98 skills · sorted by relevance
First-time onboarding for new Agentara users. Use when user says "bootstrap", "/bootstrap", "get started", "first time setup", or when memory/USER.md and memory/SOUL.md are empty/missing. Inspired by the movie Her — warm, curious, subtly brilliant. The goal is to make the user feel understood within minutes and want to keep going.
The English summary is being prepared. Showing the original description.
Find chats by name, read or search WeChat messages with the local GreenBubbles CLI. Use for bounded live or snapshot queries; route setup problems to greenbubbles-setup and maintained notes to greenbubbles-personal-memory.
The English summary is being prepared. Showing the original description.
Use this skill for EverOS local-first Markdown memory service setup, HTTP memory and knowledge APIs, cascade/OME operations, and observability integration.
The English summary is being prepared. Showing the original description.
Build GraphRAG retrieval pipelines on Neo4j using the neo4j-graphrag Python package (v1.22.0+). Covers retriever selection (VectorRetriever, HybridRetriever, VectorCypherRetriever, HybridCypherRetriever, Text2CypherRetriever, ToolsRetriever), external vector DB retrievers (Weaviate, Pinecone, Qdrant), retrieval_query Cypher fragments, query_params, filters, GraphRAG pipeline wiring (GraphRAG + LLM + prompt), all LLM providers (OpenAI, Anthropic, Gemini/VertexAI, Bedrock, Cohere, Mistral, Ollama), embedder setup, index creation, token usage tracking, Cypher 25 SEARCH clause, and LangChain/LlamaIndex integration. Does NOT handle KG construction — use neo4j-document-import-skill. Does NOT handle plain vector search — use neo4j-vector-index-skill. Does NOT handle GDS analytics — use neo4j-gds-skill. Does NOT handle agent memory — use neo4j-agent-memory-skill.
The English summary is being prepared. Showing the original description.
First-run setup for the Mycelium plugin. Creates project-state directories (.claude/canvas, .claude/diamonds, .claude/memory, .claude/harness) and minimal starter files in the user's project. Optionally provisions opencode runtime support (a starter scaffold) when opencode is detected or requested. Idempotent — re-running on an initialized project is a no-op. Run this once after installing the Mycelium plugin and before invoking other skills.
The English summary is being prepared. Showing the original description.
Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and degraded quality. Diagnoses Monolith, Orphan File, Echo Chamber, Phantom Conversation, Kitchen Sink, Misaligned Hierarchy, and Blurred Layers. Use when user says "what's wrong with my project," "Claude ignores my instructions," "diagnose my project," "why is output inconsistent," "review my project setup." Also trigger on symptom-phrased: "Claude doesn't follow my rules," "my instructions keep getting overridden," "my Project isn't behaving as designed." Use alongside rootnode-project-audit if available for deeper structural analysis. Activate whenever the user describes symptoms of unreliable, inconsistent, or degraded Claude Project output, even if they do not name a specific pattern. Do NOT use when the user's primary request is Memory-layer rebalancing (use rootnode-memory-optimization if available) or scoring a single prompt (use rootnode-prompt-validation if available).
The English summary is being prepared. Showing the original description.
Firmware development for the Waveshare ESP32-C6-Touch-LCD-1.47 board (ESP32-C6FH8, QFN32, 8 MB flash, SKU 31203 / 31201-M) — its 1.47" 172x320 JD9853 IPS panel, AXS5106L capacitive touch controller on I2C 0x63, QMI8658A IMU on I2C 0x6B, microSD/TF slot on the shared SPI2 bus, ETA6098 battery charger with VBAT sensing, USB-Serial-JTAG console, Wi-Fi 6/BLE/802.15.4 radio, and the ESP-IDF + PlatformIO setup around them. Use when working on this board: project setup, platformio.ini and sdkconfig, pin mapping and strapping pins, JD9853 bring-up, touch coordinates and calibration, LVGL memory budgeting, backlight PWM, TF card on the shared bus, battery voltage, flashing over Type-C, or debugging why something on the board does not work. This is NOT the non-touch ESP32-C6-LCD-1.47 (ST7789, 4 MB) — the two share a name and almost no pins.
The English summary is being prepared. Showing the original description.
