Plugins

from dherman/claude-plugins

Embedded development MCP server — serial monitoring, ESP-IDF flashing, NVS management, and crash decode.

Internal Point marketing skills for brand voice, visual identity, copywriting, and content review.

Extract loyalty points/miles account activity from airline and hotel programs (Hyatt, United, IHG, Accor, Aeroplan, plus a generic playbook for unsupported programs) into a unified CSV plus current balance. Uses your own logged-in browser session via the Claude in Chrome MCP — no credentials stored, no data leaves your machine.

Define a Proof of Life probe to test a risky hypothesis cheaply.

Select the right Proof of Life probe type based on hypothesis, risk, and resources.

An all-in-one project operating system for Claude Code: standard, gate, SDLC agent fleet, orchestration cycle, and memory.

Polish content style standard (post-2026 orthography, plain language, anti-"AI-polszczyzna" register) plus a bundled, dependency-free linter. Auto-applies whenever Claude writes or edits Polish prose.

from lawvable/awesome-legal-skills

Claude Code adapter for the shared polycli companion

polyforge v1 — Go-native multi-agent AI coding coordination. Implements Iron Rules (IR1-IR4), the full wi lifecycle (work/stop/status/spec/plan/execute/retro), and MCP server registration. Requires the ieops-aihub backend.

from brittonhayes/claude-plugins

Multi-agent pipeline for generating comprehensive unit tests across any programming language. Orchestrates research, planning, and implementation phases using specialized agents to produce tests that compile, pass, and follow project conventions.

Telegram integration for Claude Code that preserves the OpenClaw per-chat session model. Migration target for OpenClaw users. Bundles /polygram:status|logs|pair-code|approvals admin commands plus history (transcript queries) and polygram-send (out-of-turn IPC sends with file-upload validation) skills.

Clojure Polylith skill — components, bases, projects, interfaces, poly commands, workspace configuration, profiles, incremental testing, and setup.

Modular, multi-source research pipeline with citation tier classification. Ships a Claude Code skill (/polysearch:research) plus a pip-installable Python CLI.

Build EVM blockchain data indexers using Ponder (ponder.sh) - index smart contract events into queryable databases with type-safe APIs

Lazy senior dev mode — simplest working solution, YAGNI, stdlib-first. 6 skills. From DietrichGebert/ponytail.

Horizontal restraint layer for coding work. An always-on 'lazy senior dev' ruleset injected every turn that runs a YAGNI ladder before the agent writes code (question whether it needs to exist, stdlib before custom, native before dependency, one line before fifty), never cutting validation, error handling, security, or accessibility. Ships the referenceable `ponytail` skill plus /ponytail (lite|full|ultra|off), /ponytail-review, /ponytail-audit, /ponytail-debt, /ponytail-gain, /ponytail-help. Vendored from DietrichGebert/ponytail (MIT) v4.8.3; pairs with gstack-execution (trim then harden) and dev-infrastructure-skills.

Lazy senior dev mode — simplest working solution, YAGNI, stdlib-first. 6 skills. From DietrichGebert/ponytail.

Minimal, YAGNI-first implementation discipline.

Forces the laziest solution that actually works, simplest, shortest, most minimal.

Lazy senior dev mode for AI agents

Lazy senior dev mode — simplest working solution, YAGNI, stdlib-first. 6 skills. From DietrichGebert/ponytail.

Lazy senior dev mode — simplest working solution, YAGNI, stdlib-first. 6 skills. From DietrichGebert/ponytail.

Lazy senior dev mode — simplest working solution, YAGNI, stdlib-first. 6 skills. From DietrichGebert/ponytail.

Aggregated (not authored here). 'Lazy senior dev' mode — forces the simplest, shortest solution. General agent-behavior skill. By DietrichGebert, MIT.

Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.

After the agent implements something for you, it springs a surprise oral exam (onverwachtse SO) on the concepts, terms, and design tradeoffs of the work — so you understand what was built and why.

Measure porosity, pore size/shape, lattice period and ordering (psi6, Voronoi coordination, radial g(r) and orientational correlation length) from top-view SEM images of porous films such as anodic aluminium oxide. The agent reads the image to calibrate and crop; a Python core does the morphometry and flags results that contradict physics. Vision decides, Python computes — no hardcoded autodetect, so it adapts to different instruments and scale-bar formats.