Context & AI engineering
25,772 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
mindstone/mcp-servers/io.github.mindstone/mcp-server-talentlms MCP server
no license10★ repoTalentLMS MCP server: users, courses, groups, branches, reporting, and assessments
mindstone/mcp-servers/io.github.mindstone/mcp-server-zendesk MCP server
no license10★ repoZendesk MCP server for Model Context Protocol hosts
mindstone/mcp-servers/io.github.mindstone/mcp-server-slack MCP server
no license10★ repoSlack MCP server: channels, messages, threads, reactions, users, files, and scheduled messages
mindstone/mcp-servers/io.github.mindstone/mcp-server-salesforce MCP server
no license10★ repoSalesforce CRM MCP server: accounts, contacts, opportunities, leads, tasks, and custom objects
mindstone/mcp-servers/io.github.mindstone/mcp-server-retell-ai MCP server
no license10★ repoRetell AI MCP server: voice agent phone calls, agent management, LLMs, and voice discovery
mindstone/mcp-servers/io.github.mindstone/mcp-server-workday MCP server
no license10★ repoWorkday HCM MCP server for Model Context Protocol hosts — workers, profiles, organizations
nonlinear-xyz/factory-kit/skills/factory-llm-workflow-engineer Skill
9★ repoUse when building LangGraph workflows, agents, RAG systems, structured-output nodes, streaming chat surfaces, or anything LLM-driven with state. Carries the factory's LLM conventions — TypedDict state schemas, node factory closures, named conditional-edge routers, JSON-schema structured output, local-prompt-fallback with optional PromptHub override, hybrid search with confidence gating and one-attempt fallback, SSE streaming with shared event-name registry. Cothon is the reference repo.
nonlinear-xyz/factory-kit/skills/factory-llm-workflows Skill
9★ repoLLM workflow conventions distilled from production agent/RAG work. Covers LangGraph TypedDict state schemas, node factory closures, conditional edge routing, structured output via JSON schema, prompt fallback patterns with optional PromptHub override, hybrid search with confidence gating + fallback supplement, SSE streaming with event dispatch, hexagonal ports/adapters when scale justifies. Read when building any LLM-driven workflow with state, tool calls, or streaming UX.
nonlinear-xyz/factory-kit/skills/factory-prompt Skill
9★ repoConvert a rough ask into a structured XML-tagged prompt using the factory-prompting vocabulary
nonlinear-xyz/factory-kit/skills/factory-prompting Skill
9★ repoStructured prompting with XML tags. A small named vocabulary (`instructions`, `context`, `input`, `output_format`, `examples`, `constraints`, `role`, `thinking`) that turns a prose ask into something the model can parse without ambiguity. Read whenever you're authoring a prompt by hand, designing a prompt template for production, or rewriting a flaky ask. Paired with `/prompt`, which converts a rough ask into the structured form.
nonlinear-xyz/factory-kit/skills/factory-verification Skill
9★ repoHow we know the software the factory produces is correct, and how we know the kit's own conventions are followed. Defines the four-tier eval spectrum (CLI rule / test / agent / human gate), the rule that evals graduate downward to their cheapest home, the banded coverage score with severity-aware disclosure, and the delta-gated GitHub Action that guards the PR boundary without disrupting the inner loop. The recipe locks to `factory-kit-check` + GitHub Actions; the principles are stack-agnostic. Read at project kickoff, when wiring the conformance gate, and whenever asking "how do we know the agent did this right?"
huzaifa525/claude-code-optimizer/templates/.claude/skills/subagent-dev Skill
9★ repoUse when executing a multi-task plan where each task is independent, or when the user wants parallel or isolated task execution with review.
huzaifa525/claude-code-optimizer/templates/.claude/skills/worktree Skill
9★ repoUse when the user wants to work in an isolated branch, start a safe development environment, or avoid polluting the main branch.
yamanidev/claude-code-configuration/skills/handoff Skill
9★ repoWorkflow for compacting the current conversation into a handoff document that another Claude Code session can pick up from later. Produces a single Markdown file capturing the goal, current state, in-flight work, decisions made, open questions, paths touched, and a recommended next-session skill — referencing existing artifacts (commits, PRs, diffs, plan docs, tickets, ADRs) by path or URL rather than duplicating them. NOT for writing tickets for a human development team (use /write-task for that) and NOT for permanent documentation of decisions (commits, ADRs, or the codebase own that).