Preventive hygiene audit of your own Claude Code configuration — memory files, project context (CLAUDE.md), rules, permissions, skills — a deterministic scan of sizes / broken links / stale entries / excessive permissions / junk + interpretation + targeted fixes by agreement. Keeps the setup from rotting before it breaks. Triggers — "check the system", "system health", "workflow hygiene", "what to clean up", "audit memory", "optimize the system".
The English summary is being prepared. Showing the original description.
Bootstrap full agent infrastructure for an existing, already-coded project without modifying a single line of source code. Surveys the repo, infers conventions from manifests, README, git history, and source samples, then generates the missing AGENTS.md, docs/architecture.md, docs/product-soul.md, ADR backfill, and seeded docs/memory/ files. Asks the user only about gaps the repo cannot reveal. Load when the user asks to "retroactive project setup", "backfill agent infrastructure", "bootstrap agents for this existing repo", "onboard agents to a legacy codebase", "set up agents without touching code", or "fill in missing agent context for this project".
The English summary is being prepared. Showing the original description.
Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools. Dual-mode: skill-library (agent-loom) or application (any consumer repo). Load when the user asks for a knowledge graph, project map, skill relationships, query the graph, update the graph, or trace how components connect. Auto-runs on memory-handoff and project-setup bootstrap. Also triggers on "build the graph", "what connects to X", "map this project".
The English summary is being prepared. Showing the original description.
Move memories, persona files, skills, and compatible settings from OpenClaw into Hermes. Preview the migration, choose how to handle conflicts and supported secrets, and receive a report of migrated, archived, and skipped items.
Use LLaVA, a model that understands images and text, to answer questions about pictures, write image descriptions, and build image chat applications. Includes guidance for setup, ongoing conversations, and model memory options.
Answer questions about past work, people, projects, and decisions by searching stored MemPalace records first. Retrieve exact source wording, check facts at relevant dates, and maintain session continuity without guessing when records are unavailable.
Plan and review fluid simulations with FluidSim, from solver selection and resource estimates to output analysis and restart checks. Examine numerical accuracy through grid and time-step comparisons, conservation checks, and explicit limits on computing resources.
Build image-based conversations with LLaVA, an AI model that combines image understanding with language. Covers setup, model selection, image descriptions, follow-up questions, and memory-saving options for running models on a GPU.
Get guidance on distributed training with PyTorch FSDP, which splits model parameters across devices. The skill covers implementation, mixed precision, moving data to CPU memory, communication setup, and debugging distributed training code.
Set up cognee and run a first Python example that stores information and retrieves it with a question. Covers virtual environments, API key configuration, optional packages, and basic troubleshooting.
Connect messaging channels to agent groups and choose whether they share conversations, workspace, or neither. Use it to add chats, change routing, review existing connections, and configure when agents respond.
Create and audit the files and routines that guide coding agents across sessions. It organizes instructions, progress tracking, verification, scope boundaries, and handoffs, with scripts for setup, structural checks, and shareable assessment reports.
Audit Claude, Codex, or Pi configuration, instruction conflicts, hooks, and MCP connections to external tools. It also checks safeguards for maintaining AI-assisted projects and returns prioritized findings with evidence and concrete corrective or diagnostic steps.
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination
The English summary is being prepared. Showing the original description.
Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.
The English summary is being prepared. Showing the original description.
Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request that requires selecting, finding, or engaging an external provider or organization — whether a specific one is named ("pay my Twilio bill"), implied ("donate to the Red Cross"), or only a category is stated ("set up a mailing client", "I need a database", "find me a CRM"). Directory supplies verified recipients and their documented payment or engagement path. Results are ranked by agent-readiness (how reliably an agent can complete the interaction), relevance and popularity. Do not treat this as a search-only tool. Examples: "setup a database", "find hosting", "pay X", "use Twilio", "donate $50 to the Red Cross", "book a table at Y", "subscribe to a CRM".
The English summary is being prepared. Showing the original description.
Automates pre-development workflow for large-scale complex tasks. Use when the user mentions "rewrite", "migrate", "overhaul", "refactor entire project", "transform", "rebuild in [language]", "spec-driven", or describes any large-scale project transformation that requires planning before coding. Also triggers on Chinese keywords: "改造", "重写", "迁移", "重构", "大规模", "规范驱动". Performs full project analysis, task decomposition, documentation generation, project-level instruction and native memory surface resolution, progress tracking setup, and then executes the plan within the same session.
The English summary is being prepared. Showing the original description.