ChromaDB
DatabaseCommonly used with
Skills using ChromaDB (84)
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
standup
Facilitate a read-only standup across git worktrees, branches, or PRs to compare changes and produce one consolidation plan.
babysit
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
design-is
Audit a design against Dieter Rams' ten "Good design is..." principles, then hand off a /make-plan prompt for one of three outcomes — new design, refine design, or redesign. Use when the user says "audit this design", "design review", "check this UI against Rams", "is this UI good", "critique this design", "design audit", or asks for a critique that should lead to a plan.
knowledge-agent
Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.
make-plan
Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
mem-search
Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
oh-my-issues
Cluster a GitHub issue backlog by root cause into a small set of plan-master issues, redirect children with a standardized comment, and bundle architectural-fix PRs that close clusters atomically. Use when an issue tracker has accumulated dozens of reports that share underlying defects, when asked to triage / consolidate / cluster / dedupe issues, when asked to build a plan series or roadmap from open issues, or when routing a new incoming bug into an existing plan.
pathfinder
Map a codebase into feature-grouped flowcharts, identify duplicated concerns across features, and propose a unified architecture. Use when asked to "find the ideal path," unify duplicated systems, or audit architecture before a refactor. Emits a proposed unified flowchart plus per-system /make-plan prompts.
smart-explore
Token-optimized structural code search using tree-sitter AST parsing. Use instead of reading full files when you need to understand code structure, find functions, or explore a codebase efficiently.
timeline-report
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline. Use when asked for a timeline report, project history analysis, development journey, or full project report.
version-bump
Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. NPM publishing (so `npx claude-mem@X.Y.Z` resolves) is handed off to the human maintainer, who raised npm security.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests", "week-by-week story", "serial timeline", or "narrative chapters" of a project's history.
wowerpoint
Turn one document into a kawaii NotebookLM slide-deck PDF. Use for "wowerpoint this", "make a deck about <file>", "turn this report into slides", or any request to render a single document as shareable narrative slides.
chroma
Embedding database for RAG and semantic search.
do
Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.
how-it-works
Explain how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks "how does claude-mem work?" or "what is this thing doing?".
learn-codebase
Prime a codebase by reading every source file in full. Use when starting work on a new or unfamiliar project, or when the user asks to "learn the codebase", "read the codebase", "prime", or "get up to speed".
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
coding-standards
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
continuous-learning
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
frontend-patterns
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
golang-testing
Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage. Follows TDD methodology with idiomatic Go practices.
iterative-retrieval
Pattern for progressively refining context retrieval to solve the subagent context problem
postgres-patterns
PostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.
security-review
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
mem9
Persistent cloud memory for OpenClaw agents. Use when users say: - "install mem9" - "setup memory" - "add memory plugin" - "openclaw memory" - "mem9 onboarding" - "memory not working" - "import memories" - "upload sessions"
ai-portable-setup
Erstellt eine portable KI-Arbeitsumgebung auf einem USB-Stick oder beliebigem Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
agenticx-memory-architect
Guide for setting up and using the AgenticX memory system including Mem0 integration, long-term memory, context management, and memory-enhanced agents. Use when the user wants to add memory to agents, persist conversation history, build memory-aware workflows, or integrate with Mem0 for long-term recall.
agenticx-quickstart
AgenticX zero-to-hero quickstart guide. Use when the user wants to get started with AgenticX, create their first project, build their first agent, or run their first workflow. Covers installation, project scaffolding, agent creation, task execution, and CLI basics.
cortex-broadcast
llm-wiki style broadcast ingest — conversational update of related existing pages when a Raw has been distilled. Use when the user says "broadcast", "跑 broadcast", "compound this into the vault", "merge pending-merge", "process broadcast queue", or when cortex-distill invokes broadcast inline after Step 8 commit (automatic dispatch for every new / pending-merge Raw).
cortex-distill
Distill raw session records into refined Notes and Projects. Use when the user says "提煉", "整理 raw", "distill", or "distill raw records".
cortex-evolve
Save knowledge to the cortex vault. Use when the user says "存到 cortex", "記一下", "save to cortex", "記到筆記", "cortex evolve", or when the session-suggest hook recommends saving content. Handles Notes and Projects.
cortex-query
Search and retrieve content from the cortex vault — the user's external memory. Use (1) when the user says "查 cortex", "之前有記過", "cortex 裡有沒有", "check my notes", "what did I write about", AND (2) PROACTIVELY — before answering any non-trivial question about ongoing projects, internal company tooling, cortex-vec, plugin development, NAS debugging, DSM workflows, or any topic that resembles prior work the user might have notes on. When the SessionStart hook lists vault topics and the user's request matches one, search cortex BEFORE asking clarifying questions or guessing. Treat the vault as authoritative prior context: searching it cheaply is always better than reinventing an answer the user already wrote down.
cortex-takeoff
Create or resume a session takeoff baton — a curated, ephemeral, git-ignored hand-off note that lets the next Claude session continue a long-running task. Use when the user says "交接", "takeoff", "交棒", "context 快滿了交接給下個 session", "hand off to next session", "/cortex:takeoff", "takeoff resume", or "takeoff done". The baton is scaffolding, not knowledge: it is never committed, distilled, broadcast, or indexed.
using-cortex
Use when starting any task or answering any non-trivial question in a cortex-enabled session — establishes that the cortex vault is the user's external memory and should be consulted BEFORE guessing, asking clarifying questions, or doing fresh exploration. Trigger unconditionally on conversation start, on every new user request that touches a domain the user has worked on before, and whenever the request mentions an ongoing project, internal company tooling, recurring topic, or anything that smells like prior work. If the SessionStart hook surfaced vault topics and the request matches one — search first.
mem9-recall
Search shared memories from past sessions. Use when the user's question could benefit from historical context, past decisions, project knowledge, or team expertise.
mem9-store
Save important information to shared memory. Use when the user asks you to remember, note down, or save something for future sessions.
mem9-setup
Setup mem9 persistent memory for OpenCode. Triggers: set up mem9, install mem9, configure memory, enable memory, setup memory, mem9 onboarding, memory not working.
mnemos-setup
Setup mnemos persistent memory with mnemo-server. Triggers: "set up mnemos", "install mnemo plugin", "configure memory plugin", "configure openclaw memory", "configure opencode memory", "configure claude code memory".
algorithmic-patterns
L-systems, cellular automata, agent-based modeling, swarm intelligence, reaction-diffusion, growth algorithms, packing algorithms, and nature-inspired computation for AEC design
bim-scripting
Revit API fundamentals, Dynamo for Revit, pyRevit framework, IFC schema and openBIM, model checking, automated documentation, clash detection, and BIM interoperability tools for AEC computational design
computational-design-calculator
Python calculators for geometry analysis, structural checking, solar calculations, panel optimization, mesh analysis, material estimation, and fabrication cost estimation for AEC computational design
computational-design-foundations
Auto-activating foundation layer providing computational design paradigms, key pioneers, tools landscape, core concepts, and skill routing for all AEC computational design tasks
computational-geometry
NURBS curves and surfaces, mesh geometry, boolean operations, subdivision surfaces, tessellation methods, surface analysis, and point cloud processing for AEC computational design
data-driven-design
GIS integration, sensor data, occupancy analytics, space syntax analysis, urban data analytics, climate data processing, and API data sources for evidence-based AEC computational design
design-automation
Rule-based design systems, constraint satisfaction, space planning algorithms, automated layout generation, drawing automation, code compliance checking, and computational workflows for AEC design automation
digital-fabrication
CNC milling, robotic fabrication, additive manufacturing, laser cutting, timber joinery, formwork design, assembly sequencing, and file preparation for digitally-fabricated AEC components
environmental-simulation
Daylight analysis, solar radiation, energy simulation, CFD wind analysis, thermal comfort, acoustic simulation, and the Ladybug Tools ecosystem for performance-driven AEC computational design
facade-computation
Panelization strategies, surface rationalization, attractor-based patterning, double-skin facades, kinetic and responsive facades, environmental performance facades, and fabrication-aware facade design for AEC
generative-design
Evolutionary algorithms, multi-objective optimization, design space exploration, fitness function design, population-based methods, and generative workflows for AEC computational design
interoperability
File format encyclopedia, data exchange strategies, API integration patterns, Grasshopper-to-Revit pipelines, Rhino.Inside workflows, Speckle data streams, and schema mapping for AEC computational design
machine-learning-for-aec
Computer vision for buildings, image-to-floorplan, generative ML models, performance prediction, structural analysis ML, energy prediction, natural language to design, and point cloud ML for AEC computational design
mesh-processing
Mesh data structures, mesh operations, mesh analysis, mesh repair, UV mapping and unfolding, quad meshing, mesh-to-NURBS conversion, and mesh quality assessment for AEC computational design
optimization-methods
Genetic algorithms, simulated annealing, particle swarm optimization, gradient-based methods, topology optimization, shape optimization, size optimization, and benchmark problems for AEC computational design
parametric-modeling
Parametric design methodology, data structures, constraint systems, Grasshopper and Dynamo patterns, parameter space exploration, and associative geometry for AEC computational design
scripting-reference
Python for Rhino and Grasshopper (RhinoCommon, rhinoscriptsyntax, ghpythonlib), C# for Grasshopper components, Python for Revit (pyRevit, RevitPythonShell), JavaScript for web 3D (Three.js), and code patterns for AEC computational design
structural-computation
Finite element analysis fundamentals, form-finding methods, shell and gridshell structures, topology optimization, structural optimization, material-aware computation, and computational structural tools for AEC
mcp-developer
Skill para desarrollar, mantener y extender el servidor MCP de Obsidian. Incluye patrones de código, arquitectura, testing y gestión de paquetes.
