Context & AI engineering
25,729 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
diamitani/rostr-agent/optional-skills/mlops/tensorrt-llm Skill
1★ repoOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
The same file is in 1 other repository
diamitani/rostr-agent/optional-skills/mlops/torchtitan Skill
1★ repoProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
The same file is in 1 other repository
diamitani/rostr-agent/optional-skills/payments/mpp-agent Skill
1★ repoPay HTTP 402 APIs via Machine Payments Protocol (MPP).
diamitani/rostr-agent/optional-skills/software-development/subagent-driven-development Skill
1★ repoExecute plans via delegate_task subagents (2-stage review).
diamitani/rostr-agent/optional-skills/web-development/page-agent Skill
1★ repoEmbed alibaba/page-agent into your own web application — a pure-JavaScript in-page GUI agent that ships as a single <script> tag or npm package and lets end-users of your site drive the UI with natural language ("click login, fill username as John"). No Python, no headless browser, no extension required. Use this skill when the user is a web developer who wants to add an AI copilot to their SaaS / admin panel / B2B tool, make a legacy web app accessible via natural language, or evaluate page-agent against a local (Ollama) or cloud (Qwen / OpenAI / OpenRouter) LLM. NOT for server-side browser automation — point those users to Hermes' built-in browser tool instead.
The same file is in 1 other repository
diamitani/rostr-agent/skills/autonomous-ai-agents/claude-code Skill
1★ repoDelegate coding to Claude Code CLI (features, PRs).
The same file is in 2 other repositories
diamitani/rostr-agent/skills/autonomous-ai-agents/hermes-agent Skill
1★ repoConfigure, extend, or contribute to Hermes Agent.
diamitani/rostr-agent/skills/creative/claude-design Skill
1★ repoDesign one-off HTML artifacts (landing, deck, prototype).
The same file is in 1 other repository
diamitani/rostr-agent/skills/creative/touchdesigner-mcp Skill
1★ repoControl a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.
The same file is in 3 other repositories
diamitani/rostr-agent/skills/mlops/evaluation/lm-evaluation-harness Skill
1★ repolm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
The same file is in 3 other repositories
diamitani/rostr-agent/skills/research/llm-wiki Skill
1★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
The same file is in 1 other repository
diamitani/rostr-agent/skills/rostr-agent Skill
1★ repoBuild, extend, and deploy ROSTR Agent — the self-improving multi-agent framework with built-in PAL, NPAO, RAG DAL, and Rostr Hub.
diamitani/rostr-agent/skills/software-development/hermes-agent-skill-authoring Skill
1★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure, and writing-quality principles.
The same file is in 1 other repository
diamitani/rostr-agent/skills/software-development/rag-dal Skill
1★ repoRAG DAL (Retrieval-Augmented Generation Dynamic Acquisition Layer) — ROSTR's knowledge engine for autonomous multi-pass retrieval with three-tier source credibility scoring, gap detection, and confidence-based convergence.
kwhorne/elyra-skills/skills/context-engineering Skill
1★ repoWrite and maintain agent context files (AGENTS.md, CLAUDE.md, .cursorrules) that actually steer coding agents - commands, conventions, architecture, and boundaries, without bloat. Use when the user wants to set up or improve agent instructions for a project, asks why an agent keeps making the same mistake, or wants to make a codebase agent-friendly.
kwhorne/elyra-skills/skills/laravel-ai-features Skill
1★ repoBuild AI features in Laravel with the laravel/ai SDK - agent and tool design, structured output, conversation storage, queued AI work, testing with fakes, and cost control. Use when adding AI functionality to a Laravel app, designing agents or tools with laravel/ai, reviewing AI integration code, or wiring LLM calls into jobs and Livewire components.
kwhorne/elyra-skills/skills/llm-feature-design Skill
1★ repoDesign LLM-powered features that survive production - model choice, prompt structure, structured output, fallbacks, cost control, evals, and guardrails. Use when the user wants to add AI/LLM functionality to a product, asks about prompt design, RAG, agent features, handling model failures, or evaluating LLM output quality.
