Guide to selecting and optimizing embedding models for vector search applications. — from majiayu000/claude-skill-registry
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embeddi — from…
[STUB - Not implemented] Asymmetric embedding strategy with RETRIEVAL_DOCUMENT for ingestion and RETRIEVAL_QUERY for queries.
Use when after instantiating and invoking a sinusoidal formula embedding layer (such as SCARF embeddings in MIST-CF) on chemical formula inputs, validate that the output…
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration.
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration.
Uses the Pluribus skill-policy receipt recipe to make hard agent-skill rules auditable before and after writes.
英語の技術ドキュメント (Hugging Face docs / GitHub README / arXiv 論文 / 技術ブログ等) を、日本人が読んで AI 生成と気づかない自然な日本語の解説サイトに変換します。フェッチ → 構成 → HTML/CSS/JS 生成 → 多角レビュー → 修正 → ローカル配信、まで一気通貫。日本語自然さチェックは…
Use when setting up Endor Labs Agent Kit for Cursor, checking readiness, verifying Endor auth, choosing namespaces, or diagnosing missing endorctl, gh, Endor MCP, or workflow…
Orchestrates EnergyCenter Cursor prompt pipelines for feature implementation, PR review, bug fixing, quality gates, and workflow task files.
Drop a multi-agent protocol pack into a project so coding assistants must satisfy reviewer, memory, and supply-chain gates before code-changing work completes.
Run Claude, Codex, and related coding-agent tasks through policy gates, evidence loops, and auditable execution tiers before risky work proceeds.
Design an agent's working context, durable memory, retrieval, compaction, and handoff behavior. Use when context quality, freshness, privacy, or token cost affects task…
Install cc10x as a Claude Code loop engine that routes complex work through specialist agents, reusable skills, durable workflow artifacts, and fail-closed review gates.
Improve broken prompts and context plans by choosing the smallest prompt-engineering technique that fits.
Guide for creating agent-invocable Agent Skills (SKILL.md packages auto-discovered by description). Use when users want to create or author a skill, or ask about skill structure…
Draftet oder prüft englischsprachige Verträge mit deutschem Recht als anwendbarem Recht. Verhindert ungewollten Import von Common-Law-Konzepten, klärt governing language,…
Use when improving agent prompts, frontmatter, and tool restrictions.
Scan Linear for agent-ready issues in the Ensemble project, pick the highest priority one, implement it following TDD, verify with frontend and backend tests/lint, and create a…
Real-time COGS metering (calculating exact $ cost per voice minute, SMS unit, LLM token, and per-tenant margin analytics) for multi-tenant AI SaaS platforms.
Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities in Microsoft 365 and Azure…
Guide agent to send a user-specified local PDF document for signature through eSignGlobal by calling the eSignGlobal CLI tool.eSignGlobal CLI is an agent-friendly CLI — all output…
Design and generate .envelope.json AI agent team definitions — the open standard for multi-agent teams with hierarchy, access policies, human-in-the-loop gates, and cron — from…
Design and generate .envelope.json AI agent team definitions — the open standard for multi-agent teams with hierarchy, access policies, human-in-the-loop gates, and cron — from…
Epic-level multi-agent ekip orkestrasyonu — vertical slice + dependency graph + critical path + parallel agent assignment + cross-team blocker mediation + weekly burndown.
当用户搜索 Epiko CineAI替代、多Agent导演、Series Mode、角色LoRA、连续剧、OiiOii同类平台、AI视频Agent、创意Agent平台、AI-HIVE MCP 时使用。为 Epiko CineAI…
Prüft Grundstück, Bauwerk, Laufzeit, Nutzung, Erbbauzins, Heimfall, Zustimmung, Versicherung, Instandhaltung und Entschädigung im Erbbaurecht Praxis.
Notare: erbvertrag testament belehrung - Kaltstart mit Faktenmatrix, Risikoampel und fehlenden Unterlagen; mit Live-Normencheck, Kammerlogik, Verhältnismäßigkeit, Belegplan und…
Notare: erbvertrag testament belehrung - Kammerantwort mit Verfahrensstrategie, Tonlage und Belegplan; mit Live-Normencheck, Kammerlogik, Verhältnismäßigkeit, Belegplan und…
Notare: erbvertrag testament belehrung - Organisationspflichten, Prävention, Team-Anweisung und Fristenkontrolle; mit Live-Normencheck, Kammerlogik, Verhältnismäßigkeit, Belegplan…
Sign and verify HTTP requests with Ethereum wallets using ERC-8128. Use when building authenticated APIs that need wallet-based auth, making signed requests to ERC-8128 endpoints,…
Erlaubnisantrag § 32 KWG Unterlagen Geschäftsleiter: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen. Norm-/Quellenanker: KWG § 1 Abs.