codex-break-loop
Post-bug-fix retrospective — classify root cause, identify prevention, write the lesson into specs. Use after fixing any non-trivial bug, when a task involving 'fix', 'bug', 'debug', or 'diagnose' is being finished, or when the user asks 'what went wrong', 'why did this break', 'root cause', or 'lessons learned'. Also use when the lifecycle hook reminds you to run break-loop.
codex-spec-bootstrap
Analyze a codebase and generate durable spec files from existing patterns, architecture, and conventions. Use to initialize or refresh .codex/spec/ for a project. Also use when the lifecycle hook reminds you to run spec-bootstrap, when a project has empty or template-only specs, when the user says 'generate specs', 'initialize specs', 'bootstrap specs', or 'make the codebase context durable'.
grill-me
Brainstorm engine — interview the user about a plan/design, auto-write PRD and context manifests as answers resolve. Use when the user wants to stress-test a plan, brainstorm a feature, design architecture, or says 'grill me', 'brainstorm', 'let's plan', 'design this', or describes a new feature they want to build. Also use when the workflow phase is 'planning' and a task is active.
searching-apple-notes
Search, recall, and create Apple Notes via semantic vector search powered by Qwen3-Embedding-0.6B and ChromaDB. Use when the user asks to find notes, search memos, recall what they previously wrote, needs note content as context for an answer, or wants to save an insight from the current conversation into Apple Notes. Triggers on phrases like "find in my notes", "search my notes", "what did I write about", "recall my note on", "do I have notes about", "save this to notes", "save this insight", "查我的笔记", "找一下我写过的", "存到备忘录".
lorekeeper-dev
Engineering practices for developing the Lorekeeper codebase. Load this skill when working on Lorekeeper source code, fixing bugs, adding features, writing tests, or reviewing PRs. Covers architecture conventions, SQLite/LanceDB/Chroma quirks, testing patterns, and the verification standard for shipped changes. For backlog/ticket workflow, see backlog-management skill.
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
codex-before-dev
Load task PRD and project specs before writing code. Use before implementation, refactors, or harness changes.
codex-check
Verify recent Codex harness or project changes against task requirements, specs, tests, and rollout checks.
codex-continue
Resume the current Codex harness task. Use when returning to a task, when the user asks what state we are in, or when the conversation has shifted between planning, implementation, and checking.
codex-update-spec
Update durable project specs/docs when implementation changes architecture, workflow, conventions, or recurring lessons.
vector-db-init
Interactively initializes the Vector DB plugin. Guided discovery asks which folders to index, confirms the manifest, then scaffolds vector_profiles.json for high-performance In-Process or Native Server connections. Mandatory first step before ingestion or search.
vector-db-launch
Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.
codex-finish-work
Finish a Codex harness task after implementation, checking, spec updates, and rollout verification.
vector-db-audit
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
vector-db-cleanup
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>
vector-db-ingest
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>
vector-db-search
Semantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase search protocol). V2 includes L4/L5 retrieval constraints.
access
Manage WeChat channel access — approve pairings, edit allowlists, set DM policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the WeChat channel.
configure
Set up the WeChat channel — scan QR code to login, check channel status. Use when the user asks to configure WeChat, login, or check channel status.
Integration detected automatically from skill content. Some results may be false positives.