yamanidev/claude-code-configuration/skills/meta Skill
9★ repoWorkflow for authoring or revising any Claude Code configuration — skills (SKILL.md), CLAUDE.md guardrails, settings.json (permissions, hooks, env, model), sub-agents, slash commands, MCP server entries, plugins, and the install or sync scripts around them. Operates from working knowledge of LLMs, agent harnesses, and context engineering so the configuration it produces leverages how Claude Code actually loads, routes, and applies it. Discovers and matches the local canon (project, user, or plugin scope) before writing — does not force one repo's conventions onto another. NOT for editing application code (use /ship in the target repo for that).
itaywol/adeptability/.adeptability/base/using-adept Skill
9★ repoUse the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
itaywol/adeptability/.adeptability/skills/authoring-adept-agents Skill
9★ repoWrite a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running `adept agent add`.
itaywol/adeptability/.adeptability/skills/using-adept Skill
9★ repoUse the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
itaywol/adeptability/.adeptability/staging/.claude/skills/authoring-adept-agents Skill
9★ repoWrite a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running `adept agent add`.
itaywol/adeptability/.adeptability/staging/.claude/skills/using-adept Skill
9★ repoUse the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
itaywol/adeptability/.adeptability/staging/skills/using-adept Skill
9★ repoUse the `adept` CLI to author AI skills once and render them into Claude Code, Cursor, Codex, Copilot, and OpenCode. Apply when installing/syncing skills, editing skill.yaml/SKILL.md, or touching .adeptability/.
itaywol/adeptability/internal/defaultskills/assets/authoring-adept-agents Skill
9★ repoWrite a good, portable adept agent (subagent): trigger-shaped description, one job per agent, generator/evaluator separation, explicit boundaries, restricted tools. Apply when creating or editing an agent file or running `adept agent add`.
itaywol/adeptability/internal/defaultskills/assets/using-adept Skill
9★ repoUse the `adept` CLI to author an AI skill once and render it into Claude Code, Cursor, Codex, Copilot, OpenCode, and 45+ agents. Apply when installing/syncing skills, editing SKILL.md, or touching .adeptability/.
vanara-agents/skills/skills/prompt-engineering Skill
9★ repoA deep, practical guide to engineering reliable LLM prompts — role/context, instructions, few-shot, structured output, chain-of-thought, delimiting untrusted data, injection defense, and evaluation. Includes worked prompts and a runnable output validator.
endorphin-ai/hasbrains-agent-kit/context-engineering/skills/prompt-expert Skill
9★ repoThe battle-tested Claude Code kit behind HasBrainsAI — agent skills, subagents & slash commands for production multi-agent systems. Install in one command.
Maudeunfledged834/startup-founder-skills/skills/tech-stack-eval Skill
9★ repoWhen the user needs to choose between technologies, frameworks, or tools — or says "which framework should I use", "compare X vs Y", "should we migrate from X to Y", "what database should I use", "calculate TCO".
ellmos-ai/skills/skills/dev/dev-soft-agent Skill
9★ repoAutomatisierte Software-Entwicklungspipeline. Scannt Projekte, priorisiert Tasks, analysiert Code und orchestriert Entwicklungsschleifen. Zero Dependencies (nur Python stdlib).
ellmos-ai/skills/skills/dev/trampelpfadanalyse Skill
9★ repoError analysis for pipeline and control-file workflows: check whether a convention or procedure is actually visible and discoverable to an LLM. Empirical baseline → intervention → retest comparison using naive subagents (isolated sandbox copies, identical test case, quantitative success measurement). Use this skill when agents repeatedly ignore a rule/README/convention or navigate incorrectly, and you want to measure whether a documentation change actually changes the behavior. Triggers on "is the convention even seen", "why does no agent follow the rule", "make a doc signpost measurably effective", "desire-path analysis", "trampelpfadanalyse".
ellmos-ai/skills/skills/infrastructure/agent-config-sync Skill
9★ repoSynchronisiert MCP-Server UND Skills uebergreifend ueber ALLE bekannten Agent-Apps und CLIs (Claude Code, Claude Desktop, Codex CLI, Antigravity/Gemini, Kimi Code, Cursor, Cline, Windsurf, GitHub Copilot, ...) auf einem oder mehreren Systemen. Aktiviert sich, wenn ein MCP-Server oder Skill in mehreren Agent-Tools verfuegbar gemacht werden soll, der User fragt "sync mcp/skills ueber alle agents", "warum hat Tool X den Server/Skill nicht", "MCP/Skills ueberall verteilen", "config-sync zwischen agents", oder ein neues Agent-Tool an den gemeinsamen Stand angeschlossen werden soll. Liest eine Registry (welche Tools syncen wie), eine Config (Anbieter-Standardspezifikationen: wo + welches Format) und einen Lauf-Cache (aufgeloeste reale Pfade), wendet Sync-Regeln an (pull vs. verteilen) und verifiziert. Enthaelt einen Lernmechanismus: unbekannte/veraltete Config-Orte werden per Systemsuche, WebSearch und Context7 nachgeschlagen und in der Config aktualisiert. Loest den aelteren, auf Claude Code <-> Claude Desktop beschraenkten Skill mcp-config-sync ab (umschliesst ihn als Spezialfall). Claude-MCP-Profile werden via ellmos-controlcenter-mcp-Backend verwaltet (resolve_profile / switch_profile), nicht durch eigene Logik.
ellmos-ai/skills/skills/infrastructure/mcp-config-sync Skill
9★ repoSynchronisiert MCP-Server zwischen den Agent-Apps Claude Code und Claude Desktop auf demselben Rechner. Aktiviert sich, wenn der User einen MCP-Server in beiden Apps verfuegbar machen will, einen MCP-Server hinzufuegt/aendert/entfernt, fragt "warum sieht Claude Desktop den Server nicht", "sync zwischen claude-code und claude-desktop", "MCP in beiden", "shared mcp", oder Plugins/Extensions zwischen beiden Apps koordinieren will. Auch beim Umzug auf ein neues System nutzen, sobald beide Apps installiert sind, damit beide denselben MCP-Stand haben. Skill enthaelt Sync-Skripte fuer Windows (PowerShell) und macOS (zsh+jq) sowie eine Master-Datei-Vorlage.
ellmos-ai/skills/skills/research/research-agent Skill
9★ repoForschungspipeline fuer PubMed und arXiv. Schnellrecherche und strukturierte Literatur-Reviews mit reiner Python-Standardbibliothek.
ellmos-ai/skills/skills/utilities/llm-text-hygiene Skill
9★ repoText-Skill zum Prüfen und Bereinigen von LLM-Spuren in fertigen Texten (Paper, README, Bericht, Blogpost, Bewerbung): Chat-/Prompt-Reste und Regieanweisungen („Wie besprochen lassen wir diesen Teil …"), stehengebliebene Platzhalter, LLM-Danksagungen, typische LLM-Stilmuster und typografische Artefakte — plus Korrektheits-Check der AI-Disclosure. Nutze diesen Skill bei „LLM-Muster/KI-Spuren entfernen", „klingt nach ChatGPT/KI", „Chat-Reste im Text", „Paper vor Publikation auf KI-Rückstände prüfen", „AI-Disclosure prüfen", oder als periodischen Check über einen Dokumentbestand. Immer über ALLE Sprachfassungen eines Dokuments. Für Byte-/Encoding-Reparatur stattdessen encoding-fix.
geledek/enterprise-ai-transformation-skills/skills/tech-agent-guardrail Skill
9★ repoUse when deploying an AI agent, reviewing agentic AI governance, checking whether an AI agent deployment is safe and well-governed, or assessing whether an organization's oversight of autonomous AI systems is adequate. Phrases like "check the governance on this agent deployment", "is our agentic AI safe to deploy?", "review guardrails for this AI agent", "we're about to launch an AI agent — what do we need to have in place?", "help me assess our agentic AI oversight" all trigger this skill. Runs IMDA's four-dimension agentic governance check across risk bounding, human accountability, technical controls, and end-user responsibility. Outputs a governance readiness assessment with gaps and required actions.
Haochenhust/ch-skills/skills/meta-prompt Skill
9★ repo把用户口语化/模糊的任务描述转成一段高质量、可直接复制到其他 AI 会话使用的 prompt。**必须用此 skill**当用户说「帮我优化 prompt」「这段任务怎么问 AI 更好」「写一个 prompt 我发给 GPT/Claude」「帮我写 prompt」「把这个需求包装成 prompt」「meta prompt」,或者显式调用 `/mp`。默认产出 Claude 友好的 XML 结构化 prompt,当用户指定目标是 GPT/ChatGPT/OpenAI 时切换为 markdown 分节格式。**不要在当前会话执行产出的 prompt,只输出 prompt 文本给用户复制**。
Chili-Piper/mcp-assets/skills/handoff-router-configuration Skill
no license9★ repoCreates, reads, updates, and deletes Chili Piper Handoff routers — the rep-to-rep handoff routing configurations that decide who receives a handoff and which meeting type gets booked. Always-live writes with dry-run diffs, representability checks, and delete confirmation.
gaelic-ghost/socket/plugins/apple-dev-skills/skills/safari-mcp-workflow Skill
9★ repoInspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
Xcode coding intelligence workflow
gaelic-ghost/socket/plugins/apple-dev-skills/skills/xcode-coding-intelligence-workflow Skill
9★ repoGuide Xcode coding-intelligence setup, Xcode-hosted agents, external-agent access through xcrun mcpbridge, command and tool permissions, Xcode-only agent configuration homes, and setup handoffs for Xcode 27 beta-era agentic coding workflows.
gaelic-ghost/socket/plugins/apple-dev-skills/skills/xcode-debugger-mcp-workflow Skill
9★ repoDiagnose a running Apple app through Xcode’s active LLDB debugging session and assess the experimental Xcode 27 lldb-mcp executable. Use when setting breakpoints, inspecting frames or variables, issuing LLDB commands, or distinguishing a usable Xcode debugger session from an unavailable standalone debugger MCP server.
gaelic-ghost/socket/plugins/cardhop-app/skills/cardhop-contact-workflow Skill
9★ repoAdd or update Cardhop.app contacts through the bundled Cardhop.app Socket MCP server. Use when a user wants to create a contact, adjust an existing contact, or validate Cardhop automation readiness on macOS.
Operate agentic security tools
gaelic-ghost/socket/plugins/cybersecurity-skills/skills/operate-agentic-security-tools Skill
9★ repoOperate security tools through an AI agent with explicit authority and evidence boundaries. Use when an agent may invoke local CLIs, GUI apps, browser automation, MCP servers, remote scanners, sandboxes, vulnerability tools, packet tools, or containment actions and permissions, mounts, network, secrets, approvals, logging, output, and cleanup must be constrained.
Conversation state human handoff
gaelic-ghost/socket/plugins/messaging-collaboration-skills/skills/conversation-state-human-handoff Skill
9★ repoPlan conversation identity, state, consent, escalation, transcript, and human-handoff behavior for bots and business messaging agents.
gaelic-ghost/socket/plugins/messaging-collaboration-skills/skills/teams-agent-workflow Skill
9★ repoPlan, build, and validate Microsoft Teams bots and agents with Teams SDK or Microsoft 365 Agents SDK, Microsoft Entra, Adaptive Cards, and tenant deployment boundaries.
gaelic-ghost/socket/plugins/model-lab-skills/skills/benchmark-model-runtime Skill
9★ repoBenchmark model runtimes across latency, throughput, memory, energy, load time, size, and stability. Use when comparing Core AI, Core ML, MLX, ExecuTorch, PyTorch, quantization, devices, or packaging.
gaelic-ghost/socket/plugins/model-lab-skills/skills/evaluate-tool-calling-model Skill
9★ repoEvaluate tool selection, arguments, schemas, execution, observation use, recovery, and side effects. Use when comparing tool-capable checkpoints, prompts, parsers, agent loops, function schemas, or harnesses.
gaelic-ghost/socket/plugins/productivity-skills/skills/codex-gui-worktree-workflow Skill
9★ repoPlan and align Codex GUI worktree-first workflows, local environments, actions, permanent worktrees, and handoffs to Git or Worktrunk worktrees. Use when a repo should make Codex app Worktree mode easier to use without mixing stack-specific commands into general guidance.
Design agent automation workflow
gaelic-ghost/socket/plugins/productivity-skills/skills/design-agent-automation-workflow Skill
9★ repoDesign framework-neutral agent and automation workflows before implementation. Use when choosing between Codex app automations, codex exec, Codex subagents, OpenAI Agents SDK services, LangGraph graphs, Hermes-specific workflows, full-auto execution, auto-with-escalation, or no automation yet, and when the user wants a planning/scaffolding pass that delegates stack-specific implementation to the owning plugin or official docs.
gaelic-ghost/socket/plugins/productivity-skills/skills/design-agent-eval-workflow Skill
9★ repoDesign evaluation workflows for agent, skill, prompt, and automation behavior before implementation. Use when choosing eval cases, graders, thresholds, regression runs, full-auto gates, or escalation points for Codex skills, repo-local agents, OpenAI Agents SDK services, LangGraph graphs, or other agentic workflows.
gaelic-ghost/socket/plugins/productivity-skills/skills/dice-job-search-workflow Skill
9★ repoSearch and triage technology jobs through Dice's remote MCP server. Use when the user wants Dice.com job search help, MCP setup guidance, role-fit triage, resume-to-listing comparison, saved search prompt design, salary or skills trend checks, or recurring job-search automation boundaries grounded in Dice's documented search_jobs tool.
gaelic-ghost/socket/plugins/python-skills/skills/bootstrap-python-mcp-service Skill
9★ repoBootstrap Python MCP server projects and workspaces on macOS using uv and FastMCP with consistent defaults. Use when creating a new MCP server from scratch, scaffolding a single uv MCP project, scaffolding a uv workspace with package/service members, customizing scaffold defaults through layered YAML profiles, initializing pytest+ruff+mypy defaults, creating README.md, initializing git, running initial validation checks, or starting from OpenAPI/FastAPI with MCP mapping guidance.
gaelic-ghost/socket/plugins/reverse-engineering-skills/skills/connect-hopper-mcp Skill
9★ repoConnect an installed Hopper MCP server safely from Codex or Hermes for document navigation, assembly, pseudocode, strings, procedures, and cross-references with a private profile, read-only allowlist, approvals, and data boundaries.
gaelic-ghost/socket/skills/benchmark-model-runtime Skill
9★ repoBenchmark model runtimes across latency, throughput, memory, energy, load time, size, and stability. Use when comparing Core AI, Core ML, MLX, ExecuTorch, PyTorch, quantization, devices, or packaging.
gaelic-ghost/socket/skills/connect-hopper-mcp Skill
9★ repoConnect an installed Hopper MCP server safely from Codex or Hermes for document navigation, assembly, pseudocode, strings, procedures, and cross-references with a private profile, read-only allowlist, approvals, and data boundaries.
Conversation state human handoff
gaelic-ghost/socket/skills/conversation-state-human-handoff Skill
9★ repoPlan conversation identity, state, consent, escalation, transcript, and human-handoff behavior for bots and business messaging agents.
gaelic-ghost/socket/skills/evaluate-tool-calling-model Skill
9★ repoEvaluate tool selection, arguments, schemas, execution, observation use, recovery, and side effects. Use when comparing tool-capable checkpoints, prompts, parsers, agent loops, function schemas, or harnesses.
gaelic-ghost/socket/skills/hermes-agent-compatibility Skill
9★ repoMaintain a clear Socket-to-Hermes compatibility boundary across skills, Codex plugins, MCP configuration, and native Hermes plugins. Use when exporting Socket skills to Hermes or deciding whether an adapter is needed.
Operate agentic security tools
gaelic-ghost/socket/skills/operate-agentic-security-tools Skill
9★ repoOperate security tools through an AI agent with explicit authority and evidence boundaries. Use when an agent may invoke local CLIs, GUI apps, browser automation, MCP servers, remote scanners, sandboxes, vulnerability tools, packet tools, or containment actions and permissions, mounts, network, secrets, approvals, logging, output, and cleanup must be constrained.
gaelic-ghost/socket/skills/safari-mcp-workflow Skill
9★ repoInspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
gaelic-ghost/socket/skills/teams-agent-workflow Skill
9★ repoPlan, build, and validate Microsoft Teams bots and agents with Teams SDK or Microsoft 365 Agents SDK, Microsoft Entra, Adaptive Cards, and tenant deployment boundaries.
duthaho/skillhub/.claude/skills/tune Skill
9★ repoHarness retro — turn recurring agent mistakes into one-line fixes. Mines recent session transcripts (plus the bugfix log and past runs) for repeated corrections, permission friction, and rules that get violated anyway, then proposes ranked changes one at a time: a CLAUDE.md rule, an allowlist entry, a script replacing repeated prose, a new-skill candidate, or a deletion that no longer earns its context cost. Nothing applies without approval; accepted/rejected findings persist in out/tune/learnings.md. Use when the user says "/tune", "improve my setup", "why does claude keep doing X", or after a frustrating session. done's one-line retro catches one lesson at ship time; tune is the periodic audit of the whole harness.
ceoimperiumprojects/imperium-brain/skills/engineering-advanced Skill
no license9★ repoAdvanced engineering patterns for AI-native products. Use when the user mentions agent design, RAG architecture, AI pipelines, MCP servers, API design best practices, CI/CD pipeline architecture, system design interviews, observability, infrastructure as code, or advanced engineering topics. Also triggers on: agent, RAG, retrieval augmented generation, MCP, API design, REST, GraphQL, CI/CD, GitHub Actions, Docker, Kubernetes, microservices architecture, event-driven, message queues, caching strategies, database design, system design.