Erlaubnisantrag § 32 KWG Unterlagen Geschäftsleiter: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen. Norm-/Quellenanker: KWG § 1 Abs.
ERNE — Run a full multi-agent pipeline from plan to validation using the pipeline-orchestrator agent
Prüfung des Eröffnungsantrags Paragrafen 13-15 InsO, Zulässigkeit, Insolvenzgrund (Paragrafen 17-19 InsO), Verfahrenskostendeckung, Anhörung des Schuldners
Systematically identify and categorize failure modes in evaluated traces using Truesight datasets and error-analysis tools.
Expert error coordinator specializing in distributed error handling, failure recovery, and system resilience.
Expert in making multi-agent systems resilient. Specializes in detecting loops, hallucinations, and failures, and implementing self-healing workflows.
Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications.
Configure with error mapping helper operations. Auto-activating skill for API Integration. Triggers on: error mapping helper, error mapping helper Part of the API Integra — from…
Trace error propagation through a multi-agent session by agent depth — where failures originated, the depth at which they appeared, and how they cascaded up to parent agents —…
Foerderantragssteller: Tatbestandsmerkmale, Beweisfragen und Beleglage im DFG-Förderantragstellung: 1. Welche Rolle hat die fragende Person und wer ist Gegenüber? 2.
Structured escalation with evidence. Surfaces blocking issues for human decision, referencing the Manifest hierarchy.
Build trustless escrow for agent-to-agent transactions on Solana and Base. Use when an AI agent needs to pay another agent, hold funds until work is verified, or resolve payment…
Sistema multi-agente especializado en inversión ESG y fondos temáticos. ACTÍVALO ante cualquier mención de: ESG, sostenible, inversión responsable, impacto, fondos verdes, energía…
Manage etag handler operations. Auto-activating skill for API Development. Triggers on: etag handler, etag handler Part of the API Development skill category.
\"Evaluate prompt effectiveness using metrics and test cases inspired by DSPy and OPRO. 以 DSPy/OPRO 啟發之指標與測試案例評估提示效果。 Use when: measuring prompt quality before/after changes,…
Run evaluation tests against a multi-agent workflow to assess orchestration quality and failure archetype resistance
Run repeatable EvalScope benchmark suites for LLM, VLM, RAG, and agent workflows, then inspect traces and reports before changing models or prompts.
Use ParseBench to run repeatable document-parser evaluations before an agent relies on PDF, table, chart, or enterprise-document output for downstream decisions.
Operate the "Documents" app of an everjust.app Odoo 19 tenant (browse/create/move folders and files, upload, download, tag, migrate storage, point Documents at the tenant's…
Evidence is an open-source framework for building data products with SQL and Markdown. It generates interactive dashboards and reports as static sites, providing a code-driven…
Open the evo-agent-team dashboard in your default web browser. Detects the OS and uses the appropriate open command.
Turn recurring agent lessons, logs, and strategy tweaks into reviewable GEP evolution artifacts that can be applied across supported coding-agent runtimes.
Mine failed agent runs for reusable skills, benchmark the candidates, and keep only the variants that improve a supported coding agent over your baseline.
Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms.
Für EV-Vollzug 005: Ordnungsmittelantrag (Paragraf 890 ZPO) nach Unterlassungstitel: erstellt Entwurf mit Antrag, Beweis und Anlagen; Ergebnis: Schriftsatz mit Begründungs- und…
EV-Vollzug: Ordnungsmittelantrag nach § 890 ZPO bei Verstoß gegen Unterlassungstitel aus einstweiliger Verfügung.
Analyze budget vs actual variances in Excel with drill-down and root cause analysis. Use when performing variance analysis or explaining budget differences.
Perform comprehensive, deep analysis of a system and its subsystems to identify bugs, race conditions, stale documentation, dead code, and correctness issues.