llm-wiki
36289Skill Claude CodeCodex
A workflow that uses Siyuan Note and Claude Code to build and maintain a linked knowledge wiki from your documents. It adds pages, connections between related ideas, and checks for conflicting information.
Skills, subagents, slash commands, hooks, settings, plugin bundles and MCP servers that install into Claude Code. 386,484 indexed, measured the same four ways as everything else here.
Skill Claude CodeCodex
A workflow that uses Siyuan Note and Claude Code to build and maintain a linked knowledge wiki from your documents. It adds pages, connections between related ideas, and checks for conflicting information.
Plugin Claude Code
Bundles 2 skills, 1 command, 4 agents · 357 tokens together
PPT slide generation workflow: requirement research → material collection → outline planning → planning draft → design draft (SVG 1280x720 Bento Grid) with Claude draft + Gemini review.
Command Claude Code
Validate the TOPO map for consistency — check bidirectional dependencies, orphan references, missing parity contracts, lifecycle hygiene, and regenerate the Mermaid dependency graph. Run periodically and as part of /check-solution.
Skill Claude CodeCodex
A post-production tool for turning existing animation HTML or video files into deliverable videos, GIFs, and music versions. It handles exporting, audio mixing, batch variants, and checks of the resulting files.
Plugin Claude Code
Bundles 36 skills, 2 agents · 2,910 tokens together
Web application security review skills: architecture recon, 33 vulnerability-class detectors, and a consolidated severity-ranked report.
Skill Claude CodeCodex
Syntax guide and ecosystem reference for writing Typst (.typ) files. Use this skill when writing, editing, or debugging Typst documents. Covers core syntax, common errors, packages, and best practices.
Plugin Claude Code
Bundles 1 skill · 14 tokens together
Generate sequence diagrams directly from natural language descriptions using Swimlanes.io syntax. Describe any workflow (authentication flows, API interactions, microservice communication, CI/CD pipelines) and get correctly formatted diagram code instantly. Supports solid, dashed, and bold arrows, conditional branches.
Agent Claude Code
Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.
Command Claude Code
Copy the last Claude response to clipboard.
Skill Claude CodeCodex
A search and download assistant for galgames, also called visual novels or ADV games, including recommendations and translation patches.
lodetomasi/claude-code-training-lab
Plugin Claude Code
Bundles 1 skill, 1 command, 1 agent, 1 hook · 44 tokens together
Plugin aziendale di esempio con skill, hook e agent per il workflow di sviluppo.
Skill Claude Code needs its repo
Continues, extends, fixes, or resumes work on a Shipjaw-scaffolded or Shipjaw-adopted TypeScript/Next app that already has documentation/knowledge-base/ and INDEX.md. Token-cheap: read INDEX.md first, then at most 1–2 relevant docs. Use when adding features, fixing bugs, refactors, implementing the next phase…
Skill Claude CodeCodex
Validate a synthetic Agent Skill when testing SkillWitness locally or in CI.
Skill Claude CodeCodex
Govern material engineering work in any AOI-configured repository through the installed AOI CLI. Use when AOI hooks report an active project, before edits or external actions, and when planning, claiming, delegating, verifying, checkpointing, delivering, or closing AOI tasks.
Skill Claude CodeCodex
A tool for turning reports, research, or business analysis into consulting-style presentation decks associated with firms such as McKinsey, BCG, and Bain. It can produce a standalone HTML file or an editable PowerPoint file.
KondrashovDenis/claude-md-docx-skill
Skill Claude CodeCodex
Tools for reading and creating Word .docx files on Windows, including documents containing Cyrillic text. They work without Pandoc or LibreOffice.
Plugin Claude Code
Bundles 5 commands · 220 tokens together
See your Claude Code spend in USD per project, per git branch, and over time (by day, week, month), computed locally by reading the session logs Claude Code already writes to /.claude/projects. Never touches API traffic. Zero key, zero prompts, zero latency.
ShiftinBits/constellation-claude
Plugin Claude Code
Bundles 8 skills, 1 MCP server · 152 tokens together
Upgrade Claude from text search to code understanding.
Plugin Claude Code
Bundles 7 commands, 2 hooks · 63 tokens together
Plays a short notification sound when an AI coding agent CLI (Claude Code or Codex) requests permission or finishes responding.
Skill Claude CodeCodex
Reference for the rmine CLI (Redmine client) — issue, time-tracking, and project commands, filter/name-matching semantics, and profile handling. Use when the user asks about Redmine issues, tickets, time logging, or projects.
Skill Claude CodeCodex
Transforma um BRIEF (ou ideia já discutida) em PLAN.md atômico — tasks com critério verificável, vertical slices, must-haves observáveis, esforço estimado e pontos de reset de contexto. Sem código no plano. Auto-suficiente para reset — uma nova sessão consegue retomar lendo só o PLAN.md. Use quando o usuário disser…
EditorialOS/pinterest-marketing-strategist
Plugin Claude Code
Bundles 3 skills, 3 commands, 1 MCP server · 280 tokens together
Produce composed Pinterest pins from your real documents and approved image library. Reads your Google Drive folder for brand context, scans your image library for visual assets, matches images to generated copy, and outputs pins ready to review and post. Tracks performance and learns from every batch — better images.
Skill Claude Code
Audit a skill against Pocock's write-a-skill spec and return a prioritized, diagnose-only fix report.
Plugin Claude Code
Bundles 9 commands, 8 agents, 31 hooks · 533 tokens together
A /goal engine whose completion is EARNED, not announced. Acceptance criteria are real shell commands; the Stop hook re-runs every one of them and only exits 0 lets a goal finish. Verification defends itself: a sealed integrity ledger re-hashes each criterion before the gate trusts it, a negative-control red team…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: