agentsclimarketplace

Context & AI engineering

25,815 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • CLIO Paraview

    iowarp/clio-kit/io.github.iowarp/paraview-mcp MCP server

    32★ repo

    MCP server for ParaView scientific visualization

  • CLIO Plot

    iowarp/clio-kit/io.github.iowarp/plot-mcp MCP server

    32★ repo

    MCP server for advanced data visualization and plotting operations

  • CLIO Sac

    iowarp/clio-kit/io.github.iowarp/sac-mcp MCP server

    32★ repo

    MCP server for analyzing SAC seismic-waveform files and TAR archives: inspect members, compute...

  • CLIO Parquet

    iowarp/clio-kit/io.github.iowarp/parquet-mcp MCP server

    32★ repo

    MCP server for Apache Parquet files

  • CLIO Slurm

    iowarp/clio-kit/io.github.iowarp/slurm-mcp MCP server

    32★ repo

    MCP server for Slurm workload management and HPC job scheduling

  • CLIO Terrain

    iowarp/clio-kit/io.github.iowarp/terrain-mcp MCP server

    32★ repo

    MCP server for terrain analysis: DEM slope/aspect/suitability and point-cloud reading/gridding

  • CLIO Seismic

    iowarp/clio-kit/io.github.iowarp/seismic-mcp MCP server

    32★ repo

    MCP server for earthquake-sequence analysis on saved catalogs: completeness magnitude,...

  • Claude seo

    georgekhananaev/claude-skills-vault/.claude/skills/claude-seo Skill

    31★ repo

    SEO toolkit with 24 specialist sub-skills (upstream v2.0) — full site audits, technical SEO, content optimization & briefs, schema markup, sitemaps, image SEO, hreflang, local/maps SEO, backlinks, topic clustering, SERP experience (SXO), drift monitoring, Google APIs (GSC/PageSpeed/CrUX), e-commerce, programmatic SEO, and GEO for AI Overviews/ChatGPT/Perplexity. Use when auditing websites, optimizing pages or content, tracking SEO regressions, or planning SEO strategy.

  • Seo dataforseo

    georgekhananaev/claude-skills-vault/.claude/skills/claude-seo/skills/seo-dataforseo Skill

    31★ repo

    Live SEO data via DataForSEO MCP server. SERP analysis (Google, Bing, Yahoo, YouTube, Google Images), keyword research (volume, difficulty, intent, trends), backlink profiles, on-page analysis (Lighthouse, content parsing), competitor analysis, content analysis, business listings, AI visibility (ChatGPT scraper, LLM mention tracking), and domain analytics. Requires DataForSEO extension installed. Use when user says "dataforseo", "live SERP", "keyword volume", "backlink data", "competitor data", "AI visibility check", "LLM mentions", "image SERP", "google images", "image rankings", or "real search data".

  • Codex cli

    georgekhananaev/claude-skills-vault/.claude/skills/codex-cli Skill

    31★ repo

    Run OpenAI Codex CLI for coding tasks, implementation, reviews, and second-opinion audits with mandatory task-based routing across GPT-5.6-or-newer models. Use when a user asks to run, ask, or use Codex; says "codex prompt"; wants a Codex code/logic/plan audit; or wants Claude to delegate work to OpenAI models. Inspect the live Codex model catalog, explicitly pin an eligible model and reasoning effort on every invocation, route clear high-volume work to Luna, everyday work to Terra, and difficult or high-value work to Sol. Use Sol with max reasoning for plan audits. Never invoke or fall back to GPT-5.5, GPT-5.4, GPT-5.3-Codex-Spark, OSS, or any model older than GPT-5.6.

  • Firebase cli

    georgekhananaev/claude-skills-vault/.claude/skills/firebase-cli Skill

    31★ repo

    Safety-first Firebase CLI (firebase-tools v15) skill for full project control — deploy, Hosting (sites/channels/rollback), Cloud Functions (+secrets), Firestore (databases/indexes/backups/delete), Realtime Database, Auth import/export, Remote Config, App Distribution, App Hosting, Extensions, Data Connect, Emulator Suite & MCP server. Classifies every command by risk tier via a deterministic classifier script and gates destructive/irreversible/cost-incurring ops behind AskUserQuestion confirmation; enforces the --non-interactive/--force contract so nothing hangs and nothing is auto-confirmed. Wrong-project preflight prevents deploying to prod by accident. Ships a 3-level self-test (static classifier battery, live read-only, guarded live-write w/ cleanup). Use when running, planning, or debugging any `firebase` command.