Auto skill build agent reliability loop
Arnie016/codex-prompt-templates/skills/auto-skill-build-agent-reliability-loop Skill
1★ repoDesign production agent reliability loops across traces, evals, guardrails, gateways, model budgets, and shadow tests. Use when shipping AI/agent workflows that need simulate/evaluate/protect/monitor/optimize structure, gateway policy, eval suites, guardrail rollout, or trace-to-regression feedback. Skip when the task only needs a local Codex run ledger; use `$agent-observability` instead.
Auto skill build agent run ledger dashboard
Arnie016/codex-prompt-templates/skills/auto-skill-build-agent-run-ledger-dashboard Skill
1★ repoAppend and summarize a lightweight local `.agent-runs/runs.jsonl` ledger (claudetop-inspired) so Codex sessions build durable observability over time. Use at the end of a significant task, after running tests, or when you want a quick “what did we do lately?” dashboard. Skip when the user only wants a one-off fix and does not care about tracking runs.
Auto skill build mcp conformance harness
Arnie016/codex-prompt-templates/skills/auto-skill-build-mcp-conformance-harness Skill
1★ repoDesign a repeatable MCP conformance, health-check, and tool-surface regression harness for local or CI use. Use when the user asks for MCP CI, protocol or OAuth conformance, server doctor checks, tool-surface diffing, JUnit/XML reports, or release gates for an MCP server. Requires an MCP endpoint or stdio launch command; skip when the task is only ad-hoc manual inspection where `$mcp-server-lab` is enough.
Auto skill build memsearch codex memory
Arnie016/codex-prompt-templates/skills/auto-skill-build-memsearch-codex-memory Skill
1★ repoUse memsearch as an on-demand semantic index for project markdown memory (search → expand → optional deep drill). Use when the user asks to recall past decisions, prior debugging, or “have we seen this before?” and a `.memsearch/memory/` store exists (or the user wants to set one up). Skip when the question is only about current code state (use Read/Grep) or when the user explicitly does not want semantic indexing / installs.
Auto skill safety external skill intake
Arnie016/codex-prompt-templates/skills/auto-skill-safety-external-skill-intake Skill
1★ repoSafely inspect and adapt third-party agent/Codex/Claude skill packs before installation. Use when importing external skills, prompt packs, slash commands, Skill Forge candidates, OpenDesign-style catalog stubs, or repos with SKILL.md files, commands, hooks, or installers. Triggers: import skills, install skill pack, evaluate third-party skill, prompt-pack safety, adapt Claude skill to Codex. Skip when authoring a new first-party skill from scratch; use `$skill-pack-factory` and `$automation-skill-forge`.
Auto skill safety mcp secret guard
Arnie016/codex-prompt-templates/skills/auto-skill-safety-mcp-secret-guard Skill
1★ repoPrevent secret leakage when adding or reviewing MCP server configs. Use when you see `mcpServers` JSON, `.env`, config snippets, tool docs, or logs that might contain API keys/tokens. Produces a redacted config + a short secret hygiene report.
Arnie016/codex-prompt-templates/skills/codex-prompt-template-builder Skill
1★ repoCreate, choose, adapt, and validate reusable Codex prompt templates that orchestrate skills, plugins, files, tools, and safety gates. Use when the user asks for massive prompts, prompt templates, reusable Codex prompts, plugin-orchestration prompts, marketplace prompt packs, or turning a prompt into a skill. Triggers: prompt template, reusable prompt, massive prompt, plugin stack prompt, prompt pack, turn this prompt into a skill. Skip when the user only needs a one-off short prompt with no reusable structure.
Arnie016/codex-prompt-templates/skills/experiment-loop-runner Skill
1★ repoRun a controlled THINK-EXECUTE-REFLECT loop for coding, research, or ML experiments. Use when the user wants iterative improvement, benchmark-driven changes, autonomous experiment planning, low-cost monitoring, or progress reports without uncontrolled agent drift. Skip production release loops that require gateway policy, trace-to-regression evals, guardrail rollout, budgets, or shadow/canary traffic; use `$auto-skill-build-agent-reliability-loop`.
Arnie016/codex-prompt-templates/skills/mcp-safety-review Skill
1★ repoReview MCP servers, agent tools, install scripts, or fresh GitHub repos for security and trust risk. Use when tools request shell/filesystem/network access, credentials, browser/session control, messaging accounts, package installs, or destructive write permissions. Skip pure CI/conformance harness design after trust is established; use `$auto-skill-build-mcp-conformance-harness`.
Arnie016/codex-prompt-templates/skills/mcp-server-lab Skill
1★ repoInspect, test, debug, or integrate MCP servers for Codex workflows. Use for MCPJam, MCP Inspector, stdio/HTTP MCP configs, tools/resources/prompts, Apps SDK widgets, OAuth checks, conformance, evals, or creating a local MCP integration plan. Skip when the task is specifically to design repeatable CI conformance gates or release diffs; use `$auto-skill-build-mcp-conformance-harness` instead.
Arnie016/codex-prompt-templates/skills/model-cost-router Skill
1★ repoDecide when to use cheaper, local, or frontier models and how to measure cost tradeoffs. Use for token limits, model routing, cost-conscious Codex work, DeepSeek/Claude/OpenAI comparisons, prompt caching, or agent workflow economics. Skip when cost routing is enforced by a production gateway, budget policy, fallback policy, or live alerting; use `$auto-skill-build-agent-reliability-loop`. Avoid unverifiable savings claims.
Arnie016/codex-prompt-templates/skills/openapi-to-mcp-skill Skill
1★ repoConvert OpenAPI/Swagger APIs into Codex-friendly MCP/tool workflows and generated skills. Use when the user wants to expose an API to agents, create a skill from API docs, use toolcast-style conversion, or design safe API tool schemas. Triggers: OpenAPI to MCP, Swagger to tools, API tool plan, generate MCP server from API spec. Skip when there is no stable spec or the user only needs one ad-hoc HTTP request.
brenbuilds1/skills/skills/memory-audit Skill
1★ repoFact-check an agent's persistent memory against the repo it describes. Use when an agent acts on outdated notes, when inheriting a project with existing CLAUDE.md / AGENTS.md / rules files, after a large refactor, or periodically on any long-lived project. Inventories every memory and instruction file the agent loads, splits them into atomic claims, verifies each claim against the current codebase and git history, and reports a per-line verdict table (confirmed, stale, wrong, contradiction, preference) with a receipt for every verdict. Reports only; never edits or deletes memory.
brenbuilds1/skills/skills/skill-auditor Skill
1★ repoAudit a third-party agent skill (Claude Code / Codex / Gemini CLI SKILL.md packages) before you install it. Use when asked to audit, vet, review, or security-check a skill, plugin, or marketplace package, or before installing one from GitHub or a marketplace. Clones the package read-only, runs supply-chain greps for fetch-and-execute, credential access, hidden code, network calls, and broad permissions, then reports findings with exact file:line and an honest severity for each. Does not install anything.
designgrappler/agent-os/claude/skills/create-agent Skill
1★ repoInteractively scaffolds a new agent definition file at .claude/agents/<name>.md
designgrappler/agent-os/claude/skills/install-agent-scaffold Skill
1★ repoBootstraps a new project with the Agent OS structure.
designgrappler/agent-os/claude/skills/orchestrator Skill
1★ repoBase orchestrator behavior for Agent OS — triage incoming tasks and route to the right execution path. Auto-loaded at session start. Never executes directly on source files.
designgrappler/agent-os/claude/skills/submit-agent-os-feedback Skill
1★ repoFile a structured issue against the designgrappler/agent-os public mirror. Use when the user says "file feedback", "report an Agent OS issue", "this Agent OS skill is broken", or wants to report a bug or improvement in Agent OS.
designgrappler/agent-os/claude/skills/update-agent-os Skill
1★ repoSynchronizes your local `~/.claude/skills/`, `~/.claude/agents/`, and `~/.claude/blueprints/` installation against the canonical Agent OS library.
designgrappler/agent-os/skills/add-specialist Skill
1★ repoAdd a new specialist agent to an existing team — define their role scope, owned paths, and operating rules, then register them in AGENTIC.md.
designgrappler/agent-os/skills/index-memory Skill
1★ repoThe "Long-Term Knowledge" specialist that curates the persistent memory (KIs) of the project.
designgrappler/agent-os/skills/install-agent-scaffold Skill
1★ repoScaffold the full Agent OS structure for a new project. Drops a setup file the user fills in — no files are generated until it's complete.
designgrappler/agent-os/skills/optimize-handoff Skill
1★ repoThe "Intent Link" that ensures seamless transition of strategy and context between specialized agents via a structured Handoff Bridge.
eliransu/digital-brain/skills/wiki Skill
1★ repoClaude + Obsidian knowledge companion. Sets up a persistent wiki vault, scaffolds structure from a one-sentence description, and routes to specialized sub-skills. Use for setup, scaffolding, cross-project referencing, and hot cache management. Triggers on: "set up wiki", "scaffold vault", "create knowledge base", "/digital-brain:wiki", "wiki setup", "obsidian vault", "knowledge base", "second brain setup", "running notetaker", "persistent memory", "llm wiki".
MarcoAntolini/cursor-sync/agents/skills/frontend/design-taste/frontend/gpt-taste Skill
no license1★ repoOpt-in only — invoke by name for Awwwards-style GSAP-heavy layouts. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.
MarcoAntolini/cursor-sync/agents/skills/mattpocock/productivity/handoff Skill
no license1★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 11 other repositories
MarcoAntolini/cursor-sync/cursor-skills/multi-agent-runner Skill
no license1★ repoRun a manually-invoked workflow where multiple agents, optionally with user-specified models, attempt the same task and compare results. Use only when the user explicitly invokes this skill or asks to run a task with N models, best-of-N agents, multiple agent attempts, parallel proposals, competing implementations, or multi-agent task runs.
paulnsorensen/skillz-that-grillz/skills/copilot Skill
1★ repoUse when the user says "copilot review", "review with copilot", "delegate to copilot", "have copilot fix this", "copilot agent task", "set up copilot", "generate copilot instructions", "bootstrap copilot for this repo", or invokes `/copilot`. Three modes: `review` (run a code review on a PR and route fixes to Copilot via inline `@copilot fix this` comments), `delegate` (create a `gh agent-task`, poll until the coding agent opens a PR, optionally hand off to review), and `setup` (one-time bootstrap that writes `.github/copilot-instructions.md` and the per-role `.github/instructions/*.instructions.md` files). `review` and `delegate` are routine; `setup` is a one-time repo bootstrap loaded on demand from `references/setup.md` only when the user explicitly asks. Do NOT use for plain GitHub PR work — that is `/gh`'s job.
Github copilot personal instructions
paulnsorensen/skillz-that-grillz/skills/github-copilot-personal-instructions Skill
1★ repoAdd or audit GitHub Copilot **personal** custom instructions — the per-user prompt configured at github.com/copilot that applies to every Copilot Chat conversation that account has on github.com. Covers where to set them, what they do and don't apply to (github.com Chat only — not IDE, not mobile, not coding agent), how they merge with repository and organization instructions, and verification. Use when the user says "set personal Copilot instructions", "configure my Copilot", "Copilot keeps responding in the wrong language", "make Copilot use my preferred tone", "personal Copilot prompt", "user-level Copilot config", "Copilot is ignoring my preferences", or invokes /github-copilot-personal-instructions. Do NOT use for repository-scoped instructions — that is /github-copilot-repo-instructions.
