Agent Skills: improve-codebase-architecture
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
ID: iamladi/cautious-computing-machine--sdlc-plugin/improve-codebase-architecture
1
Install this agent skill to your local
Skill Files
The files that make up improve-codebase-architecture.
More agent skills
- alchemyBlockchain API access via Alchemy. Use when an agent needs to query blockchain data (balances, token prices, NFT ownership, transfer history, transaction simulation, gas estimates) across Ethereum, Base, Arbitrum, BNB, Polygon, Solana, and more. Supports API key access ($ALCHEMY_API_KEY), x402 wallet-based pay-per-request (SIWE/SIWS + USDC), and MPP protocol (SIWE + Tempo/Stripe). Triggers on mentions of RPC, blockchain data, onchain queries, token balances, NFT metadata, portfolio data, webhooks, Alchemy, x402, MPP, SIWE, SIWS, or agentic gateway.
- parallel-dev-cycleMulti-agent parallel development cycle with requirement analysis, exploration planning, code development, and validation. Orchestration runs inline in main flow (no separate orchestrator agent). Supports continuous iteration with markdown progress documentation. Triggers on "parallel-dev-cycle".
- dyad:fix-issueCreate a plan to fix a GitHub issue, then implement it locally.
- technical-analystThis skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs. Use this skill when the user provides chart images and requests technical analysis, trend identification, support/resistance levels, scenario planning, or probability assessments based purely on chart data without consideration of news or fundamental factors.
- the-foolUse when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.
- resolve-fixmeFind all FIXME comments across the codebase and fully implement the work they describe. Use when the user asks to fix, resolve, or address FIXME comments, or when running the "fixme" command. Runs a discovery script to find every FIXME, expands multiline comment blocks, groups related FIXMEs across files into a single implementation task, completes the full underlying code changes, removes the FIXME comments only after the work is done, and verifies that no FIXMEs remain.