  • Mcp builder

    georgekhananaev/claude-skills-vault/.claude/skills/mcp-builder Skill

    31★ repo

    Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

  • Monday com

    georgekhananaev/claude-skills-vault/.claude/skills/monday-com Skill

    31★ repo

    Monday.com workspace management via official MCP server. This skill should be used when creating, updating, moving, archiving, or deleting items/boards/groups on Monday.com, managing columns, adding comments, or querying workspace data. Supports both hosted and local MCP deployment with interactive setup guidance.

  • Multi agent patterns

    georgekhananaev/claude-skills-vault/.claude/skills/multi-agent-patterns Skill

    31★ repo

    Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures

  • Neon postgres agent platforms

    georgekhananaev/claude-skills-vault/.claude/skills/neon-postgres-agent-platforms Skill

    31★ repo

    Build and operate multi-tenant AI agent platforms on Neon. Use this skill whenever the user is designing an agent/app builder, provisioning a Neon project or database per user/app/agent run, managing thousands of tenant projects, separating sponsored free users from paid customers, moving projects between orgs, choosing personal vs organization vs project-scoped API keys, tracking fleet consumption or Agent Plan costs, creating compound checkpoints that combine DB snapshots with source revisions/secrets/deploy metadata, or orchestrating snapshot/restore flows for generated apps. Also use it for Neon Agent Program, Agent Plan, org/project limits, HIPAA, co-marketing, support, or neondatabase/neon-for-agent-platforms examples.

  • Parallel agents

    georgekhananaev/claude-skills-vault/.claude/skills/parallel-agents Skill

    31★ repo

    Multi-agent orchestration patterns. Use when multiple independent tasks can run w/ different domain expertise or when comprehensive analysis requires multiple perspectives.

  • Skill creator

    georgekhananaev/claude-skills-vault/.claude/skills/skill-creator Skill

    31★ repo

    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

    The same file is in 1 other repository

  • Humanizer

    Borda/AI-Rig/plugins/cc_foundry/skills/humanizer Skill

    31★ repo

    A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

  • Manage

    Borda/AI-Rig/plugins/cc_foundry/skills/manage Skill

    31★ repo

    A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

  • Profile

    Borda/AI-Rig/plugins/cc_foundry/skills/profile Skill

    31★ repo

    A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

  • Agent shims

    Borda/AI-Rig/plugins/codex-rig/skills/agent-shims Skill

    31★ repo

    A collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.

  • Swmm end to end

    Zhonghao1995/agentic-swmm-workflow/skills/swmm-end-to-end Skill

    31★ repo

    Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex, Hermes, Claude code as well as OpenClaw compatibility

  • Swmm experiment audit

    Zhonghao1995/agentic-swmm-workflow/skills/swmm-experiment-audit Skill

    31★ repo

    Consolidate Agentic SWMM run artifacts into auditable provenance, comparison records, and local Obsidian audit notes. Use after any SWMM build/run/QA attempt, successful or failed, when an agent or CLI workflow needs a traceable record of inputs, commands, artifacts, metrics, QA checks, run-to-run differences, and first-user-friendly Obsidian visualization.

  • Swmm modeling memory

    Zhonghao1995/agentic-swmm-workflow/skills/swmm-modeling-memory Skill

    31★ repo

    Read historical Agentic SWMM experiment audit artifacts and summarize repeated assumptions, QA issues, failures, missing evidence, run-to-run differences, lessons learned, and controlled skill update proposals. Use downstream of swmm-experiment-audit when multiple audited runs exist or when a user asks for modeling memory, failure-pattern extraction, lessons learned, or human-reviewed skill refinement proposals.

  • Swmm rag memory

    Zhonghao1995/agentic-swmm-workflow/skills/swmm-rag-memory Skill

    31★ repo

    Retrieve relevant Agentic SWMM modeling memory from audited runs, modeling-memory summaries, and Obsidian-compatible notes at query time. Use when a user asks for RAG, similar past runs, evidence-linked memory retrieval, historical QA/failure patterns, or memory-grounded answers.

