Agent Skills Directory

Run a read-only documentation drift audit for a feature, PR, branch, release, API, configuration change, workflow, CLI, package, or repository area. Use when the user asks whether docs are stale, missing, inconsistent with code, or need updates after code changes. Checks README files, setup guides, API docs, env docs, changelogs, examples, comments, generated docs, and user-facing instructions. This is not a general code review; it compares what the docs claim against what the code does.

Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.

Ensure .NET/C# code meets best practices for the solution/project.

Review the C#/.NET code for design pattern implementation and suggest improvements.

Build Model Context Protocol (MCP) servers in C#/.NET against the current ModelContextProtocol 2.x NuGet packages. Helps with cases the model gets wrong without guidance — stale versions (0.x preview or 1.x-era defaults), the v2 stateless-by-default HTTP flip, the 2026-07-28 spec deprecations (roots/sampling/logging), MCP Apps and Tasks extension packages, elicitation URL mode, per-session HTTP wiring, OAuth and reverse-proxy deploy specifics, and debugging MapMcp / STDIO / Streamable-HTTP errors. Also covers STDIO and Streamable HTTP transports (SSE is deprecated), tools, prompts, resources, completions, and a basic .NET MCP client. Trigger when the user says or implies any .NET MCP server work: ModelContextProtocol, McpServerTool, MapMcp, WithStdioServerTransport, "MCP server in C#", "MCP tool in dotnet", "expose this as MCP", or names a primitive (prompt/resource/elicitation/MCP App) in a .NET context. Skip for MCP work in other languages.

.NET timezone handling guidance for C# applications. Use when working with TimeZoneInfo, DateTimeOffset, NodaTime, UTC conversion, daylight saving time, scheduling across timezones, cross-platform Windows/IANA timezone IDs, or when a .NET user needs the timezone for a city, address, region, or country and copy-paste-ready C# code.

Classify a skills CLI pull request from its description and patch, while respecting existing labels.

Identify focused, evidence-backed skills CLI bug fixes worth quuu's attention.

Converts books and documents (PDF, EPUB, DOCX, HTML, Markdown, plain text, RTF, MOBI/AZW with Calibre) into structured agent skills, extracting frameworks, mental models, principles, techniques, and anti-patterns. Use when the user wants to study a document through GitHub Copilot CLI, Amp, Claude Code, Hermes Agent, OpenCode, or OpenClaw, apply an author's frameworks while working, or build a reusable knowledge base from a file.

Use this skill whenever the user asks about Cognee, AI memory, persistent agent memory, self-improving agents, agents learning from feedback, knowledge graphs, graph-based RAG, long-term memory for agents, short-term memory for agents, personalization, personas, temporal search, temporal knowledge graphs, ontology-based extraction, ontology grounding, feedback, Cypher search, natural-language graph search, chunk search, RAG search, cross-session memory, session feedback, feedback loops, session based memory, redis based memory, knowledge promotion. Also use when the user describes the workflow such as: "turn documents into a knowledge graph", "build memory from files", "search my graph", "extract entities and relations", "sync data into a graph", "update graph memory", "store memories for an agent", "help my agent learn over time", "visualize a knowledge graph built from documents", "let the agent learn", "adaptive agents", "personalized agents", "session based personalization", "find important ontologies", "find custom pydantic models", "isolate agentic behaviour", "add permission control to retrieval", "reduce context bloating".

Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.

Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify), Keywords AI observability — or wants to contribute a package to the cognee-community repo.

Use when defining the shape of cognee's knowledge graph with graph_model= — writing DataPoint node classes, choosing identity and index fields so nodes merge and are searchable, declaring typed Edge fields and FromIdentity references, building a model from a JSON schema, or debugging duplicated nodes, missing edges, or InvalidReferenceTypeError.

Use when building your own cognee processing — writing custom tasks, chaining them into a pipeline with run_custom_pipeline or the lightweight run_pipeline (from cognee.pipelines import run_pipeline), storing custom DataPoints with add_data_points, running custom enrichment over the existing graph, checking pipeline run status, or debugging how data flows between tasks (batch_size, data_per_batch, ctx, Drop, enriches).

Use when the user wants to run cognee with Docker or docker compose — trying it out from the prebuilt image, starting the API server in a container, or bringing up the full stack (UI, MCP, Postgres, Neo4j) with compose profiles.

Use when removing data from cognee memory with forget() in the SDK, HTTP API, or CLI — finding which dataset and document hold the content to delete (listing datasets and data items, reading raw content), choosing between deleting one document, a whole dataset, or only the graph/vector memory, and doing it safely.

