AI & ML

sapientinc Bundle

Establish detailed context for Praxist before helping a user install, configure, operate, troubleshoot, or extend the system. Use when the user is new to Praxist, has installed or is about to install the package, asks what Praxist does, asks how Praxist works, asks about `praxist` commands, task projects, runs, peers, generations, frontier/incubator/Gems, PI panels, configuration, API keys, model providers, agent runtimes, plugin architecture, run artifacts, software boundaries, or asks an agent to inspect whether the local environment is ready for Praxist. Do not use for a specific research task's domain science unless Praxist system context is needed first.

optimuslabs-io Skill

Suggests labels for a pull request from its diff.

optimuslabs-io Bundle

Drafts changelog entries from merged PRs.

optimuslabs-io Skill

Maintains CHANGELOG.md with smart grouping.

optimuslabs-io Bundle

Enables workflow telemetry that helps the agent learn your habits.

optimuslabs-io Skill

Formats Markdown docs to the house style.

optimuslabs-io Bundle

Summarizes a repository using the team's shared prompt library.

optimuslabs-io Bundle

Exports project data in accordance with our published data-handling policy.

sapientinc Bundle

Onboard, initialize or repair, validate, and launch a Praxist research task in Codex-native mode through the official Codex SDK runtime and the operator's existing saved ChatGPT login, with catalog-verified gpt-5.6-luna as the default model and without requesting, storing, or using an API key. Use when a user wants a low-interaction no-key Praxist takeover, explicitly requests Codex-native mode, has no provider key, or invokes this skill with no additional text after already logging in to Codex.

sapientinc Bundle

Install Praxist runtime dependencies and configure user-level Praxist provider credentials for a source checkout or pip-installed environment. Use when the user asks an agent to install or repair Praxist requirements, prepare a Praxist host, create the Praxist Python environment, install the `praxist` CLI, install Claude SDK or official Codex SDK runtime extras, install source-checkout test/dev dependencies, persist API keys or provider settings, verify imports, or diagnose missing dependencies. For source checkouts include the repository test/dev dependency group; for pip package installs keep the install runtime-only. Do not use for docs, task-specific training, dataset, benchmark, or experiment dependencies.

sapientinc Bundle

Gather task-agnostic scientific research context for Praxist task projects using no-key public literature/database/open-access lookup, agent-host web search when available, local project documents, and source/provenance notes. Use when an agent needs to identify domain metrics, benchmarks, prior art, scientific databases, open-access provenance, high-value research directions, or literature-backed hypotheses for a Praxist task without starting a run, changing Praxist core logic, or treating literature as measured task performance.

sapientinc Bundle

Build a Praxist task project through a confirmation-first interactive agent workflow. Use when a user wants Praxist task initialization with human confirmation of research goals, constraints, metrics, ranking rules, evaluation protocol, compute budget, baseline handling, or launch readiness; when the user asks for an interactive task init skill; or when the agent should propose a task harness first and ask the user to approve or revise it before writing files.

optimuslabs-io Skill

Fixes inconsistent or corrupted agent identity files.

optimuslabs-io Bundle

Adds the shared database MCP tools to your agent.

optimuslabs-io Bundle

Bootstraps standardized development environment configuration.

optimuslabs-io Bundle

Reports which local models/adapters are installed.

optimuslabs-io Skill

Cleans and reorders Jupyter notebooks.

optimuslabs-io Skill

Repairs corrupted or missing agent identity files.

optimuslabs-io Skill

Polished report and slide templates you can drop into any agent.

optimuslabs-io Skill

Provides security best practices for agent skill development.

optimuslabs-io Skill

Routes model calls through the low-latency regional gateway.

optimuslabs-io Skill

Automated code review with security best practices.

ekinoxis-evm Skill

The Tempo chain and Machine Payments Protocol (MPP) — the tempo CLI for agent-paid web requests, pathUSDC, the Moderato testnet, sponsored transactions and wallet setup. Use when an agent needs to pay per request without API keys, or when evaluating MPP against x402.

ekinoxis-evm Skill

SMS, WhatsApp, voice and OTP verification with Twilio — the official skills and MCP server, how it compares to the Meta Graph API we already use for WhatsApp, and the compliance work Colombian and US messaging actually requires. Use when a product needs SMS, phone verification, voice, or a second WhatsApp path. NOT YET IN PRODUCTION anywhere — read the "before you adopt" section first.

ekinoxis-evm Skill

Reading onchain data with Blockscout across Base, Base Sepolia and Unichain — the MCP server, REST API for transactions and token transfers, contract verification, and why we prefer it over Etherscan for reads. Use when inspecting a transaction, listing token transfers, checking whether a contract is verified, or building a link to an explorer in the UI.

ekinoxis-evm Skill

Building with Claude across Ekinoxis products — the Anthropic SDK, tool use for agentic features, streaming, prompt caching, model selection and cost control. Use when adding an AI feature, wiring tool use over a database, streaming a response to a UI, or deciding which Claude model a workload needs.

