Find plugins

Операционный плагин AI/ML-харнесса: маршрутизация знания (md vs playbook vs skill vs hook), гигиена библиотеки скиллов и дистилляция. Отвечает на вопрос «надо ли вообще писать скилл», а не «как его написать». Триггеры: «куда это положить», «нужен ли скилл», «оформить как скилл или заметку», «дистиллировать материал», ретро-ревью библиотеки скиллов.

by wrzonance

agentkit v2: parallel issues and PRs to green with a thin root and workers that own their PR.

by Che Cheng

Akashic-Library 文獻探索 skills（引用追溯、被引、關聯、作者與期刊著作）——依賴 akashic-mcp 的 canonical store。目前有 akashic-work-references（往回追一篇論文的參考文獻，#617）；其餘由後續 issue 各自加入。

by Che Cheng

Akashic-Library MCP server — file-based canonical literature store: search, relations, graph, derived-layer writes (tags/status/links/person updates), person & organization resolution, divergence recording with judgement, resolution verdicts (confirm/reject with four-state counts incl. checked-undecided, no ratios), Zotero one-way pull. Store format 19.

by itlackey

Search, show, and curate AKM concepts, record feedback, and turn corrections, preferences, memories, and recurring workflows into reviewable AKM proposals.

by envoydev

The Claude Code stack, guided: setup installs it from scratch into a project, init bootstraps it once after the restart (services, memory, captures, CLAUDE.md), update refreshes an existing install and prunes what upstream removed, configure adjusts the selection (add or drop), validate reconciles an install to the project - prunes what its framework does not use and adds what the detected stacks are missing - all drive a dependency-complete selection with a prerequisite check; status shows the install read-only, per-area tables; uninstall removes what the install ledger says the stack wrote, and nothing of the user's.

by Alpha Squad Coding Craft contributors

Portable orchestration workflow with role templates and host-aware model selection.

by Ivan-WG

Meta-bundle: the user-scope baseline — project-agnostic plugins worth enabling once in ~/.claude/settings.json and keeping on everywhere. secret-scanning's write-time secret block, candor's honesty Stop gate, lean's output pricing, terse's chat-brevity contract (inert until you set a level), file-aware skill auto-routing (skill-router), git-workflow discipline, cross-session friction mining (hindsight), and two scouts for what this bundle leaves out (plugin-scout, vercel-skills-scout) — command-guard among them, whose ask tier replaces the host's own permission classifier. Membership is prose, unchecked. /always-on-suite:uninstall removes the bundle and prunes what it installed.

by zerlinpi

Amazon Ads AI Agent skills, playbooks and eval fixtures for auditing, monitoring, causal diagnosis, growth discovery, experiments, weekly reviews, post-change evaluation, optimization memory and guarded decisions.

by David Kim

Verification loop for analytics and research deliverables: claim ledger, mechanical check script, independent verifier on a fresh context, re-check of every fix, and a receipt bound to the exact file sent.

by farbodjavan

Evidence-based, multidisciplinary UX/UI analysis and implementation-ready redesign workflows with privacy-gated public evolution.

by Ando / Asari Inc.

Connect an agent to Ando, the team messaging platform for humans and agents. Wraps the hosted streamable HTTP MCP at https://mcp.ando.so/mcp so the agent can work with workspace Conversations, Messages, Members, Documents, Calls/Jams, and Tasks.

by Anselm Hahn

Walks a repository's value stream stage-by-stage, proposing fixes for discovered gaps, proving each wire before advancing via seven evidence-grounded strategies, and halting rather than passing broken or unproven handoffs.

by Anselm Hahn

Self-optimizing hardening loop over a project's value stream (an ordered chain of stages connected by wires/data-contracts). Fixes one gap per stage and refuses to advance past a wire that isn't proven.

Anki MCP integration — deck operations, managed note types, card generation, and feedback-driven card edits

by Mohammed Talas

Verify-first discipline for Codex. Bundles Codex-native skills (including session handover — a comprehensive handoff so a fresh session can resume without re-deriving or guessing anything) plus an installer for the Codex hook subset that can be enforced today: session/prompt nudges, a codex-availability PATH probe, shell-command guards, Stop guards, task discipline, and speculation checks. Claude Code plugin files are kept separate and unchanged.

by Ivan-WG

APIs in both directions: design your own (resource naming, status-code discipline, pagination/filtering/sorting, versioning, RFC 9457 errors, idempotency, Laravel API Resources, plus a graphql-grpc skill for non-REST surfaces; /api-design:review and spec-first /api-design:scaffold) and consume others' honestly — verify current official API/SDK docs before writing integration code (UserPromptSubmit reminder + /api-design:check, the api-docs-first skill) and keep your own docs true after a change with the docs-upkeep drift scan: README claims, changelog gaps, stale examples, dead links (/api-design:drift).

by Jung Jiwon & Lee Jongkwan

The api-design role on contract v3: 서비스 경계의 인터페이스 형태. use_when: 여러 소비자가 걸리는 API 표면을 설계/변경할 때. Hand-off: 컴포넌트 경계 자체가 바뀌면 → architecture; 스키마 신설/변경이면 → data-modeling.

by Engineering

app-factory skill: one spoken idea to a submitted App Store build. Requirements, architecture, Xcode scaffolding, implementation, review, simulator QA, screenshots, App Store Connect metadata, TestFlight and submission.

by whale_net

Postgres MCP access (crystaldba postgres-mcp) to the App Registry database across tilt/dev/prod

by Ivan-WG

Solution-approach deliberation before non-trivial implementation: 2-3 structurally different approaches with trade-offs and a kill-trigger, a strategy catalog mapped to the risk each beats, a four-persona blind opinion round for refactor-shaped tasks — plus the merged pre-code disciplines: build-vs-buy checks, S/M/L/XL estimation, rollout planning, design-pattern selection, and /approaches:consult, a blind stronger-model second opinion when a session is stuck or about to do something irreversible (fresh-take merged in). Includes /approaches:compare, /approaches:opinions, /approaches:build-vs-buy, /approaches:size, /approaches:rollout, /approaches:pattern.

by pvallarino

Develop Google Apps Script projects locally with Claude using clasp -- create/clone standalone, container-bound (Sheets/Docs/Forms), or web app projects, write and iterate on code, push/pull, run functions, tail logs, and manage deployments.

by Anselm Hahn

Compiles a stated problem into an executable, budgeted agentic workflow, runs it as a redundant swarm — N candidates over the SAME scope in their own git worktrees, judged blind, exactly one landed and the rest deleted — and refuses to converge by retrying. Ordering is delegated to takt via a generated beat declaration rather than enforced twice. Writes to a scoped output directory (analysis/arbeitsplan/**), to candidate worktrees under .arbeitsplan/**, and — only behind an explicit approval gate — to .claude/takt.local.md; the single landing step is the one place it touches the working tree. A PreToolUse hook denies an identical re-dispatch, an out-of-scope write, a shared-tree write during a fan-out, and a dispatch past the declared budget. Ships a headless `claude -p` matrix runner for sweeps that need a fresh process and a real per-cell --model.

by Altug Sogutoglu

Auto-inject ArcadeDB graph context per project; slash commands for decisions, queries, indexing, and status. Pre-bundled hooks, zero runtime npm deps.