  • Auto research

    maystudios/claude-skills/auto-research Skill

    31★ repo

    Improve any existing Claude Code skill, CLAUDE.md, subagent definition, slash-command, or prompt markdown file by combining web-researched best-practice rewrites with autonomous Karpathy-style binary eval loops. Use when the user wants to "auto-research", "self-improve", "auto-improve", "optimize", "modernize", or "research-improve" any existing SKILL.md, CLAUDE.md, agent file under .claude/agents/, slash-command file under .claude/commands/, or any prompt markdown file. Triggers on phrases like "use auto-research to improve skill X", "auto-improve this CLAUDE.md", "research best practices and rewrite Y", or "self-research and optimize this agent". Researches authoritative sources (Anthropic docs, anthropic.com engineering blog, anthropics/skills GitHub) in parallel sub-agents, proposes a cited rewrite, runs an autonomous binary-assertion eval loop with git commit and reset bookkeeping for testable artifacts, and asks the user to confirm only at the end with a before-and-after score and full source list.

  • Google ai studio tts

    maystudios/claude-skills/google-ai-studio-tts Skill

    31★ repo

    Generate speech, podcasts, voiceovers, and multi-speaker dialogue with Google AI Studio's Gemini Flash TTS by driving the live web app in Chrome via the claude-in-chrome MCP server. Use whenever the user asks to (1) create a podcast, audiobook chapter, narration, audio drama, or voiceover with Gemini / Google AI Studio TTS; (2) turn a script into multi-speaker audio (e.g. "two-host podcast", "Speaker 1 / Speaker 2 dialogue", "Puck and Zephyr"); (3) tweak a TTS prompt with Scene, Sample Context, Director's note (Style/Pace/Accent), Audio Profile, voice picker, or Temperature; or (4) render audio with inline tags like [enthusiastic], [whispers], [laughs]. Triggers on phrases like "use AI Studio TTS", "generate this podcast in AI Studio", "render with gemini-3.1-flash-tts-preview", "speak this with Aoede/Puck/Zephyr", or any request for browser-driven Gemini speech generation.

  • Opencode

    maystudios/claude-skills/opencode Skill

    31★ repo

    Invoke OpenCode CLI as a sub-agent to leverage alternative AI models (GPT-5.x, Codex, local models) for code implementation, review, debugging, research, and second opinions. Use when the user asks to "use opencode", "get a second opinion from GPT/Codex", "implement with opencode", "review with opencode", "let opencode handle this", "use a different model", or wants cross-model validation. Also triggers when the user explicitly names an OpenCode model (e.g., "use gpt-5.4", "use codex") or wants to delegate a task to a non-Claude AI system. Supports all providers configured in the user's OpenCode installation (OpenAI, GitHub Copilot, local models via Ollama/LM Studio, and OpenCode's own free-tier models).

  • Seedance

    maystudios/claude-skills/seedance Skill

    31★ repo

    Expert guide for prompting ByteDance's Seedance 2.0 AI video model (text-to-video, image-to-video, first/last-frame, multi-reference, and multi-shot generation with native synchronized audio). Use when the user wants to write, improve, or debug a Seedance 2.0 prompt; plan a shot; work with reference images/videos/audio; animate a start frame or interpolate first-and-last frames; direct camera moves, motion, and cinematic style; generate dialogue, sound effects, or music; keep a character consistent across shots; or understand Seedance 2.0's capabilities, specs, API model IDs, limits, and access routes (Dreamina, Volcano Ark, BytePlus, fal.ai, Replicate). Triggers on "Seedance", "Seedance 2.0", "ByteDance video model", "Dreamina video", "seedance prompt", "reference-to-video", "first and last frame video".

  • Aios prompt compare

    ArchSightLabs/archsight-aios/skills/aios-prompt-compare Skill

    31★ repo

    内部 Prompt 测试工具。仅供开发者明确调用,用于 weak/basic/runtime 三栏评测、prompt 回归、Skill 沉淀价值判断和 AIOS 技能包验收。

  • Aios runtime

    ArchSightLabs/archsight-aios/skills/aios-runtime Skill

    31★ repo

    高级 Runtime 和知识管线设计入口。用于设计 Prompt、上下文压缩、Memory 策略、Hermes/OpenClaw 等适配器、Tool Calling、MCP 权限、RAG、GraphRAG、Embedding、评估、多 Agent 编排和状态治理。