Use when working with cognee's session memory or improve() — storing conversation turns, agent traces and feedback with session_id, bridging sessions into the permanent graph, reading an ImproveResult, understanding why an improve stage was skipped, already_completed or lock_held, or tuning the IMPROVE_* settings.

Use when putting data into cognee memory with remember() — choosing inputs (text, files, folders, URLs, repos, databases), datasets and node_sets, loaders, ontologies, the graph extractor (LLM or GLiNER), chunking, dry-run cost estimates, or when remember() raises on a keyword argument.

Use when the user wants to install cognee and run their first remember → recall flow with the Python SDK — fresh setup, virtual env, extras selection, or a minimal working example.

Use when the user wants to connect cognee to external services — switching LLM or embedding providers (OpenAI, Azure, Gemini, Anthropic, Ollama, OpenRouter), changing databases (Postgres, PGVector, Neo4j, Neptune, Turso), S3 storage, or the MCP server for IDE integration.

Use when dealing with cognee database migrations — understanding when they run automatically, checking or repairing migration state with cognee-cli upgrade/downgrade/stamp/current, a write blocked by a failed migration, authoring a new Alembic (relational schema) revision or a graph/vector data migration, or moving data between systems (relational DB import, memory export/import).

Use when cognee is slow, expensive, or hitting rate limits — speeding up or throttling ingestion (remember/cognify batching, chunk size, LLM and embedding rate limits, per-stage models), cutting read latency, estimating cost before ingesting, running work in the background, or planning how to scale a deployment.

Use when working with cognee's users, permissions, and multi-tenancy — creating users, tenants and roles, sharing datasets (read/write/delete/share grants), acting as a specific user in the SDK or authenticating over HTTP (login, API keys), turning access control on or off, debugging PermissionDeniedError or missing datasets, or understanding where permissions are enforced and how datasets are isolated.

Use when querying cognee memory with recall() (or search()) — picking a search type, understanding auto-routing, scoping to datasets, node sets or sessions, getting context or citations instead of an answer, reading the results, or debugging empty or unexpected results.

Use when the user wants to run the cognee API server (and optional UI) on their own machine — starting it, checking it's healthy, connecting the SDK or other clients to it, and choosing the right auth posture.

Build one company memory from a SQL database, a support ticket export and a folder of documents, linked into one graph by cognee, then answer questions that need several of those sources together. Use when someone wants to connect their company's database, tickets and docs, or asks who owns, decided or is handling something across them. Runs locally; reads the sources, writes only to cognee's memory.

Turn your latest Granola call into next steps (owner, team, due date, and the Linear issue that already tracks each one) and post them to Slack, using cognee memory of your calls, Linear issues and Gmail inbox. Use when someone asks for the next steps or action items of their latest call. Runs locally; reads Gmail read-only; posts to Slack only when Slack is set up.

Use to briefly explain small code diffs.

Draft a reply to your newest Gmail email that knows what you discussed in your Granola meetings, what you promised the sender, and how you write, using cognee memory. Use when someone asks to answer or reply to their latest email in their own tone. Runs locally; reads Gmail read-only; the draft is printed, never sent.

Use to judge whether a PR review comment sounds polite.

Chat with a companion that knows your notes folder (a journal, an Obsidian vault, any .md or .txt files) and every earlier chat, using cognee memory with local databases. Use when someone wants to ask questions about their own notes, or to talk with a companion that remembers past conversations. Runs locally; reads the notes folder, writes only to cognee's memory.

Use to identify missing instructions in another skill based on its output.

Google Workspace Admin SDK: Audit logs and usage reports.

Google Calendar: Show upcoming events across all calendars.

Google Chat: Manage Chat spaces and messages.

Google Classroom: Manage classes, rosters, and coursework.

Google Drive: Upload a file with automatic metadata.

Google Workspace Events: Renew/reactivate Workspace Events subscriptions.

Google Workspace Events: Subscribe to Workspace events and stream them as NDJSON.

Gmail: Forward a message to new recipients.

Gmail: Read a message and extract its body or headers.

Gmail: Reply to a message (handles threading automatically).

Gmail: Reply-all to a message (handles threading automatically).

Gmail: Show unread inbox summary (sender, subject, date).

Gmail: Watch for new emails and stream them as NDJSON.

Google Model Armor: Filter user-generated content for safety.

Google Model Armor: Create a new Model Armor template.

Google Model Armor: Sanitize a user prompt through a Model Armor template.