Productivity plugins

Skills for reflowing prose with Semantic Line Breaks

1 skill

Measure fast radio bursts with FLITS instead of writing dedispersion and measurement code by hand

1 skill

A /desk-review:simplify-review skill (/simplify, then /code-review medium) whose report opens in a side pane: each item with its file, line and reason, its diff or current source unfolding in place, and the file opened in desk-look's diff pane. Needs desk-look

1 skill

见字 · 公众号编辑工作台：本地优先的中文内容编辑与图文生产工作台

1 skill

Automated content discovery and curation for Nixtla and time-series forecasting practitioners. Searches web and GitHub, generates AI summaries, and publishes formatted digests to Slack.

Claude Code mod that redraws the terminal transcript to look like the Code tab of the Claude desktop app: prompt bubbles, markdown tables, mermaid diagrams, folded tool calls, agent cards, GitHub/GitLab PR bar, diff and context panes

Portable Corca harness layer exported into Claude and Codex plugin layouts from shared repo artifacts.

Your Asana tasks in a Claude Code side pane (/desk-asana): assigned tasks, workspace search, project tasks by section, details, comments, assignee, fields and status, through the Asana MCP server. Pairs with desk-look

Shows your Claude Code usage above the prompt: 5-hour and weekly plan limits with reset times, and context window fill, each as a live card with a percentage and a bar. Claude Code only.

Australian accounting and tax preparation workflows with source checks and human review.

107 skills · 1 MCP server

Code-first, spec-driven MVP builder. v0.14 makes every loop stop state its reason and its next command, cuts review agents without cutting a single mechanical check, and puts the whole plugin into ASD-STE100 Simplified Technical English, enforced by scripts/ste-check.sh.

13 skills · 16 commands · 3 agents · hooks

Evidence-Driven Development Protocol — 24 command-equivalent skill surfaces plus a skill-native deep-work entry alias (cross-platform: Claude Code skills + Codex / Copilot CLI / Gemini CLI / SDK), 3-layer architecture with Skill-based phase dispatch, computational enforcement (worktree guard + phase transition injection), TDD enforcement, and receipt validation

27 skills · 4 agents · hooks

Spec-first engineering workflows, frontend design, project memory, and evidence-based quality gates.

31 skills · hooks

Simple workflow orchestration for Claude Code sessions

22 commands · 6 agents

Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct procedure (accounting: sales/purchase invoices, payments/bank, VAT/KMD, reports, reverse charge; payroll: employees, salaries/absences, reports, settings), agents, and slash commands. Bundles LHV's official read-only bank MCP server for direct statement import.

18 skills · 5 commands · 3 agents · 1 MCP server

presentation-slide-generator v8.4.2 の全機能を移植した共通コア + output_mode=slide/report の 2 モード・ビジュアル生成ハーネス。意匠/技術層 (Kanagawa/16:9/GSAP/インライン SVG2/Codex Image2/決定論レンダラ/A4 印刷/style genome) を単一 SSOT で共有し、コンテンツ意図層のみ mode 別に分岐する。slide=1スライド1メッセージ/107 slideType、report=読み物/4 reportType/1項目1ビジュアル最適化/Mermaid 統合。Node 製レンダリング/画像/印刷/検証エンジンは vendor として携行し、OS/CPU別Playwright Chromiumはinstall先のplugin-local cacheへ決定論的に復元して起動する。

6 skills · 2 commands · 17 agents · hooks

Install all 26 Taplio LinkedIn skills at once: post writing, hook generation, carousels, repurposing, story extraction, CTA optimization, niche and audience definition, content pillars and calendar, profile optimization, analytics interpretation, comment opportunities, smart comments and replies, warm leads, engagement routine and tracking, connection requests, and DM openers. Requires the Taplio MCP.

26 skills

A multi-host Minecraft Java and Bedrock development skills bundle for Claude Code, Codex, and compatible agent hosts; image-generation workflows are available when the host supports them.

20 skills · 5 agents

Collaborative whiteboard for Claude Code. Wraps the @kamiazya/whiteboard-mcp server and exposes the bundled /drawing-visuals, /coauthoring-visuals, and /auditing-workspaces skills.

22 skills · 1 MCP server

Complete client discovery workflow — sitemap audit, competitor research, buyer personas, keyword strategy, and production-ready website copy with a 90-day content plan

11 skills · 10 commands · hooks

harness-creator の前段ヒアリングを非技術者にも開く plugin。Markdown/JSON/Notion ページを Keychain 経由で一括生成。図解マスト + 5 軸ヒアリング (出力先/情報源/共有相手/真の課題/ナレッジ資産) を機械検証。

12 skills · 4 commands · 4 agents · hooks

Agent-neutral AI testing skills for Katalon True Platform covering the full software testing lifecycle: test planning, test design, test management and requirement traceability, test review, manual and automated execution with AI, failure analysis and release readiness, and test maintenance - operated through the Katalon MCP.

19 skills · 1 MCP server

Agent Skills for Crowdin, an AI-powered localization platform for teams and businesses

15 skills · 1 MCP server

Messaging, collaboration, communication, and meeting workflows.

16 skills

Skills, subagents, and scripts for the PageKit method: signal doc, message spine, first-page decision, page argument shape, proof map, first-page draft, claim check.

12 skills · 2 agents

Job-search help from resume import to offer: a career profile built from your resume, ranked job searches with skill matching, tailored resumes and cover letters, mock interviews, application tracking and offer comparison. 8 commands, 3 agents, and a 5-tool job-data server.

1 skill · 8 commands · 3 agents · 1 MCP server · hooks

Automated research paper discovery, PDF monitoring, and AI-powered summarization for academic and technical literature

13 commands · 1 agent

Maintains project documentation: README.md (what/how to use), ARCHITECTURE.md (design/patterns), process-notes/ (per-entry work history), and A/B test docs

5 skills · 7 commands · 2 agents

Contract-checking harness for Claude Code and Codex: full delegation inside an approved per-run contract, mechanical stop-and-ask outside it, and model-owned semantic completion review.

12 skills · hooks

システム構築(Web/モバイル/タブレット/デスクトップ横断)に必要な仕様情報を、ユーザーとの往復ヒアリングでカテゴリ×プラットフォームの網羅マトリクスとして漏れなく収集し、設計知識 (クリーンアーキテクチャ/デザインパターン/API デザインパターン/セキュアバイデザイン/DDD/クリーンコード) の参照と最新公式ドキュメントの出典記録を添えて、章立て複数 Markdown ファイル + index の仕様書ドキュメントセットへまとめるハーネス plugin。ヒアリングは5周ごとに状態保存+resume で継続し未収集セルを完了扱いしない。収集マトリクス網羅性 (validate-coverage-matrix.py) と出典記録 (validate-source-citation.py) を決定論ゲートで検証し、独立 context の完成度評価 (assign-system-spec-completeness-evaluator) と 3 監査 sub-agent (hearing/matrix/doc-freshness) で網羅性を担保する。確定済み章は fail-closed hook で誤上書きを防ぐ。改善要望は `/run-skill-feedback system-spec-harness` で投入可能。

6 skills · 2 commands · 3 agents · hooks