  • Skill creator

    waterfeet/DoroPet_V3/opendoro/src/skills/skill-creator Skill

    31★ repo

    Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

  • Security checklists

    eugenelim/agent-ready-repo/.agents/skills/security-checklists Skill

    31★ repo

    Progressive-disclosure security-depth modules for the security-reviewer. Holds boundary-keyed checklists (access-control, authn-session, injection, path-and-file, secrets-and-crypto, outbound-ssrf, supply-chain, config-misconfig, exceptional-conditions, llm-agent, agentic-skills) as references/, each anchored on a current standard (OWASP Top 10:2025, ASVS 5.0, API Security Top 10:2023, Proactive Controls 2024, CWE Top 25, OWASP LLM Top 10:2025, OWASP Top 10 for Agentic Applications:2026, OWASP Agentic Skills Top 10 v1.0 (AST01–AST10)). The work-loop's orchestrator loads only the boundary-matching modules and inlines them into the security-reviewer's brief; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer reasons from.

  • Mcp server headers

    eugenelim/agent-ready-repo/packages/agentbundle/tests/fixtures/creds/skills/mcp-server-headers Skill

    31★ repo

    MCP-server class fixture using header-naming flags (`--bearer-header`); AC26(b) ban is scoped to credentialed-cli only — lint must NOT flag this fixture.

  • Assimilate primitive

    eugenelim/agent-ready-repo/packs/catalogue-curation/.apm/skills/assimilate-primitive Skill

    31★ repo

    Use to bring a single external agent primitive — one skill, subagent, hook, or command (or a small connected bundle) — from a local path or URL into this catalogue. Fetches it, diagnoses the destination pack and lifecycle from the local charter, and migrates it to pack convention, or rejects it with a reason. Triggers on "assimilate this skill from <path/url>", "bring in this agent", "adopt this hook into a pack". Do NOT use to survey a whole repo (use assimilate-repo) or to justify a new pack (use propose-catalogue-pack).

  • Security checklists

    eugenelim/agent-ready-repo/packs/core/.apm/skills/security-checklists Skill

    31★ repo

    Progressive-disclosure security-depth modules for the security-reviewer. Holds boundary-keyed checklists (access-control, authn-session, injection, path-and-file, secrets-and-crypto, outbound-ssrf, supply-chain, config-misconfig, exceptional-conditions, llm-agent, agentic-skills) as references/, each anchored on a current standard (OWASP Top 10:2025, ASVS 5.0, API Security Top 10:2023, Proactive Controls 2024, CWE Top 25, OWASP LLM Top 10:2025, OWASP Top 10 for Agentic Applications:2026, OWASP Agentic Skills Top 10 v1.0 (AST01–AST10)). The work-loop's orchestrator loads only the boundary-matching modules and inlines them into the security-reviewer's brief; the subagent never self-discovers this skill. Not a reviewer prompt itself — it is the depth library the reviewer reasons from.

  • Compare hypotheses

    eugenelim/agent-ready-repo/packs/desk-research/.apm/skills/compare-hypotheses Skill

    31★ repo

    Compare competing hypotheses on a decision-shaped question using an ACH-style evidence matrix (hypotheses × evidence-for/against). Dispatches per-hypothesis parallel retrieval on Claude Code (one `evidence-retriever` subagent per hypothesis — the +81% parallelizable-task case from multi-agent research). In decision-pipeline invocations expects upstream `<topic-slug>-perspectives.md` and `<topic-slug>-sources.md`; standalone invocations enumerate hypotheses inline. Produces `<topic-slug>-hypotheses.md` with the matrix and a most-supported ranking. Depth cues — `quickly`, `top three`, `briefly`, `summary only` for the dominant hypotheses; `comprehensively`, `exhaustively`, `in depth`, `extensive` for fringe ones too.

  • Workspace design

    eugenelim/agent-ready-repo/packs/experience-design/.apm/skills/workspace-design Skill

    31★ repo

    Use when designing a workspace surface — a productivity tool, a collaborative environment, an agentic UI, or any surface whose primary purpose is to support sustained professional work across sessions. Triggers on 'design the workspace', 'structure the tool UI', 'collaborative editing surface', 'agentic UI design', 'multi-agent coordination UI', 'task management surface', 'session arc design'. Covers context-persistence, collaboration state IA, ambient attention, agentic patterns, and interrupt design. Do NOT use for dashboards and monitoring views (use analytical-design) or marketplace surfaces (use marketplace-design). Surface genre: workspace.

  • Cowork vs chat demo

    EAIconsulting/cowork-skills-library/skills/cowork-vs-chat-demo Skill

    no license30★ repo

    See the difference between Chat and Cowork with a live side-by-side comparison for understanding why Cowork is built differently. Use when evaluating AI tools, for comparing chat versus agent capabilities, during an AI tool decision, when switching from ChatGPT or Claude Chat, or when the user says "what is different about cowork", "cowork vs chat", "why not just use chatgpt", "show me the difference", "compare chat and cowork", or "why should I use cowork instead of chat".

    The same file is in 2 other repositories

  • Delegation coach

    EAIconsulting/cowork-skills-library/skills/delegation-coach Skill

    no license30★ repo

    Teaches you how to delegate tasks to Cowork so clearly that you get exactly what you asked for — every time. Use when learning how to give better instructions, for improving your delegation technique, during early Cowork adoption when results feel off, when writing clearer task descriptions, or when the user says "how do I ask cowork to do things", "delegation tips", "better instructions", "cowork isn't doing what I want", "help me delegate", "my results are bad", "how do I give better prompts", "cowork keeps getting it wrong", "I don't know how to use this", or "how do I get good results".

    The same file is in 2 other repositories

  • Memory system

    EAIconsulting/cowork-skills-library/skills/memory-system Skill

    no license30★ repo

    Sets up a file-based memory system so Cowork always knows who you are, how you work, and where your projects stand. For eliminating repetitive re-introductions at session start, when building persistent context across multiple projects, or during initial Cowork onboarding. Use when the user says "claude doesn't remember me", "memory system", "persistent context", "why does it forget", "remember my preferences", "I keep re-explaining myself", or "how do I make Claude remember things".

    The same file is in 2 other repositories

  • Skill creator guide

    EAIconsulting/cowork-skills-library/skills/skill-creator-guide Skill

    no license30★ repo

    Interviews you about a task you repeat often, then walks you through building a custom skill for it using Cowork's built-in skill creator — no coding required. For packaging a repeating workflow into a one-phrase trigger, when teaching Cowork your personal process from scratch, or during a skill library build session. Use when the user says "create a skill", "teach claude my workflow", "custom skill", "make cowork do this automatically", "automate my process", "I do this every week", or "how do I make a skill".

    The same file is in 2 other repositories

  • Skill forge

    bjcoombs/ai-native-toolkit/skills/skill-forge Skill

    30★ repo

    Harden a skill or any agent instruction file (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules, .github/copilot-instructions.md) through judge-panel refinement rounds until it clears a 3-tier promotion gate, then promote it. A quality gate that runs after authoring, not an authoring tool. TRIGGER when the user types /skill-forge, asks to test/harden/forge/prove a skill or an instruction file, wants a CLAUDE.md or AGENTS.md driven through adversarial rounds before shipping, asks 'is this skill ready?' or 'is this CLAUDE.md safe for a cold-start agent?', or wants a skill or instruction file quality-gated by a judge panel.

  • Agent loops

    NickCrew/Claude-Cortex/skills/agent-loops Skill

    30★ repo

    Complete operational workflow for implementer agents (Codex, Gemini, etc.) making code changes and writing tests. Drives all work through atomic commits — each loop operates on the smallest complete, reviewable change. Defines the Code Change Loop, Test Writing Loop, Lint Gate, and Issue Filing process with circuit breakers, severity levels, and escalation rules. Requires `cortex git commit` for all commits. Includes bundled provider-aware review scripts that keep same-model shell-outs as the last resort, plus a fresh-context Codex fallback for code review and test audit. Use this skill when starting any implementation task.

  • Dispatching parallel agents

    NickCrew/Claude-Cortex/skills/dispatching-parallel-agents Skill

    30★ repo

    Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

  • Eval designer

    NickCrew/Claude-Cortex/skills/eval-designer Skill

    30★ repo

    Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.

  • Multi llm consult

    NickCrew/Claude-Cortex/skills/multi-llm-consult Skill

    30★ repo

    Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compare answers, or requests delegating a subtask to Gemini/Codex/Qwen.

  • Prompt engineering

    NickCrew/Claude-Cortex/skills/prompt-engineering Skill

    30★ repo

    Optimize prompts for LLMs and AI systems with structured techniques, evaluation patterns, and synthetic test data generation. Use when building AI features, improving agent performance, or crafting system prompts.

  • Skill creator

    NickCrew/Claude-Cortex/skills/skill-creator Skill

    30★ repo

    Guide for creating effective skills. Use when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

  • Subagent driven development

    NickCrew/Claude-Cortex/skills/subagent-driven-development Skill

    30★ repo

    Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

  • Task orchestration

    NickCrew/Claude-Cortex/skills/task-orchestration Skill

    30★ repo

    Use when coordinating complex tasks with orchestration, delegation, or parallel workstreams - provides structured workflows for orchestrate:brainstorm, orchestrate:spawn, and orchestrate:task.

  • Agent constraint triangle scorer

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/crisis/agent-constraint-triangle-scorer Skill

    30★ repo

    Score an agent configuration against Ch1's Agent Constraint Triangle — the three interconnected constraints (complexity management, tool orchestration, context utilization) that make agent design an inherently difficult operational problem. Given the agent's reasoning-chain length, tool-catalog size and disambiguity, and context budget vs. usage, produce a 0-100 pressure score and band per constraint, name which of Ch1's three cyclic trade-offs are active (complexity->tools->context, tools->context->complexity, context->complexity->tools), and give the minimal-but-sufficient recommendation for each stressed constraint. Use before scaling an agent's tools/steps/context to see which corner of the triangle will break first. NOT for model-quality issues (Ch1: the triangle is architectural), NOT for agents under ~10 tools with short chains where no corner is under pressure.

  • Workflow agent spectrum classifier

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/crisis/workflow-agent-spectrum-classifier Skill

    30★ repo

    Place an AI system on Ch1's continuous workflow-agent spectrum instead of the false binary "is it an agent or not". Scores the three dimensions of agency (autonomy / action / authority) plus how predefined the execution path is, returns a spectrum position (0 = workflow, 1 = agent) and a band (WORKFLOW / BLENDED / AGENT), applies Ch1's action test (a system that cannot effect change is an assistant/advisor, not an agent), and reports the four emergent capabilities (autonomous decision-making, contextual understanding, strategic tool utilization, memory persistence). Accepts numeric dimensions or a free-text system description. Use to right-size an architecture — deterministic workflow, blended human-in-the-loop, or full agent. NOT for ranking model quality, NOT for systems with no LLM in the loop.

  • Entity resolution strategy selector

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/knowledge-representation/entity-resolution-strategy-selector Skill

    30★ repo

    Choose HOW to decide when two records are the same real-world entity — EVIDENCE-BASED resolution (deterministic feature-by-feature scoring with explainable evidence and culturally-robust rules) vs GENERALIZATION-BASED AI (LLM statistical similarity, nondeterministic, post-hoc rationalization) — per Ch3 "Entity Resolution: The Foundation of Agent Knowledge". Scores a six-factor requirement profile and picks evidence-based, generalization-AI, or a hybrid; ships a deterministic matcher that scores name/address/phone similarity into an explainable confidence, classifies the resulting graph edge, and flags the edge cases naive matching misses. Use when standing up entity resolution for an agent knowledge graph, justifying an evidence-vs-LLM choice for identity/compliance/fraud work, or auditing a proposed merge. NOT for the extraction stage that produces the records (that is upstream KG construction), NOT for picking a specific ER product, NOT for arity-2 relationship modeling (use graph-model-selector).

  • Kg extraction approach selector

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/knowledge-representation/kg-extraction-approach-selector Skill

    30★ repo

    Select a knowledge-graph EXTRACTION approach for a given source — structured database integration vs LLM-based triple extraction vs iText2KG (incremental) vs RAKG (document-level) — by scoring a SOURCE PROFILE against five features (handles unstructured text, incremental-friendly, document-level context, determinism, setup cost), per Ch3 "Extraction Approaches for Heterogeneous Sources". A structured source hard-routes to schema materialization; the `incremental-cost` helper makes the iText2KG win concrete (re-process only new documents, not the entire corpus). Use when picking how to ingest a source into an agent's knowledge graph. NOT for choosing the graph MODEL class (use graph-model-selector), NOT for vendor/product selection, NOT for temporal/bitemporal modeling (that is the ATOM discussion, out of scope here), NOT when the ingestion pipeline is already mandated.

  • Three graph router

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/knowledge-representation/three-graph-router Skill

    30★ repo

    Route an incoming record/fact into the correct graph of the Three-Graph Architecture (Ch3) — DOMAIN (trusted, entity-resolved single source of truth), LEXICAL (verbatim source text with provenance, the "retrieval" in RAG), or SUBJECT (LLM-extracted artifacts kept SEPARATE from domain until entity resolution links them). The router enforces the boundaries that make the architecture work — an extraction can NEVER be written straight into the domain graph; it must enter subject and link via CORRESPONDS_TO above a confidence threshold (default 0.85). Use when ingesting mixed structured + unstructured data into an agent knowledge graph, when designing the separation between trusted and extracted knowledge, or when preventing extraction errors from contaminating ground truth. NOT for single-source trusted data (no separation needed), NOT for the entity- resolution matching algorithm itself (this gates the link; a real matcher swaps in at the seam), NOT for graph storage/query engine choice.

  • Hierarchical memory

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/memory/hierarchical-memory Skill

    30★ repo

    Three-tier hierarchical memory (Letta / MemGPT pattern) — core / recall / archival. Core holds a small, fast, frequently-accessed working set (e.g. core_limit=2000 tokens). Recall holds raw interaction history for "what did we talk about yesterday" questions. Archival holds effectively unlimited overflow, still searchable. Make forgetting and archiving explicit design choices, not afterthoughts. Use when an agent must feel consistent across long sessions and the context window is the scarcest resource. NOT for one-shot agents (no persistence needed), NOT for event logs (use append-only kafka-style), NOT when every fact is equally important (then a flat store is correct).

  • Memory consistency model selector

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/memory/memory-consistency-model-selector Skill

    30★ repo

    Choose a memory consistency model PER agent-coordination operation — STRONG (linearizable), CAUSAL, READ-YOUR-WRITES, or EVENTUAL — by scoring the operation's requirements (shared authoritative state, conflict intolerance, staleness budget, collaboration, self-session continuity), per Ch4 "Memory consistency models for agent coordination". The chapter's rule: default to causal, escalate to strong only for irreversible decision points. Also flags cache-sharing divergence — an agent acting on a cached read older than a committed write it depends on. Use when designing shared memory for a multi-agent system, justifying a consistency choice, or auditing a stale- cache handoff. NOT for single-agent stateless systems (no coordination), NOT for picking a datastore product (this picks the model, not Redis-vs-etcd), NOT when the platform already mandates a consistency model (just adopt it).

  • Memory consolidation

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/memory/memory-consolidation Skill

    30★ repo

    Consolidation pipeline — turn noisy raw episodes into durable knowledge (Agentic GraphRAG Ch4, Example 4-5 + Example 4-13). Four steps: cluster related episodes by topic, summarize each cluster into one consolidated fact, create the consolidated node, and maintain a provenance chain back to the source episodes so "how do you know that?" is answerable. Clusters below a minimum size (default 3) are skipped — not enough examples to generalize. Adds the sleep-time-compute discipline: run consolidation during idle periods, never on the synchronous response path, and pre-compute inferences that anticipate likely queries. Use when an agent accumulates redundant, overlapping experiences that must compress into stable, queryable patterns. NOT for one-shot agents (nothing to consolidate), NOT for the response hot path (consolidation is a background/idle job), NOT for facts that must stay individually addressable (consolidation merges them).

  • Execution graph

    AnthonyAlcaraz/agentic-graph-rag-skills/skills/self-evolution/execution-graph Skill

    30★ repo

    Foundational Ch7 primitive: an immutable, queryable graph of every decision / retrieval / tool-call / LLM-call an agent made for a specific query. Nodes are atomic operations carrying input/output/timestamp/ latency/cost/tokens; edges are TRIGGERED relationships establishing the full causal lineage. Two-phase write — create-on-start (captures structure even on failure), fill-on-complete (latency + cost + output). Enables diagnostic queries that flat logs cannot answer ("every tool invocation that followed an LLM call with confidence < 0.7 and resulted in latency > 3s"). Use BEFORE building any Ch7 evaluation or self-evolution machinery — it is the substrate everything else depends on. NOT for one-shot single-call agents (no graph to trace), NOT for systems where observability already lives in OpenTelemetry-to-graph pipeline (you have it already).