Productivity plugins

Sync Claude Code configuration across machines using GitHub

6 skills · 7 commands

Scout a topic, chart a syllabus, walk it with Socratic /learn sessions.

1 skill · 4 commands · 8 agents

Connect Claude to your Hera workspace. Query associates, routes, incidents, performance data, and more via the Hera Public API.

12 commands · 1 MCP server

Teaches your agent how to build sites and complete WooCommerce stores with Oxygen 6 or Breakdance: pages, templates, dynamic data, shop and product pages, cart, checkout and account.

12 skills · 1 MCP server

A delivery workflow: load, brainstorm, design, research, spec-panel, workflow, build, plan and save, each writing a markdown record of one feature. Build executes the plan one task at a time and ticks a task only with recorded verification evidence.

8 skills · 4 agents · hooks

TDD, SOLID, atomic-commit, and code-quality skills generated from the same packs as the argus-standards CLI.

13 skills

Know your unknowns — skills for the gap between your plan and the actual situation, in any domain: what you don't know, what the AI doesn't, and what neither knows yet. Eleven skills: blind-spot passes, field primers, interviews, divergent prototypes, brainstorming, reference read-backs, tweakable plans, a deviation log, buy-in docs and quizzes — plus two Claude Code agents.

11 skills · 2 agents

v0.3.3 · Turns a messy, spoken-style brain-dump into a clear, complete prompt, then runs it. Talk or dictate what you want (half-sentences fine) and Promptception builds the prompt you would have written if you were a prompt expert, shows it to you, asks only the questions that close real gaps, and executes on your go. Beginner-first: it teaches prompting by showing, not lecturing, and offers to build a full plan when the ask is bigger than one prompt. Also ships Orchestrator Mode: /orchestrator-mode runs big cross-system work through tiered subagents (scout, reader, builder, checker, premortem) with both-directions verification, and /premortem red-teams any draft plan before it ships. Plus four builders that craft the ideal prompt for Claude Code's newest commands: /goal-builder, /loop-builder, /schedule-builder, and /plan-builder for jobs too big for a single prompt.

7 skills · 5 agents · hooks

Campaign explainers and cinematic short films: direction from the brief, native English or Indonesian scripts, ElevenLabs narration and sound, continuity bibles, contact-sheet boards, approved Higgsfield or Gemini API takes with dailies, HyperFrames compositions, assembly, QC and handoff into the campaign's approved assets

13 skills

Agent skills by Ryan Ilano: copyable-markdown, prompt-pack, docs-mirror, yt-cc, ffmpeg, socials-mirror, tool-call-repair, spamcheck, cherrypicker, deltamaxx, plus vendored skills (humanizer, writing-fragments, writing-beats, writing-shape) with pinned provenance. writing-for-agents now comes from Matt Pocock's mattpocock-skills plugin.

13 skills

Install all twelve Agent Toolkit engineering skills.

12 skills

Compound knowledge base via git-versioned, LLM-maintained markdown.

6 skills · 6 commands

Structural thoroughness enforcement — verification gates, multi-model orchestration (Codex/Gemini), context persistence across compaction, mission-driven workflow

3 skills · 7 agents · 1 MCP server · hooks

Social science research workflows plugin

4 skills · 4 commands · 4 agents

Manage ServaDiscord workspace graphs — list, add, update, toggle, and remove nodes — directly from Claude Code.

10 skills · 1 MCP server · hooks

Development stack for AI-assisted multi-repo work. Persistent memory, quality gates, VPS deployment, cross-repo sync.

8 skills · 3 commands · hooks

Search UK car listings, track prices, and build buyer intelligence dashboards with regression-based value scoring.

4 skills · 8 commands

Autopoiesis Plugin - Self-maintaining promise loops that enforce honest AI work through stop hooks

1 skill · 10 commands · hooks

UltraMemory Agent Kit (Tier 3) — Turbo Token Saver (recall-first hook + client cache) + the harness (grounding / checklist-bound execution skills, subagents, Stop gate) + optional MCP setup (Context7 keyless, Exa BYO) and our Playwright Human Vision Control skill. Bring your own UltraMemory key.

7 skills · 2 agents · 2 MCP servers · hooks

Evidence-backed five-phase investigation for Access/VBA and SQL Server legacy applications, plus an optional Django REST + React modernization pipeline that carries a project from that investigation's output to implemented, coverage-traced code.

11 skills · hooks

Portable standups, Slack response monitoring, productivity setup, Obsidian todo capture, session hygiene, daily planning, AI coaching, and agent operations.

12 skills

macOS automation toolkit plugin with Notes, Calendar, Mail, Safari, Spotlight, disk reclaim, and more

11 skills · 1 agent

Distilled one-page methods pulled out of longer sources.

12 skills

Evidence-controlled hospitality planning, analysis, and drafts for restaurants, hotels, guest service, events, inventory, revenue, and owner reviews.

12 skills

Transcrição na GPU local (faster-whisper), corte pela fala sem reencodar, legendas estilo filme com editor de revisão sincronizado e render 4K NVENC, Shorts verticais com os melhores momentos, capas de YouTube por IA (OpenRouter) a partir de frames do vídeo e narração com a sua própria voz (ElevenLabs). Testado com motovlog em NVIDIA RTX.

6 skills · 6 commands

Long-term memory for Claude Code: the NovaMem MCP server, the novamem and session-recap skills, and /remember, /recall, /today and friends.

2 skills · 9 commands · 1 MCP server

Hybrid knowledge vault for Claude Code — auto-archives sessions into an Obsidian-compatible wiki, split between a global (~/Global Claude Vault/) vault and per-project (docs/vault/) vaults. At session start, vault context (index, project entity, recent sessions) is automatically injected so Claude can reference past decisions and lessons without re-discovering them. Builds on the LLM-Wiki pattern by Selma Kocabıyık.

1 skill · 10 commands · hooks

Seamless context continuity across Claude Code and Grok compaction. Multi-layer background capture (continuous tool-call capture, mechanical PostCompact handoff, async Opus 4.7 enrichment at --effort max, async Stop-hook refinement, and preemptive snapshot before the next compact) keeps the agent working state intact across every compaction and resume. All summarization is isolated from CLAUDE.md/auto-memory and invisible to the user.

1 skill · 8 commands · 1 agent · 1 MCP server · hooks

Open a PR, run /loop /pr-autopilot:step <PR#>, walk away. Enabled reviewers review (default: Cursor each iter + Copilot final-only). Claude reads each review and either fixes or pushes back with reasoning, pushes, waits for re-review. Exits when all per-iter reviewers report success (with 10 independent safety stops). Optionally pings @copilot for a final sanity check.

11 skills · hooks

Three skills plus the hosted Wabi MCP servers: orient in an organization, try the sandbox number, connect the CLI, MCP or an API key, and read pricing and usage.

10 skills · 2 MCP servers