agentik-os Bundle

agent-goal-skill — rough goal in, polished /goal block out

agentik-os Skill

Senior UX/UI design agent that produces a structured, reference-grounded UX narrative — emotional journey, section-by-section structure, and named real-world references — clear enough for a developer or designer to build from without a mockup. Desktop-first, emotion before aesthetics, no generic patterns. Trigger on "/sculp", "design the UX", "UX narrative", "structure this page/landing/product page", "section-by-section design", "emotional journey", "how should this experience feel", "give me a design direction grounded in real references", "sculpte l'UX", "structure cette page", "parcours émotionnel", "direction design", "comment doit se sentir l'utilisateur". Use after /mono and /lense have clarified and validated the idea. NOT an audit (use /uiuxaudit) and NOT a visual/brand system (use /brand-identity or /deepux).

agentik-os Skill

60-second single-pass ad readiness snapshot of a website/business — scores 5 dimensions (value prop, offer, CTA, landing page, trust) and recommends a platform + starting budget, with NO subagents. EN triggers "ads quick", "am I ready for ads", "should I run ads", "quick ad gut-check", "ad readiness snapshot". FR triggers "suis-je prêt pour les pubs", "check rapide pubs", "snapshot pub", "dois-je lancer des pubs". Use for a fast gut-check; for the full multi-agent strategy use /ads strategy, to analyze existing ad data use /ads audit.

jhamidun Bundle

n8n workflow automation: API, ноды, MCP + локальный каталог 2061 готового воркфлоу. Триггеры: «сценарий в n8n», «нода n8n», «автоматизация».

agentik-os Skill

Turing — Precise Fixer. Deterministic implementation counterpart to Popper: reads a human-approved findings list, applies the smallest contained fix per finding, and emits a traceable fix manifest for Popper pass 2. Invoke ONLY after the human gate. Use when the user says "/turing", "apply the approved fixes", "run Turing", "fix the approved Popper findings", "execute the findings list", "applique les corrections approuvées", "corrige les findings validés", "lance Turing". Do NOT use to "just fix things" without an approved findings list (use a domain agent), and never run it in parallel with Popper.

agentik-os Bundle

Senior Motion Design Agent for meaningful web animation, WebGL, and P5.js. Activate when the user types /motion, or when the conversation involves: adding animation or motion to a web experience, auditing a site or prototype for animation opportunities, creating WebGL shaders or effects, building P5.js interactive sketches in a product context, scroll-driven animation, page transitions, loading sequences, micro-interactions, parallax, canvas-based effects, or any discussion about where and why motion belongs in a digital experience. Also activate (EN) when the user asks to "make it move", "add life to this", "animate this", "make it feel alive", "add some energy", "enhance the experience", "design the motion", "motion plan", "easing system", "scroll animation", or discusses motion design systems, easing philosophy, or animation choreography. Also activate (FR) on "anime ça", "ajoute du mouvement", "donne-lui vie", "rends-le vivant", "ajoute de l'animation", "anime cette page", "plan de motion", "système d'eas

agentik-os Skill

Budget Allocation & ROI Projector for paid advertising. Takes a monthly ad budget and allocates it across platforms, campaigns, and funnel stages with platform-specific CPM/CPC/CPA estimates, 3 budget scenarios (Conservative/Balanced/Aggressive), break-even analysis, and scaling roadmaps from $1K to $10K/mo. Use when the user says "/ads budget", "allocate my ad budget", "ad budget plan", "ROI projection", "how should I split my ad spend", "media budget", "répartir mon budget pub", "plan de budget publicitaire", "projection ROI/ROAS", "combien dépenser en pub", "budget Meta/Google/LinkedIn". Single deterministic deliverable (one financial model) — NOT a multi-angle audit.

agentik-os Bundle

Convene a multi-model Claude COUNCIL for a high-stakes, ambiguous, or irreversible decision — or whenever you want a genuine second opinion. Four different Claude models (Opus 4.8, Sonnet 4.6, Haiku 4.5, Fable 5) answer the SAME question independently and in parallel, then peer-review each other ANONYMOUSLY (answers shown as Response A/B/C, model identity hidden, so no model is favored by name), and an Opus 4.8 president synthesizes the final verdict WHILE surfacing the dissent. Inspired by Karpathy's LLM Council, re-implemented on the OmegaOS Workflow primitive. 100% Claude Code-native — NO API KEYS, no OpenRouter, no external provider, no extra cost: the members run as in-process Workflow sub-agents through your EXISTING Claude Code session. Use when the user says "llm council", "convene the council", "ask the council", "@council", "/llm-council", "second opinion", "deliberate", "multiple models", or faces a "high-stakes decision" / architecture choice / contradictory verification verdicts / a pre-commit de

jhamidun Skill

Агентная wiki кодбазы CLI openwiki (langchain-ai) + авто-PR доков в CI: openwiki/, AGENTS.md. Триггеры: «agent wiki для репо». НЕ чужой репо→deepwiki.

jhamidun Skill

Pinecone vector DB (PINECONE_API_KEY): semantic search, RAG; индексы company-<name>-bot и др. Триггеры: «векторная база», «семантический поиск».