for template compliance, source integrity, HLD alignment, implementation readiness, and context fidelity. Walks through each issue interactively with resolution options including parallel code + web research.

2 3mo ago A 45 tokens original MIT

code-research

16

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Use when investigating a codebase to understand existing patterns, trace execution paths, find reusable utilities, identify implementation gaps, or map dependencies. Invoke before writing design documents, during ADR/HLD/LLD exploration phases, when onboarding to unfamiliar code, or when comparing implementations…

2 3mo ago A 60 tokens original MIT

doc-review

17

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

PR-Aware Architecture Document Review — pulls GitHub PR comments, identifies grey areas across reviewer feedback as R-XX review decisions, tracks all comments (resolved + unresolved) with thread status, produces REVIEW.md state file with resume capability.

2 3mo ago A 49 tokens original MIT

hld-discuss

18

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Identify gray areas and capture architecture-level decisions before writing a High Level Design. Scouts the codebase and ADR constraints, surfaces 3-5 concrete decision points about component boundaries, integration patterns, and technology selections. Outputs a numbered decisions file that feeds into hld-gather and…

2 3mo ago A 65 tokens original MIT

hld-gather

19

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Compile a structured context file for HLD generation by merging decisions (from hld-discuss), research (from arch-research), and ADR constraints with gap-fill questions. Can also run standalone with direct Q&A when no decisions file exists.

2 3mo ago A 53 tokens original MIT

hld-generate

20

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Generate a High Level Design document from a gathered context file. Runs with clean context — reads the context file and produces a complete HLD. Non-interactive.

2 3mo ago A 37 tokens original MIT

implement

21

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Architecture Document Implementation — ingests an HLD or LLD, performs gap analysis, establishes goal-backward must-haves, creates a phased plan, executes with verification, and validates goals were achieved. Supports pause/resume for multi-session implementation.

2 3mo ago A 51 tokens original MIT

jira-tickets

22

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Extract actionable items from an ADR, HLD, or LLD and create Jira tickets under a specified epic. Detects document type, applies section-specific extraction rules, drafts tickets for human review, creates them via Atlassian MCP, and writes a ticket manifest to docs/context/. All tickets created unassigned.

2 3mo ago A 66 tokens original MIT

lld-discuss

23

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Identify gray areas and capture implementation-level decisions before writing a Low Level Design. Scouts existing code patterns and HLD constraints, surfaces 3-5 concrete decision points about interfaces, state management, error handling, and testing strategy. Outputs a numbered decisions file that feeds into…

2 3mo ago A 67 tokens original MIT

lld-gather

24

GoogilyBoogily/googilyboogily-claude-power-tools

Skill Claude CodeCodex

Compile a structured context file for LLD generation by merging decisions (from lld-discuss), research (from arch-research), and HLD constraints with gap-fill questions. Can also run standalone with direct Q&A when no decisions file exists.

2 3mo ago A 53 tokens original MIT