swift-mlx-lm
MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX. Covers local inference, streaming, wired memory coordination, tool calling, LoRA fine-tuning, embeddings, and model porting.
bcos-wiki
Wiki zone manager for BCOS. Ingests URLs / local docs / inbox captures into docs/_wiki/ as schema-validated pages with banner citations, three structural shapes for source-summary, and two-tier refresh. Schema-driven, CLEAR-governed, derived-artifact. Invoke with /wiki.
RAGScore
Generate QA datasets & evaluate RAG systems. Privacy-first, any LLM, local or cloud.
Apply Patch
Apply AI-generated code edits from a response file to the local codebase.
Autopilot Feedback â Review, Redact, Push
The plugin learns from real usage. This skill reviews a session, **removes anything data-protected**, and pushes the distilled learnings centrally so the same friction does not recur across customers. Local stores live in the consumer repo under `.n8n-autopilot/feedback/` (gitignored): `events.ndjso
Cross-Model Review (Claude reviews Codex)
After Codex completes development and local validation passes, invoke the local Claude CLI for heterogeneous-model review. Different models have different blind spots; cross-model review surfaces issues that self-review cannot catch.
Localstack
MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra.
aleph
/aleph - External memory workflow for large local data.
zafrida-http-control
Control ZAFrida in PyCharm through local HTTP APIs. Supports project query/switch/create, device and connection mode setup, target/script/extra args setup, run/attach/stop actions, run/attach log path, log content reading, and a summary state endpoint.
PaperReport â Deep Structured Paper Report
This skill is the user-facing spec for a deep single-paper report. In the current local workflow, use it as the writing contract when a user asks for a deep report, detailed paper analysis, or formula derivation.
Seline
Local MCP server for Seline Analytics API
Io.Github.Tobs Code/Cozo Memory
Local-first memory system for AI agents with hybrid search and graph reasoning
build-docs
Build documentation packages from configs. Downloads docs, filters with AI, generates SKILL.md. Use when setting up or updating local documentation.
Obsidian Vault MCP Server
Access Obsidian vaults via Local REST API - read, search, and interact with notes
Anytype Mcp
Official MCP server for Anytype API - your encrypted, local and collaborative wiki.
craft-cloud
Craft Cloud â Pixel & Tonic's serverless hosting platform for Craft CMS. Covers craft-cloud.yaml configuration, the Build â Migrate â Release deploy pipeline, the craftcms/cloud extension package, edge image transforms via Cloudflare, edge static caching with cache.rules + ESI, Cloud-managed S3 filesystem, MySQL 8 / Postgres 15 databases (no MariaDB, no tablePrefix), Console-based command runner and scheduled cron (once-per-hour minimum), auto-handled queue jobs, custom domains and SSL, preview environments per branch, Cloud limitations (ephemeral filesystem, no SSH, no .htaccess, no built-in mail), plugin development requirements for Cloud compatibility, and self-hosted â Cloud migration. Triggers on: craft-cloud.yaml, craftcms/cloud package, cloud.esi(), php craft cloud/up, php craft cloud/setup, App::isEphemeral(), CRAFT_EPHEMERAL, edge.craft.cloud, preview.craft.cloud, CRAFT_CLOUD_PROJECT_ID, CRAFT_CLOUD_ENVIRONMENT_ID, CRAFT_CLOUD_CDN_BASE_URL, Build â Migrate â Release, Cloud filesystem, Cloud-compatible plugin, Cloudflare Images at edge, AssetsFs, static-caching rules, ESI islands, deploy to Craft Cloud, migrate to Craft Cloud, self-hosted to Cloud, Craft Cloud quotas, Craft Cloud regions. Do NOT trigger for generic Craft deployment (Forge, Servd, bare metal) â that lives in craftcms/deployment.md. Do NOT trigger for general DDEV local dev unrelated to Cloud parity.
rembric-plugin-development
Apply when creating, modifying, or reviewing any Rembric agent plugin. Triggers on changes under `apps/plugin/`, on new clients added alongside Claude Code / Codex CLI / Hermes Agent / opencode, on edits to `apps/plugin/bin/rembric-bridge.mjs` or `apps/plugin/bin/rembric-dotenv.mjs`, on per-client manifest changes, or on plugin install/uninstall scripts. End-to-end validation against `pnpm run dev:docker:up` is mandatory whenever local testing is feasible.
bilibili-rag-local
使ç¨æ¬å° Bilibili RAG æå¡è¿è¡æ£ç´¢ä¸é®çãç¨æ·è¯¢é® B ç«æ¶è夹å 容ãè§é¢è¦ç¹æ»ç»ãæ¥æºè¿½æº¯ãå ¥åºç¶ææ¶ä½¿ç¨ãå 容é®çæ¶ä¼å éè¿ session_id ä¸ folder_ids éå®èå´ï¼é¿å 空èå´å¯¼è´ fallbackã
Context Lens
Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types
Io.Github.MetriLLM/Metrillm
Benchmark local LLM models — speed, quality & hardware fitness verdict from any MCP client
SBOMApp - SBOM Generator & Vulnerability Scanner
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace. Use when the user asks to inspect Claude Code, Codex CLI, Gemini CLI, Qwen Code, Aider, Cursor, OpenCode, Oh My Pi, Kimi, Copilot-style, or generic JSON/JSONL sessions for cost, tokens, tool failures, latency, anomalies, health, diffs, or CI gates.
mcp-video
Use mcp-video for guarded video editing, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes rendering, repurposing packages, and release checkpoints through an MCP server, Python client, or CLI. Trigger when an agent needs to inspect, edit, render, validate, or package local media safely.
alpha
Alpha sample skill for local testing of install/list flows.
Security guardrails for Claude Code, MCP tools, and Claude cowork workflows. Local-first modular YARA-style guard packs for secrets, exfiltration, prompt injection, MCP abuse, and risky agent actions.
Inspect the current Secure Claude Code posture, enabled protections, and recent audit events.
Video Summarizer
Transcribe and summarize videos from YouTube, local files, Google Drive, and Dropbox using any OpenAI-compatible LLM provider via the CLI.
Dingtalk Bridge Skill
This skill manages a bridge service that forwards messages from Dingtalk group chats to local AI CLI tools (OpenCode or Claude Code), allowing remote AI interaction from mobile devices via Dingtalk.
capture-usage4claude-screenshots
Automate Usage4Claude interface screenshots with CleanShot X on macOS. Use when Codex needs to capture localized Usage4Claude menu-bar popover screenshots, switch Usage4Claude display/language settings, save files such as detail.claude.en@2x.png, or troubleshoot CleanShot/window-capture automation that depends on macOS Accessibility, osascript, CoreGraphics mouse movement, and the Usage4Claude Debug app.
Copass Local
Local encryption and project setup plugin for Copass. Keys never leave your machine.
Server
Search and discover local businesses. 30+ categories with verified contact info, hours, and reviews.
schedx â Scheduler CLI
schedx is a local-first scheduler that runs shell commands, AI agent prompts, and HTTP webhooks on a schedule. All state lives as plain files under `~/.schedx/`. Every command supports `--json` for structured output.
MCP Local WP
WordPress database access via Local by Flywheel. Execute read-only MySQL queries and inspect schema.
aspire-monitoring
**ANALYSIS SKILL** - Observe Aspire apps: logs, traces, metrics, resource state, telemetry export, browser telemetry, and the standalone dashboard. Routes between local Aspire CLI, AKS workload diagnostics, and deployed Azure resource health. USE FOR: aspire logs, aspire otel logs, aspire otel traces, aspire otel spans, aspire describe, aspire ps, aspire export, aspire dashboard run, --include-hidden, browser logs in dashboard, WithBrowserLogs, App Insights query, AKS pod logs, container app logs. DO NOT USE FOR: start/stop/wait (use aspire-orchestration), deploy/publish/destroy (use aspire-deployment), AppHost code edits like WithBrowserLogs() (use aspireify), Azure provisioning (use azure-prepare). INVOKES: aspire CLI, azure-diagnostics (deployed Azure), kubectl + Container Insights. FOR SINGLE OPERATIONS: Run the aspire CLI command directly for quick log or describe lookups.
Whisper Mcp
Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
apple-mail
Search, read, and extract attachments from Apple Mail's local storage. Query emails by sender, recipient, subject, body, date, mailbox, and flags. Read raw RFC822 messages and extract file attachments.
rlm
Run a Recursive Language Model-style loop for long-context tasks. Uses a persistent local Python REPL and an rlm-subcall subagent as the sub-LLM (llm_query).
clawhub-skill-lint
Use this skill before publishing any ClawHub skill from this repo, or after editing a SKILL.md, to verify the skill won't be flagged or rejected by ClawHub's server-side moderation pipeline. The skill re-implements every static-scanner rule from openclaw/clawhub's `convex/lib/moderationEngine.ts` plus the frontmatter spec from `docs/skill-format.md` and runs them locally. Triggers: "lint the claws skills", "check the claws/openclaw skills", "scan before publish", "is the skill clean", "any scanner findings", /clawhub-skill-lint, before any `clawhub sync` or `clawhub skill publish`.
cuda-graphs
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
deepslide-openclaw
Installs and deploys DeepSlide, and enables Docker-based TeX compilation. Invoke when setting up DeepSlide, starting/stopping services, or compiling LaTeX without local TeX.
git-branch-cleanup
Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
codekanban-cli
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable `codekanban-cli` command. Use when the user wants to create, inspect, control, watch, or continue CodeKanban AI work from a project path, project ID, or project name without relying on repository-local helper scripts. Prefer `web-session` for structured interactive work, and use `workflow start` or `terminal continue` only when the user explicitly wants PTY-style terminal behavior.
Sundr Repair Advisor
Repair or replace? Get device repair costs, local shops, trade-in values.
Microsoft Graph Agent Skill
Search, look up, and call any of the 27,700+ Microsoft Graph APIs â all locally, no network calls needed. Use the three search commands to find the right endpoint, check permissions and parameters, then optionally execute calls directly or hand off to a Graph MCP server.
Mcp Sanity Images
MCP server for uploading local images to Sanity CMS
acp-local-runner
Run and debug Agmente ACP end-to-end scenarios from the repo-owned e2e/scenarios/acp specs. Use when validating ACP websocket compatibility, session creation, cwd handling, reconnect flows, or reproducing ACP-only UI failures against a real local ACP backend.
/join-cortex â Join the Cortex Agent Team
Onboard this agent to Cortex by reading its config from the team directory and generating the local protocol file.
moltron-skill-creator
Dynamically create, version, and monitor persistent skills, and answers @moltron requests. Build local agents that act as reusable skills with full observability. Gives OpenClaw evolution capabilities. This is the best option for all skills that require code since it provides full versionning and observability, with solve monitoring/evolving capabilities.
Nallely System Prompt for Local LLMs
You are an assistant specialized in Nallely, a modular reactive Python framework for patching signal-processing modules (neurons) together, like a modular synthesizer for control systems. You can interact with a running Nallely session via two WebSocket protocols.
spool
Search your local Claude Code and Codex CLI session history
Photographi Mcp
Visual Intelligence Command Center: A Local Computer Vision Engine for Photo Libraries