Gemini, Google AI Studio, and Vertex AI workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.
Research-before-coding workflow: search npm/PyPI, MCP servers, skills, and GitHub for existing tools before writing custom code, then adopt, extend, or build. Launches the researcher agent for non-trivial needs. Use when starting a feature, adding a dependency or integration, or about to write a utility that may already exist.
Inspect or modify Letta Code's own memory, model, context window, system prompt, compaction, permissions, toolsets, mods, skills, channels, schedules, agent secrets, and local runtime settings. Use when the user asks how this agent or conversation is configured, asks about account usage, remaining credits, or model quota, asks you to change how you behave or how the harness runs you, or renames you.
Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.
Diagnose and repair MemFS repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts. Do not load for routine memory reads or edits.
Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot-length distribution, hero stills, screen-blend overlay plates, and a text spec for a generative model. Use when the user wants to capture the look of reference footage, build a repeatable look, mint assets from references, or reproduce someone's grade and pacing.
Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Grok Build, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-driven sessions ("telephone game" flow). For coding-agent thread requests, read this skill first, then use only sessionsspawn for thread creation. Codex chat binding defaults to the native Codex app-server plugin unless ACP is explicit or background spawn needs ACP.
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura tool is present, whenever the user refers to past work ("what did we decide", "last time", "earlier"), or whenever any durable fact needs to be stored, recalled, superseded, or shared with the fleet. Do not use it for throwaway within-session scratch state.
Persistent per-project memory for Claude Code (Context Keeper) driven by deterministic Node.js /ck commands: init, save, resume, info, list, forget, and v1-to-v2 migrate, plus a SessionStart hook that injects a compact project brief. Use when context must survive across sessions, saving session state with next steps and decisions, resuming where a previous session left off, or picking up a project without re-explaining it.
Send chat completions, stream responses, and start an interactive REPL session from the CLI. Supports all OmniRoute providers, combo routing, and system prompt configuration.
Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.
Manage provider connections from the CLI: list available/configured providers, add, test, test-all, validate, rotate API keys, and view per-provider metrics.
Operate on GitLab projects, merge requests, pipelines, and repository contents through a GitLab account the user's team has bound to Nuphos. Nuphos backend hands out the binding's short-lived OAuth token; the agent talks to the GitLab API and clones or pushes over HTTPS directly. Use whenever the user asks about their GitLab repos, MRs, CI pipelines, wants code read from a GitLab repo, or asks to open/update/comment on merge requests.
Inspect and operate Grafana instances bound to an Nuphos team. All HTTP calls go through Nuphos backend's authenticated proxy — no SA token handling, no CORS, no extra setup. Covers dashboards, folders, datasources, queries (/api/ds/query), alerting, and Loki/Prometheus log + metric pulls.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
Run HOL Guard scanner and guard operations via uv run hol-guard. Use when the user asks to scan plugins/MCP/skills for security, quality, or ecosystem compliance, or when they ask to run guard detect/install/protect workflows for local AI harnesses.
Splits uniform sprite sheet grids into individual frame PNGs using FFmpeg crop. Use when the user wants to split sprite sheets, extract animation frames, divide grid images into cells, cut 4x4 or NxM sheets, slice tilesets, or prepare frames for background removal.
Converts one or more images into faithful text descriptions or OCR with the local 1.3B MiniCPM-V 4.6 GGUF model through llama.cpp, automatically preferring an available Vulkan GPU and falling back to CPU. Use when the user asks to describe, caption, compare, transcribe, inspect, or extract visible details and text from PNG, JPEG, WebP, GIF, BMP, or TIFF images without a GPU or remote vision API.
Set up new Lobu agents end to end and operate existing Lobu projects and memory: interview, scaffold, validate, authenticate, connect feeds, execute operations, and test Automations.
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura tool is present, whenever the user refers to past work ("what did we decide", "last time", "earlier"), or whenever any durable fact needs to be stored, recalled, superseded, or shared with the fleet. Do not use it for throwaway within-session scratch state.
Audits all memory systems in a Perseus environment, identifies stale or superseded stores (Mem0, Mempalace, old vector DBs, garbled federation artifacts), and deletes them. Keeps Perseus Mneme (the live system) as the single source of truth. Run periodically or when upgrading Perseus versions.
Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.
Use this skill when the user is building a fundraising / investor pitch deck — seed, Series A / B / C, convertible note, SAFE round, strategic raise. Trigger on: 'pitch deck', 'investor deck', 'Series A deck', 'Series B deck', 'Series C deck', 'fundraising deck', 'seed pitch', 'VC deck', 'raising capital', 'term sheet presentation'. Output is a single .pptx. This skill is a scene layer on top of officecli-pptx — inherits every pptx v2 rule (visual floor, grid, palettes, connector canon, Delivery Gate). DO NOT invoke for a generic board review, sales deck, all-hands, or product launch — route those to officecli-pptx base.