reimagine-it
claudecodexRedesigns existing HTML from its own content. 15 visual directions, standalone offline pages. Not a mood board.
7 skills · 1 command
Every plugin for Claude Code we can find on GitHub, read straight from each repo's .claude-plugin manifests. Install one with claude plugin marketplace add owner/repo and claude plugin install name@marketplace — each page has the exact lines. Looking for Codex? See Codex plugins.
Redesigns existing HTML from its own content. 15 visual directions, standalone offline pages. Not a mood board.
7 skills · 1 command
AKARI Video の編集スキル一式(27 本)+ SessionStart 進捗注入 + /akari 導線
1 command · hooks
Evolve a better answer to any query: sample N candidates from the strong model, then route group recombination by answer-diversity (consensus = free, low = haiku, medium = sonnet, high = opus) and synthesize a final answer with a per-loop diversity/routing trace.
1 command
Opt-in Claude Code mod for MCP Task Orchestrator: live work graph, gate band, and in-process orchestration hooks (early-access function-hooks API)
Пульт в Claude Code: прогресс задачи, что сейчас выполняется, лимиты и контекст, хендофф перед сжатием, панель «Активность», уведомления
Opt-in Claude Code mod that shows which Task Orchestrator orchestration mode a session is in (today: director): a footer label, a live run board above the prompt, a tinted desktop backdrop and enter/exit toasts (early-access function-hooks API)
Claude Code configurations for R development.
8 skills · 4 commands · 3 agents
One command, ultradesign: designs a marketing page, a multi-screen product or a redesign from a one-line request, one cycle at a time. Each cycle makes the work, has a cold outside eye look at it, and stops to show you; reply "one more" or "continue".
2 skills · 2 agents · 1 MCP server
A harness that gives AI coders the tools and skills to work like a senior developer
1 skill · 34 commands
한국 취업 통합 엑셀러레이터 — 이력서·자소서·기업분석·채용공고·모의면접·지원 추적 16개 스킬
16 skills · 1 agent
Dispatch subtasks to DeepSeek Harness (DSH) agents as native subagents with live progress
3 skills · 5 commands · 2 agents · 1 MCP server
KiCad MCP Pro plugin for schematic review, PCB design assistance, DRC/ERC validation, DFM checks, and manufacturing release workflows.
10 skills · 1 MCP server
Real-time cost tracking, cache efficiency, model comparison, smart alerts, web dashboard, and session analytics
6 commands
Send and receive emails, build with React Email, follow deliverability best practices
5 skills · 1 MCP server
Read-only hosted KiCad project review, scoped to user-authorized projects.
1 skill · 1 MCP server
Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-calibrated judges, gated self-update loop, pressure testing, 10 authoring principles grounded in empirical research.
1 skill
Patent drafting, prior-art search, USPTO rule search and compliance checks for Claude Code. Needs the companion patent-creator tool (README Quick Start, Step 1) for search and checks.
17 skills · 15 commands · 13 agents · hooks
AI agent Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, ai agent, and growth engineering, ai agent
45 skills
Composable AI skills covering the full software delivery lifecycle — for backend engineers, frontend engineers, QA, BAs, and more. Install once, invoke the skills you need.
33 skills · 1 agent
29 skills in six layers: workflow and the ARR-SPEC contract; general craft (melody, harmony, progressions, modulation, rhythm, form, counterpoint, motivic development); arrangement craft (architecture, orchestration including Chinese folk orchestra, texture, rhythm section, sound design, vocal direction, mix intent); nine style layers (J-pop, city pop & R&B, jazz, Latin, Mandarin pop, EDM, rock band, cinematic, hip-hop) each with a transfer table and declared fusion ownership; execution (compile to Suno/YuE2/MIDI, symbolic score, AI-tell audit); and a corpus layer of measured recordings. Plain text, no tooling required; answers in the language you ask in
29 skills
Human SOP → a controlled agentic loop, or a bounded graph of them: typed handoff edges, one declaring writer per state field, bounded back-edges, and a static topology gate that refuses an illegal graph before it runs. Methodology skills + /sop-flow + a project-scoped regression Stop-hook + the portable kit.
13 skills · hooks
Autofill a .sub from a manuscript, run validate's AI checks, submit, debug a stalled portal run, and add venues.
11 skills
Drop-in memory harness for AI agents — 3-tier memory, compaction tree, hybrid search. One command to set up. Works with Claude Code and OpenClaw.
5 skills
Excalidraw diagramming toolkit — say 'diagram this repo' for zero-config architecture diagrams, plus data flows, parameter traces, and PNG/SVG/URL export
3 skills · 1 MCP server
Independent adversarial honesty reviewer: scrutinizes a DRAFT output's claims-vs-evidence (no fabrication / overreach / invented IDs) before a human approves. Snaps onto agentic-sop-kit run dirs (FULL, uses the trace) or reviews any plain document (DEGRADED). Deterministic checks + a capped advisory LLM pass; the report is a DRAFT — the human owns the verdict.
1 skill · hooks
Deterministic ALCOA+ data-integrity linter: checks Attributable / Contemporaneous / Complete / Accurate / Consistent in code and surfaces the human-judgment slice as a 【待補】 checklist it never auto-concludes. DEGRADED lints any CSV/JSON record against a declared contract; FULL snaps onto an agentic-sop-kit run dir. The report is a DRAFT — the human owns the verdict. Pure stdlib.
1 skill · hooks
Unified meta-plugin — the full agentii skill namespace (14 verticals, 80 skills) under a single /agentii:skill-name namespace. The recommended single install. Skills with same-name vertical variants (e.g., bio-pharm's med-adapted earnings-preview) ship via their own vertical plugins.
51 commands
9 financial-modeling + presentation skills: DCF, comps, 3-statement, LBO, SOTP-valuation, audit-xls, xlsx-financials, earnings-preview, and pitch-deck. All Excel-producing skills follow the FR-044 4-step office protocol (spec → build → recalc → audit).
9 skills · 9 commands · 2 MCP servers
9 equity-research dimension skills with ~48 addressable sub-prompt modes: recent-quarter performance, business-model analysis, competitive landscape, growth strategy, secular tech trends, turnaround analysis, risk analysis, earnings sentiment, and valuation methods.
9 skills · 9 commands · 1 MCP server
All official Modular skills for MAX and Mojo
11 skills