Results for “meta-llama”

Store and query embeddings with metadata filtering, vector search, and full-text search using an open-source database that scales from notebooks to production.

Meta-skill — defines when to apply other skills automatically without being asked

Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.

Use when an agent needs to send one private MetaWeb message to a remote Bot/MetaBot globalMetaId, or when a human wants to find any online Bot/MetaBot/agent/AI for casual chat without choosing a target or writing the first message. Treat Bot, bot, and MetaBot wording as equivalent and case-insensitive; treat agent and AI wording the same way when the intent is private or casual chat. Do not use this skill for paid service delegation, trace lifecycle handling, or network source management.

Llama 3: The Llama 3 Herd of Models

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Use when the user wants to automate SEO tasks using Gemini CLI — meta titles, meta descriptions, alt text, schema markup, keyword research, or bulk page optimization. Trigger phrases: Gemini CLI SEO, bulk meta tags via CLI, automate SEO with Gemini, generate schema with Gemini CLI. For AI-powered SEO strategy see ai-seo.

Use when an agent needs to publish one simplebuzz post to MetaWeb (optionally with uploaded attachments); do not use this skill for private chat, service-order delegation, or network source management.

Use when a human or agent needs local Bot/MetaBot identity create/list/assign/who workflows, persona setup or updates, including first-time bootstrap creation plus doctor verification. Treat user wording such as Bot, bot, and MetaBot as equivalent and case-insensitive for this skill; do not use this skill for remote service calls, network source management, or generic chain content publishing.

Use when a user asks to use, run, delegate, or fulfill a task through a capability that may exist as an online Bot/MetaBot skill-service, especially when no local specialized skill matches. Treat Bot, bot, and MetaBot wording as equivalent and case-insensitive for remote service requests; select from the local cached online service list first, then call the remote service and continue through trace get/watch, optional conversation view opening, and rating closure. Do not use for browse-only service discovery, network source registry management, identity creation/switching, or private chat-only requests.

Documents Meta's design system for commerce surfaces, including color tokens, typography hierarchy, spacing, and responsive patterns for hardware merchandising.

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Use when a human asks what OAC, Open Agent Connect, MetaBot, metabot, Bot, or bot can do; asks for available features, abilities, functions, usage examples, or a capability map; or needs an explanation of what the user can accomplish through OAC/MetaBot/Bot after installation. This skill dynamically summarizes installed metabot-* skills and metabot CLI help instead of relying on a static feature list.

Creates or updates Salesforce metadata components at runtime from Apex using the Metadata namespace, including custom fields, objects, picklist values, and labels, with asynchronous deployment and callback handling.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Resolves legacy references to the cyber-intel capability by routing to the current runtime agent or skill.

multi-llm-review

Use when a local Bot/MetaBot should publish/register one paid MetaWeb service, choose a provider MetaBot and publishable skill, gather service fields conversationally, or list/modify/revoke/manage one of its discoverable services. Treat Bot, bot, and MetaBot wording as equivalent and case-insensitive for provider identity; do not use this skill for service consumption (services call), buyer trace follow-up, or network source registry management.

Use when an agent needs to design or build Agent Internet MetaApps, convert a local static HTML site, frontend project, or ZIP into an on-chain MetaApp, create Bot homepage/Bot Page MetaApps from Bot Homepage v3 data, or preview, publish, update, share, view, delete, or comment on MetaApps through Open Agent Connect.

Metasuperhypergraph orchestrator with fractal scale-invariant recursion. Activates maximum performance mode through renormalization-group optimization, power-law resource allocation, and homoiconic self-improvement. Triggers on "ultrawork", complex multi-domain tasks, or when parallelization/delegation yields superlinear returns.

---

Runs a 13-agent deep research pipeline for rigorous academic work on any topic across 7 modes (full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis), covering research-question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk-of-bias assessment, meta-analysis, APA 7.0 report compilation, editorial and devil's-advocate review, ethics review, and post-research literature monitoring. Use when the request mentions research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, or 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題. Part of the AlterLab Academic Skills suite.

Extracts selected metadata from a DICOM file and flags standard-tag PHI presence. Not for anonymization or clinical use.

Silently restructures natural-language prompts into the format best suited for the model currently executing the skill, then answers the rewritten version.

Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.

Applies medicinal-chemistry filters with the medchem library — drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, and molecular complexity metrics for compound prioritization and library cleanup. Use when filtering or triaging a compound library, flagging PAINS or reactive groups, or assessing drug-likeness of candidate molecules. Part of the AlterLab Academic Skills suite.

The AlterLab front door and multi-agent launcher — routes a task to the right AlterLab skill(s) when the user invokes the suite without naming one, and for a multi-stage goal (or on the keyword 'alterflow', aliases 'alterresearch' / 'ultralab') it CLARIFIES the goal with a few questions, SELECTS the skills the task needs, and runs a dynamic multi-agent workflow composing them (via alterlab-workflow-orchestration, alterlab-research-pipeline, or alterlab-ssci-orchestrator). Triggers on 'use AlterLab skills', 'which AlterLab skill for X', 'is there an AlterLab skill for…', a multi-stage research goal, 'alterflow …', or any generic AlterLab request where the user does not know skill names. It always asks clarifying questions before executing a multi-step run. Use when someone references AlterLab generically, describes a multi-stage goal, or fires the alterflow keyword; when the user already names a specific skill, defer to that skill directly. Part of the AlterLab Academic Skills suite.

Use when an agent needs read-only MetaWeb data access (local Bot/MetaBot identity state, service, trace, or chain reads) and should prefer public metabot interfaces. Treat Bot, bot, and MetaBot wording as equivalent and case-insensitive for read-only identity/service queries; do not use this skill for writes like buzz post, service publish, file upload, or remote order submission; do not use this skill to look up, view, or open other users or Bots by name, personality, skill, or profile — people search, Bot pages, and identity profiles belong to metabot-browser, even when the request is phrased as a read-only "show me someone's info" query.

Use OpenMetadata UI for data discovery, governance, and collaboration. Use when searching for data assets, managing descriptions and ownership, creating glossary terms, setting up data contracts, or tracking data insights and KPIs.

Searches and loads runnable skill guidance from two skill corpora via MCP or CLI, with admin commands for feedback, outcomes, and reindexing.