design-paradigms
claudeModern OOP, functional, structural, SQL, API, Docker, cloud, and React design paradigms with code examples.
12 skills
Token-efficient habits, per-task model and effort selection, session memory, docs-first discipline, autonomous execution, and structured work reports for Claude Code.
Plugin session-efficiency from marketplace engineering-standards-marketplace in shah-arnav3/eng_standards-marketplace-claudecode. Commands read from the repo's manifest — 6 days ago.
model-selectionChoosing the right Claude model and effort level per task in Claude Code — for the main session, for subagents via frontmatter or the Agent tool's model parameter, and for skills — and avoiding the cache and quality costs of switching. Use when delegating work to a subagent, defining a subagent or s
plow-aheadAutonomous execution through ordinary ambiguity — turning routine questions into stated assumptions, choosing small reversible options, validating as you go, and stopping only for real blockers (missing credentials, destructive or outward-facing actions, decisions the user reserved). Use only when t
read-the-docsDocs-first discipline — reading current, authoritative documentation (local specs, official references, migration guides, SDK types) before writing code or answers that depend on an external API, library, CLI, cloud service, or fast-moving product behavior, instead of relying on memory. Use when add
session-memoryManaging what Claude Code remembers within and across sessions — keeping CLAUDE.md and rules lean and scoped, maintaining auto memory (MEMORY.md and topic files), compacting at the right time with focus instructions, persisting state before compaction or /clear, handoff documents for multi-session w
token-efficiencyToken-efficient working habits for Claude Code sessions — reading files narrowly, delegating broad searches to subagents, filtering command output, keeping the prompt cache warm, and trimming always-on context from skills, plugins, and MCP servers. Use when a task will read many files or produce lar
work-reportA structured, detailed end-of-task report — results with verification evidence, actions taken, open findings, clarifications (assumptions made and questions to confirm), and next steps split between the user and Claude Code. Use when finishing or pausing multi-step work such as implementing a featur
Modern OOP, functional, structural, SQL, API, Docker, cloud, and React design paradigms with code examples.
12 skills
Concurrency, testing, git workflows, code quality, debugging, scoped changes, documentation, performance, observability, and debloating.
10 skills
Seven-agent delivery pipeline with a /ship orchestrator and a human-approval gate on deploys and rollbacks.
1 skill · 7 agents · hooks
Backend, frontend, network, system, database, and dependency/supply-chain security scanning checklists.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.