🔌
Plugins
Loading...
Showing 30 of 27361 results
Before flipping a previously-stated position under pressure, restate its strongest form and the goal it served, then check whether the trigger refutes the core on the same goal, not just a decorative argument or a different axis.
Thinking, planning, and ideation skills — custom and community-sourced
Compact conversation-steering skills for changing direction, explaining decisions, asking for clarity, answering questions without implied action, finishing punted work, tightening prose, executing decisively, and raising frontend quality.
Claude Codeの全ステアリング要素（CLAUDE.md/rules・skills・subagents・hooks・slash commands・output styles・MCP・settings.json）を監査・評価するプラグイン。Anthropicの『Steering Claude Code』の枠組みに基づき、各成果物が正しいprimitiveで実装されているか（advisory→CLAUDE.md / mandatory→hook / procedural→skill / context isolation→subagent）と設計ベストプラクティスへの適合を、サブエージェントに並列評価させて重大度付きの監査レポートと改善ロードマップを生成する。
from varaku1012/aditi.code
Keep a lookout for ways to harden steering rules while executing any task.
Teaches AI coding agents how to build Stellar blockchain applications using stellar-ios-mac-sdk. Covers transactions, operations, Horizon API, Soroban smart contracts, XDR encoding, and SEP protocols.
STEM Subjects skills in one install (9 skills; 3 paid-key skills excluded, install separately).
Sum a directory of multitrack audio stems into stereo mixdowns (acapella, instrumental, custom groupings) at the highest quality the source material honestly supports. Six-pass pipeline (identify → optional Pro Tools track-name borrow → analyze → plan → mix → verify) with full provenance: SHA-anchored idempotency, sidecar logs per output, declared pan law, ITU-R BS.1770 true-peak headroom, dither when reducing depth, and refusal-by-default for upsampling, normalization, and writing into the source folder. Optional master-reference pipeline (Cmd 19) produces a three-synced-versions reference-bundle and runs a recombine-null + inverse-stems-null verification battery against the released master. Eighteen commandments, all cited by error messages and plan rationale.
Teach a dense technical document to someone new to it — step by step, at the user's pace, accumulating into one persistent page.
Agentic step-by-step project builder. Plans first, gets approval, then executes one verified step at a time via subagents.
Deutsche Einkommensteuererklärung: TaxReport über alle Anlagen, Krypto-FIFO nach § 23 EStG mit taggenauer Haltefrist, Kapitalerträge mit Verlusttöpfen, Broker- und Börsen-Import über Profildateien (Koinly, eToro, Kraken, Coinbase, Bitpanda, Binance), Export als HTML, PDF und ELSTER-Feld-Mapping. Orientierung, keine Steuerberatung.
Channels Steve Jobs, reframing the question before answering.
Steve Hobbs' personal Claude Code skills collection, including tools for scaffolding new Rails applications.
Unified repo stewardship: a /maintain orchestrator deploys read-only maintainer agents for user docs, spec docs, project instructions, cross-project conventions, and structured schemas/manifests, merges their drift findings into one prioritized report, and applies approved fixes through bundled skills that audit, revise, and restructure AGENTS.md (and legacy CLAUDE.md), scaffold project conventions, and keep docs/STATE.md current. Report-and-propose - nothing is applied without approval.
Restructures the George -> Opus -> Blueberry pipeline around efficient use of George's attention
A tiny stick-man RPG to play on top of your terminal while Claude Code works
Social listening e SAC da Stilingue by Blip dentro do Claude: buzz e sentimento em toda a base pública (Radar), análise profunda do painel do cliente (Warroom), auditoria de configuração de painel (Setup) e métricas de atendimento (Smartcare).
Social listening e SAC da Stilingue by Blip dentro do Claude: buzz e sentimento em toda a base pública (Radar), análise profunda do painel do cliente (Warroom), auditoria de configuração de painel (Setup) e métricas de atendimento (Smartcare).
Design generation, review, extraction, and implementation workflows.
Google Stitch AI UI generation — brainstorm, generate, edit, iterate on UI designs from text prompts. Bundles 4 sub-skills (design / theme / edit / upload).
Full Stitch Studio plugin — all 6 skills, 3 agents, hooks, and MCP config.
STM32 hardware debugging for AI agents: the stm32-gdb-mcp server plus the stm32-debug and stm32-instrument skills, with a SessionStart hook that locks the golden rules in at conversation start.
STM32F4 펌웨어 풀스택 개발: 5단계 에이전트 파이프라인(요구사항→아키텍처→코드→빌드→검토) + KiCad 회로도 핀/페리페럴 검증(42항목) + 호스트 기반 TDD(Unity+FFF) + CMake+Ninja 빌드 실행(CubeMX/CubeIDE 자동 변환) + 소스코드 리뷰(34항목) + QA 최종검수. 5개 스킬 + 4개 에이전트.
Enterprise AI development pipeline — from idea to verified code. Multi-lens brainstorming, zero-placeholder DAG planning, checkpoint-verified execution with fidelity scoring, and 13-domain codebase auditing. 8 skills, 6 hooks (safety + context priming), technology-agnostic. Research-backed: structured decomposition yields 12-18% higher correctness; per-step verification prevents 20-27% quality degradation.
The Stoa multi-tier agent substrate: CAPTAIN roster, MAJOR roles (runtime-parametrized), skills, modules, templates.
Author, run, and analyse a stochastic simulation as a single YAML config — no Go, no compilation, no toolchain. Bundles the stochadex-model skill with four validated, converging worked recipes (evolution-strategy, posterior estimation, SMC, regression).