hushwork
claudeRun Hushwork from your chatbot: make, run and review agents, read the Hushwork Agent's notes, and approve what they want to send.
4 skills · 1 MCP server
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Run Hushwork from your chatbot: make, run and review agents, read the Hushwork Agent's notes, and approve what they want to send.
4 skills · 1 MCP server
Zero-bloat micro-skills, runaway loop guard, and real-time token/cost ROI telemetry.
1 skill · 4 commands
Read-only financial evidence routing across LiquiLens, Undertow, Seiche, and Palimpsest.
4 skills · 1 MCP server
Run and author Agent IX workflows from Claude.
2 skills · 2 commands
Dan's personal Claude Code skills and automations.
3 skills · hooks
Set up and resume projects with durable context and optional manual Project Blueprint metadata import and timers.
4 skills
Build, test locally, migrate, and deploy Optimizely Connect Platform (OCP) apps.
4 skills
Portable persona packs for Claude Code with Personify persona skills.
4 skills
Durable project workstreams across agents, sessions, and machines.
4 skills
simple git commands
4 commands
Turn messy choices and proposals into transparent, defensible decisions.
1 skill · 3 commands
Memory and session management for Claude Code. Requires Obsidian backend. Includes /dream, /session-log, /session-tidy, and /obsidian-check.
4 skills
Ask other AI command-line agents the same question in parallel and get a claim-by-claim report, a second opinion, or a critic from a different model family.
4 skills
Two debater agents directly argue with each other across multiple rounds until they converge on the most correct answer — then an arbiter synthesizes the final result
2 commands · 2 agents
Rewrite dense text into faster-to-read shapes, and build clickable code rundowns for live reviews
3 skills · hooks
Draft and edit software-engineering prose with a conservative base skill and optional compression and laconic modifiers.
3 skills · 1 command
Native retain/recall/retrieve/remove MCP memory tools plus bounded session-start memory injection, backed by the shared nanomneme SQLite store.
1 skill · 1 command · 1 MCP server · hooks
Enforce honesty, verification, and transparency. Block hedges. Require file:line / URL / cmd output citations.
3 skills · hooks
Talk like grug and think like grug, without the drift. Hooks re-inject the ruleset at every session boundary and every turn.
3 skills · hooks
Record a non-trivial change before implementation, then run exactly one fresh-agent hunt for material absences. Ships the validator, pre-edit hook, and /groundwork commands.
1 skill · 2 commands · hooks
Create, inspect, validate, and assess furniture layouts with bounded next actions in Pascal through MCP.
2 skills · 2 MCP servers
Portable scratch-notebook core: per-thread STATE.md handoffs + compiled INDEX dashboard, 3 skills + a graph-backlink hook. Language-agnostic, no ticket system required.
3 skills · hooks
the vocabulary you weren't taught, at either end — an ambient flashcard while Claude thinks, immersion in its answers when you want it. Five languages, three levels, your dials.
1 skill · 2 commands · hooks
Instant on-the-fly harness assembler. Discovers skills, agents, and commands — pops them together to execute any multi-domain task.
1 skill · 1 command · 2 agents
Adds persistent long-term memory to Claude via the Lore API. Session transcripts are automatically ingested at session end, and Claude can read/write the wiki mid-session.
2 skills · 1 command · hooks
Standalone utility skills — memory, session discovery, and development tools.
4 skills
OpenProject MCP 연동 플러그인 - 48개 도구 자동 연결, 프로젝트 현황 조회, 대화형 작업 생성
1 skill · 2 commands · 1 MCP server
A spellbook of agent skills for AI. Cast wisely. Four skills: eagle-eye, which lays coupled decisions out as a morphological box and renders a page that reads any configuration back; groundtrack, which draws a plan or a written change as a call graph a reader can step through; contract, which interviews a person to agree the terms for a skill, an agent or a CLAUDE.md, then generates its file from that contract; and head-chef, which lets a Claude Desktop session start and lead other sessions. And one pane, Brigade, opened with /brigade or when the head-chef skill loads, which shows them.
4 skills
Research any topic from the last 30 days. Become an expert and write copy-paste-ready prompts.
3 skills · hooks
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, quadrant, radar/spider, loop/flywheel, nested, tree, org chart, layer stack, Venn, pyramid/funnel, bar, line, Gantt and scatter charts, high-level, process, medallion, data flow, DP integration, or DP security matrix diagrams as standalone HTML/SVG/PNG. Redraw .drawio/.drawio.png/.drawio.svg or Mermaid .mmd sources at a chosen size/detail; onboard brand tokens from a website; add semantic patterns, callouts, accessible motion, or sketchy/hand-drawn styling.
1 skill · 3 commands