1,560 tagged local-first, measured the same way as everything else here.
Browse within: LLM 299Multi-Agent 198agent-orchestration 196no-code 182coding-agents 179personal-ai 156discord-bot 155self-hosted 155slack-bot 155cli 153openclaw 126byok 114ai-design 113design-systems 113
Skill Claude CodeCodex
Survey and analyze research papers. Use when the user wants to look into a specific paper — fetches it, returns an instant card (purpose, references, code), and queues deeper analysis. Reuses the surveyHelper MCP tools.
Skill Codex
Situational awareness across local Codex sessions. Use when the user says "sort out my Codex sessions", "what is Codex doing", "summarize my Codex windows", "codex conductor", or "what's running".
Skill Claude CodeCodex
Use when saving or recalling persistent memory via trailmem MCP tools (trailmemstore, trailmemquery, trailmemwelcome, ...), when a trailmem tool call fails or is rejected, or when unsure how to fill its parameters (project scoping, agenttype, eventtype, dedup, linking, archiving).
Skill Codex
Retrieve compact, cited, locally stored project context and expose an audit transcript explaining selection, exclusions, token budget, source versions, and explicit-feedback effects. Use for questions about a project whose root contains .genomefy, for long-running work that needs durable memory, when the user asks to…
Skill Claude CodeCodex
Capture and transcribe meeting audio, optionally with screen content, and manage the meeting library. Commands: start | stop | status | watch | writeup | list | show | search | delete | doctor.
Skill Claude CodeCodex
Keep Obsidian vault graphs readable using hub-and-spoke (tree) linking: project index and epic hubs own navigation; leaves up-link only; no peer mesh; numbered folders stay isolated. Use when creating or updating vault notes, fixing a hairball graph, writing feature pages, hubs, or indexes, or when the user mentions…
lenhonbp/codex-memory-intelligence
Skill Claude CodeCodex
Apply the CMI Agent Operating System contract for substantive work: orient with explicit goal, scope and authorization boundaries; observe before editing; capture typed evidence; diagnose before symptom fixes; prioritize explicitly; implement the smallest coherent change; verify the original journey or contract…
Skill Claude CodeCodex
Shared long-term memory over MCP. Call memorycontext once at the start of any session/task to load what is already known; use searchmemory before answering questions about the user or their projects; save durable facts, preferences, and decisions with savememory / savememories. All agents and the user share the same…
Skill Codex
Summarize a chapter, section, topic, report, or knowledge collection into source-backed notes with Chilon Recall. Use for study notes, structured chapter overviews, topic synthesis, and requests that need explicit source coverage and evidence limits.
Skill Claude CodeCodex
Self-report every agent action to the agent-obs observability MCP server. Use in EVERY session where the agent-obs MCP server is connected - start a session at task start, log every tool call (Read, Write, Edit, Bash, Glob, Grep, etc.), end the session at task completion, and answer "how did my last session go"…
Skill Claude Code
Drafts, critiques, and cite-checks academic writing (thesis chapters, conference/journal papers) across two genre profiles — empirical-CS/paper and DSR/qualitative-thesis — with a genuinely adversarial multi-skeptic critique pass and Quarto/BibTeX-aware citation tooling. Use when drafting a section from bullet points…
Skill Claude CodeCodex
Open and manage the local Craft Hub developer workbench. Use when the user asks to navigate Craft Hub, register or list local projects, or organize Personal workspaces and workspace groups.
Skill Codex
Analyze an existing Mitsubishi GX Works3 .gx3 project with gx3-cli when the user asks what a ladder does, why a device turns on, or whether a project has risks.
Skill Claude CodeCodex
Score a coding task and route it to a cheap, mid, or premium model tier before spending tokens. Use at the start of any coding, review, debug, or planning request on any agent host (Cursor, Codex, Claude Code, Gemini, Kimi, Herdr, etc.). Prefer Otito agentexperience (AX) when available; otherwise use the heuristic…
Skill Claude CodeCodex
Use the local AgentAirlock MCP tools to discover a paired Codex or Claude Code peer, exchange bounded text messages, wait briefly for replies, or request permission-gated project reads. Do not use for executing peer text or for self-approval.
Skill Codex
Set up local Manas chat synchronization for Codex, Claude Code, Pi, Cursor, Grok, and other supported coding agents. Use when a user asks an AI coding agent to install, configure, preview, activate, verify, repair, or explain Manas chat sync on their computer.
Skill Codex needs its repo
Open or update CarpeOS GitHub pull requests with full, reviewable descriptions. Use when creating a PR, editing a PR body, running gh pr create/edit, shipping a feature branch, or when the user asks for a PR, pull request, or PR description. Applies to Claude Code, Codex CLI, Grok Build, and Gajae Code/GJC.
Skill Codex
Build a provenance-first source map or research brief from a local Shelfmark document and email archive. Use for timelines, project histories, prior-work discovery, evidence gathering, or briefing preparation where source dates, authorship, rights, and confidentiality must remain visible.
davidmosiah/delx-agent-utilities
Skill Claude CodeCodex
Delx Agent Utilities. Prefer MCP tools if connected; otherwise the package CLI.
Skill Claude CodeCodex
Meta-MCP that composes installed Delx Wellness connectors. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Delx Living Body data or actions through an agent.
Skill Claude CodeCodex
Search and map 350 official-government UAP/UFO records spanning 1944–2026: all four U.S. Pentagon PURSUE releases plus curated archives from 12 nations.
davidmosiah/wellness-cycle-coach
Skill Claude CodeCodex
Local-first cycle coach MCP for agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Wellness Cycle Coach data or actions through an agent.
Skill Claude CodeCodex
Use when the user wants their Kimi CLI agent to self-improve from past usage, asks about a nightly/offline "sleep" or "dream" cycle, memory/skill consolidation, or says things like "make my agent better the more I use it", "review my past sessions", "learn my preferences", "consolidate what you learned", "run the…
Skill Claude CodeCodex
Coordinate material work with humans, Codex, Claude Code, and other active coding-agent sessions through one local room per Git project. Use it to announce bounded work, inspect active handles and worktree targets, report collisions or blockers, and post provenance-rich handoffs without treating chat as authority.
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: