Context & AI engineering
25,745 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
MadewellRD/skills-lab/dist/vendor/anthropic/sales-command-desk/customer-handoff-desk Skill
2★ repoprepare post-sale handoff packages for onboarding, customer success, support, or implementation teams. use when Claude needs to perform or continue sales revenue command desk work involving accounts, leads, opportunities, crm, calendar, email, files, prospecting, proposals, forecasts, renewals, or customer handoffs.
MadewellRD/skills-lab/dist/vendor/anthropic/sdlc-command-desk/implementation-handoff-desk Skill
2★ repocreate, review, refine, and package connector-grounded implementation handoffs for coding agents after requirements, discovery, architecture, and issue planning are complete. use when the user asks for Claude Code instructions, branch work, commit plans, pull request handoffs, halt-resume prompts, merge-train runbooks, repo cleanup prompts, docs/proof handoffs, or low-token coding-agent execution plans backed by github, issues, docs, ci checks, and source facts.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/agent-architecture-desk Skill
2★ repodesign AI agent architecture including planning boundaries, execution loops, memory and state strategy, tool routing, approval gates, retries, delegation, and halt behavior.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/agent-observability-desk Skill
2★ repodesign observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval events, approvals, errors, eval probes, cost, latency, and safety signals.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/ai-engineering-command-desk Skill
2★ repoorchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eval, safety, inference, observability, release, and incident stages using connector-grounded evidence, workflow packets, stage advancement, and halt behavior.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/ai-incident-response-desk Skill
2★ repotriage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse, data leakage, model regressions, cost spikes, latency degradation, eval regressions, or user harm reports.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/eval-design-desk Skill
2★ repodesign AI evaluation plans with goals, datasets, rubrics, grading methods, thresholds, regression slices, safety checks, human review, and reporting requirements.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/eval-run-analysis-desk Skill
2★ repoanalyze completed AI eval runs, regression deltas, failure clusters, grading reliability, threshold status, release blockers, and rerun recommendations.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/prompt-systems-desk Skill
2★ repodesign prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior, prompt evaluation fixtures, prompt injection defenses, and prompt observability hooks for AI capabilities.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/red-team-eval-desk Skill
2★ repoplan and analyze adversarial AI testing for jailbreaks, prompt injection, data exfiltration, harmful instructions, over-permissioned tools, and policy evasion.
MadewellRD/skills-lab/dist/vendor/google/ai-engineering-command-desk/retrieval-rag-design-desk Skill
2★ repodesign retrieval augmented generation systems with indexing, chunking, embeddings, ranking, filters, citations, freshness policy, permission filtering, and grounding behavior.
MadewellRD/skills-lab/dist/vendor/google/customer-success-command-desk/post-sale-handoff-desk Skill
2★ reporeconcile the executed order form against what the deal narrative promised at closed-won handoff, covering entitlement and term facts read from the contract, the commitment register of sales-cycle promises with who made them and to whom, the buying group as it stood at signature, implementation assumptions the deal was priced on, and the kickoff acceptance decision. use for handoff intake, sales to customer success transition, new logo readiness, co-term and amendment intake, and reconciling what was sold against what was signed.
MadewellRD/skills-lab/dist/vendor/google/customer-support-command-desk/knowledge-base-desk Skill
2★ repoauthor and govern help center and internal knowledge base articles captured from resolved contacts, scoped to the product versions and editions they are true for, with steps verified against a stated build, titles and search terms written in the customer's words, ownership and review dates, duplicate and contradiction reconciliation, and a staleness register for articles a release has silently invalidated. use for knowledge-centered service work, article drafting, kb audits, content lifecycle, and post-release documentation checks.
MadewellRD/skills-lab/dist/vendor/google/data-command-desk/batch-orchestration-desk Skill
2★ repodesign pipeline scheduling and the dag, covering data aware triggering that waits for data rather than for a clock, sensors and arrival timeouts, retry policy and non retryable failure classes, concurrency pools and queueing at peak, sla miss conditions and notification, catch up and backfill controls with partition bounds and concurrency caps, run isolation between backfill and scheduled runs, and the failure pattern read from run history. use for airflow or dagster dag design, scheduling reviews, sla definition, retry tuning, and backfill orchestration.
MadewellRD/skills-lab/dist/vendor/google/sales-command-desk/customer-handoff-desk Skill
2★ repoprepare post-sale handoff packages for onboarding, customer success, support, or implementation teams. use when Gemini needs to perform or continue sales revenue command desk work involving accounts, leads, opportunities, crm, calendar, email, files, prospecting, proposals, forecasts, renewals, or customer handoffs.
MadewellRD/skills-lab/dist/vendor/google/sdlc-command-desk/implementation-handoff-desk Skill
2★ repocreate, review, refine, and package connector-grounded implementation handoffs for coding agents after requirements, discovery, architecture, and issue planning are complete. use when the user asks for Jules instructions, branch work, commit plans, pull request handoffs, halt-resume prompts, merge-train runbooks, repo cleanup prompts, docs/proof handoffs, or low-token coding-agent execution plans backed by github, issues, docs, ci checks, and source facts.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/agent-architecture-desk Skill
2★ repodesign AI agent architecture including planning boundaries, execution loops, memory and state strategy, tool routing, approval gates, retries, delegation, and halt behavior.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/agent-observability-desk Skill
2★ repodesign observability for AI agents and workflows including traces, prompts, model calls, tool calls, retrieval events, approvals, errors, eval probes, cost, latency, and safety signals.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/ai-engineering-command-desk Skill
2★ repoorchestrate AI engineering workflows from capability intent through model, prompt, tool, agent, retrieval, eval, safety, inference, observability, release, and incident stages using connector-grounded evidence, workflow packets, stage advancement, and halt behavior.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/ai-incident-response-desk Skill
2★ repotriage AI production incidents involving hallucination spikes, safety failures, prompt injection, tool misuse, data leakage, model regressions, cost spikes, latency degradation, eval regressions, or user harm reports.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/eval-design-desk Skill
2★ repodesign AI evaluation plans with goals, datasets, rubrics, grading methods, thresholds, regression slices, safety checks, human review, and reporting requirements.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/eval-run-analysis-desk Skill
2★ repoanalyze completed AI eval runs, regression deltas, failure clusters, grading reliability, threshold status, release blockers, and rerun recommendations.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/prompt-systems-desk Skill
2★ repodesign prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior, prompt evaluation fixtures, prompt injection defenses, and prompt observability hooks for AI capabilities.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/red-team-eval-desk Skill
2★ repoplan and analyze adversarial AI testing for jailbreaks, prompt injection, data exfiltration, harmful instructions, over-permissioned tools, and policy evasion.
MadewellRD/skills-lab/dist/vendor/openai/ai-engineering-command-desk/retrieval-rag-design-desk Skill
2★ repodesign retrieval augmented generation systems with indexing, chunking, embeddings, ranking, filters, citations, freshness policy, permission filtering, and grounding behavior.
MadewellRD/skills-lab/dist/vendor/openai/customer-success-command-desk/post-sale-handoff-desk Skill
2★ reporeconcile the executed order form against what the deal narrative promised at closed-won handoff, covering entitlement and term facts read from the contract, the commitment register of sales-cycle promises with who made them and to whom, the buying group as it stood at signature, implementation assumptions the deal was priced on, and the kickoff acceptance decision. use for handoff intake, sales to customer success transition, new logo readiness, co-term and amendment intake, and reconciling what was sold against what was signed.
MadewellRD/skills-lab/dist/vendor/openai/customer-support-command-desk/knowledge-base-desk Skill
2★ repoauthor and govern help center and internal knowledge base articles captured from resolved contacts, scoped to the product versions and editions they are true for, with steps verified against a stated build, titles and search terms written in the customer's words, ownership and review dates, duplicate and contradiction reconciliation, and a staleness register for articles a release has silently invalidated. use for knowledge-centered service work, article drafting, kb audits, content lifecycle, and post-release documentation checks.
MadewellRD/skills-lab/dist/vendor/openai/data-command-desk/batch-orchestration-desk Skill
2★ repodesign pipeline scheduling and the dag, covering data aware triggering that waits for data rather than for a clock, sensors and arrival timeouts, retry policy and non retryable failure classes, concurrency pools and queueing at peak, sla miss conditions and notification, catch up and backfill controls with partition bounds and concurrency caps, run isolation between backfill and scheduled runs, and the failure pattern read from run history. use for airflow or dagster dag design, scheduling reviews, sla definition, retry tuning, and backfill orchestration.
MadewellRD/skills-lab/dist/vendor/openai/sales-command-desk/customer-handoff-desk Skill
2★ repoprepare post-sale handoff packages for onboarding, customer success, support, or implementation teams. use when ChatGPT needs to perform or continue sales revenue command desk work involving accounts, leads, opportunities, crm, calendar, email, files, prospecting, proposals, forecasts, renewals, or customer handoffs.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/implementation-handoff-desk Skill
2★ repocreate, review, refine, and package connector-grounded implementation handoffs for coding agents after requirements, discovery, architecture, and issue planning are complete. use when the user asks for Codex instructions, branch work, commit plans, pull request handoffs, halt-resume prompts, merge-train runbooks, repo cleanup prompts, docs/proof handoffs, or low-token coding-agent execution plans backed by github, issues, docs, ci checks, and source facts.
stephen94125/peon-lib/.skills/skill-creator Skill
2★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.
The same file is in 66 other repositories
Claude in chrome troubleshooting
Fodhol/skills/plugins/claude-in-chrome-troubleshooting/skills/claude-in-chrome-troubleshooting Skill
2★ repoDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
The same file is in 3 other repositories
Rayan55050/progressive-agent/skills/skill_creator Skill
2★ repoСоздание новых скиллов — агент сам себя развивает
is-bo/fullstack-forge-skill/.cursor/skills/forge-ai Skill
2★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.gemini/skills/forge-ai Skill
2★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.github/skills/forge-ai Skill
2★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/.windsurf/skills/forge-ai Skill
2★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.
is-bo/fullstack-forge-skill/src/fullstack-forge/commands/forge-ai Skill
2★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Activate automatically for llm, embedding, classifier, agent, retrieval, or generative-media features when that concern is relevant to a software-engineering request.
andylbrummer/math-mcp/io.github.andylbrummer/neural-mcp MCP server
2★ repoGPU-accelerated MCP server for neural network training, deep learning, and model experimentation
andylbrummer/math-mcp/io.github.andylbrummer/quantum-mcp MCP server
2★ repoGPU-accelerated MCP server: quantum mechanics, wavefunction evolution, Schrodinger simulations
marcelo-ochoa/servers/io.github.marcelo-ochoa/oracle MCP server
no license2★ repoMCP server for interacting with Oracle databases
marcelo-ochoa/servers/io.github.marcelo-ochoa/qnap MCP server
no license2★ repoMCP server for QNAP NAS API
marcelo-ochoa/servers/io.github.marcelo-ochoa/postgres MCP server
no license2★ repoMCP server for interacting with PostgreSQL databases
ormastes/simple/io.github.ormastes/t32-lsp-mcp-server MCP server
no license2★ repoTRACE32 CMM LSP via MCP — parse, diagnostics, completions, hover, symbols
ormastes/simple/io.github.ormastes/t32-mcp-server MCP server
no license2★ repoTRACE32 debugger MCP — session, dialog, field, history, resource inspection
DEPRECATED - Use lexiang-mcp-server
tencent-lexiang/lexiang-mcp-server/io.github.tencent-lexiang/mcp-server MCP server
2★ repoDEPRECATED: Please use io.github.tencent-lexiang/lexiang-mcp-server instead.
vdappdev2/verusidx-mcp/io.github.vdappdev2/data MCP server
2★ repoMCP server for Verus on-chain data retrieval, decryption, signing, and verification
vdappdev2/verusidx-mcp/io.github.vdappdev2/marketplace MCP server
2★ repoMCP server for Verus on-chain marketplace — create, browse, accept, and close offers
vdappdev2/verusidx-mcp/io.github.vdappdev2/send MCP server
2★ repoMCP server for Verus currency — send, convert, cross-chain transfer, balance/path/tx queries
vdappdev2/verusidx-mcp/io.github.vdappdev2/definecurrency MCP server
2★ repoMCP server for defining Verus currencies — tokens, fractional baskets, centralized, ERC-20 mapped
vdappdev2/verusidx-mcp/io.github.vdappdev2/identity MCP server
2★ repoMCP server for VerusID identities — register, update, revoke, recover, query, set timelock
toRolex/rolex-skills/skills/productivity/handoff Skill
1★ repo将当前对话压缩为 handoff 文档,供另一个 agent 接续。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/session-handoff Skill
1★ repoPrepare a sanitized, evidence-separated continuation brief so a new agent session can resume repository work without reconstructing completed work. Use when context is long, ownership is changing, or work must continue later; reference existing artifacts, record repository and validation state, recommend next Skills, and provide a copyable start prompt. Do not change business code, create commits, promise automatic loading, or write a file unless a safe scratch location and write authorization are available. 生成经过敏感信息清理且区分事实与推断的续接摘要,使新 Agent 会话无需重做已完成工作即可继续仓库任务。用于上下文过长、负责人切换或稍后继续;引用已有产物,记录仓库和验证状态,推荐下一 Skills,并提供可复制启动指令。不修改业务代码、不创建 commit、不声称会自动加载,也不在缺少安全 scratch 位置或写入授权时落盘。
dss-time/repo-doctor-skills/plugins/skill-maintainer/skills/skill-authoring Skill
1★ repoEngineer one new or updated AI Skill in this Skills repository from concrete use cases through canonical source, minimal resources, bilingual metadata, UI integration, activation contracts, validation, and cross-platform build inspection. Use when a maintainer explicitly wants a reusable Skill artifact, not for a one-off prompt, using an existing business Skill, empty plugin scaffolding, ordinary code changes, or silently creating multiple Skills. 在当前 Skills 仓库中,根据具体用例工程化创建或更新一个 AI Skill,覆盖 canonical 源、最少资源、双语元数据、UI 集成、activation 契约、验证和跨平台构建检查。维护者明确需要可复用 Skill 产物时使用;不用于一次性 Prompt、调用现有业务 Skill、只创建空插件、普通代码修改或未经确认批量创建多个 Skill。
clever-cc-plugins/cc-content/plugins/cc-content/skills/cc-content-research-prompt Skill
1★ repoUse this skill when the owner wants a ready-to-paste research prompt for a "deep research" AI tool (Claude, ChatGPT, Gemini, Perplexity, DeepSeek, or similar) to investigate a topic before writing content. Invoke when the user says "give me a research prompt for X", "write me a deep research prompt", "I need to research this before drafting", or "generate a prompt I can run in ChatGPT/Perplexity for research". This produces only the prompt text — it does not run research itself, call any external tool, or save results anywhere.
ArthurZakirov/AgentDesk/skills/manage-caffeinate Skill
1★ repoTurn macOS caffeinate sleep prevention on or off, check its status, or explain the launchd-backed setup. Use when the user says to enable, disable, start, stop, toggle, inspect, or troubleshoot caffeinate / coffee Nate / keep-awake behavior for local terminal, Codex, Claude Code, or other agent workflows.
hirokisakabe/issuekit/skills/worktree-start Skill
1★ repoAgent Skills for issue-driven development.
ronniepinnell/casper/collection/meta-and-tooling/trigger-agents Skill
1★ repoAI agent patterns with Trigger.dev — orchestration, parallelization, routing, evaluator-optimizer, and human-in-the-loop. Use when building LLM-powered factory tasks that need parallel workers, approval gates, tool calling, or multi-step agent workflows.
ajbarea/techne/plugins/techne/skills/deslop Skill
1★ repoScan the codebase for AI-generated slop in comments and docstrings — temporal markers, self-referential AI framing, narrative WHAT-comments, marketing padding — and propose tightened rewrites, routing claim-bearing docstrings that need a code-grounded rewrite to its sibling /techne:reslop. Use when the user wants to audit pending changes or the whole codebase for verbose, low-value commentary left by other assistants (Copilot, Gemini, GPT, etc.).
aimasteracc/harness-kit/skills/subagent-brief Skill
no license1★ repoWrite a sub-agent brief that survives the messaging asymmetry — explicit inputs, explicit outputs, and a degraded-mode paragraph so the sub-agent completes instead of silently stalling. Use when the user says "brief a sub-agent", "spawn an agent to…", "subagent brief", or is designing a multi-agent / swarm step.