Github copilot repo instructions
paulnsorensen/skillz-that-grillz/skills/github-copilot-repo-instructions Skill
1★ repoAdd, audit, or fix GitHub Copilot repository custom instructions — `.github/copilot-instructions.md` (repo-wide) and `.github/instructions/*.instructions.md` (path-specific) — so Copilot Chat, Copilot code review, and the Copilot coding agent all pick up project-wide guidance. Also covers `AGENTS.md`, `CLAUDE.md`, and `GEMINI.md` as alternate agent instruction files. Use when the user says "add Copilot instructions", "set up copilot-instructions.md", "audit our Copilot config", "make Copilot follow our conventions", "configure Copilot code review", "add path-specific Copilot rules", "applyTo glob", "excludeAgent", "Copilot is ignoring our guidance", or invokes /github-copilot-repo-instructions. Do NOT use for personal (per-user) Copilot instructions — that is /github-copilot-personal-instructions. Do NOT use for opinionated generation aligned with this project's opinionated engineering principles — that is the setup mode of the multi-mode Copilot driver, `/copilot setup` (if installed).
paulnsorensen/skillz-that-grillz/skills/respond Skill
1★ repoTriage PR review comments by confidence score and act — fix the high-scoring ones, push back on the low-scoring ones, and ask about the borderline. Handles both inline review threads (anchored to diff lines) and PR-level review body comments (summaries submitted with reviews, like Age tables or Copilot overviews). First checks the PR's build and merge state and fixes those before processing comments. Use when the user says "respond to PR comments", "handle review feedback", "address PR reviews", "fix the build", "fix CI", "fix merge conflicts", or invokes /respond with a PR number. Also trigger when the user mentions a specific PR and wants to deal with reviewer suggestions — Copilot, human, or bot. Every reply this skill posts ends with an "agent on behalf of;" attribution line so reviewers can tell the comment came from an agent on behalf of the human, not the human directly. Do NOT use to generate a new review — that is /copilot-review's job.
paulnsorensen/skillz-that-grillz/skills/serena-config Skill
1★ repoConfigure the Serena MCP server — its global defaults and a repo's per-project settings. Use when the user says "configure serena", "set up serena for this repo", "serena project config", "serena global config", "tune serena for this codebase", "edit serena_config.yml", "edit project.yml", "monorepo serena", "serena picked the wrong language", "serena is indexing vendor/node_modules", "make serena read-only here", "serena contexts and modes", "what context for claude-code", "disable serena memory/onboarding", "point serena at my installed language server", "ls_specific_settings", "ls_path", "SERENA_HOME", or "move the .serena folder". Routes per-repo `.serena/project.yml` questions to `references/project-config.md` and machine-wide `~/.serena/serena_config.yml` (settings, contexts, modes, language-server tuning) to `references/global-config.md`. Do NOT use for general "use serena to find / edit X" routing — that is an MCP-routing concern, not configuration.
masheev/skills/skills/masheev-mcp Skill
no license1★ repoUse when connecting Claude Code, Cursor, Copilot, or other AI coding tools to the Masheev API via MCP (Model Context Protocol). Covers installing the @masheev/mcp server, configuring authentication, and using the 4 available tools: list_api_endpoints, get_api_endpoint_schema, execute_api_endpoint, and get_api_categories. Use this skill when someone asks to "connect Masheev to Claude", "set up MCP for Masheev", or wants to manage Masheev from their AI coding environment.
Agentic workflow guard auditor
guorunjie/agentic-workflow-guard/.gemini/skills/agentic-workflow-guard-auditor Skill
1★ repoUse before granting AI automation write access, reviewing agentic GitHub Actions, Bitbucket Pipelines, GitLab CI, Travis CI, Drone CI, TeamCity, Harness CI/CD, Tekton Pipelines, Argo Workflows, AWS CodeBuild, Google Cloud Build, CircleCI, Azure Pipelines, Jenkins, Buildkite, auditing n8n, Dify, Flowise, Langflow, Node-RED, Make, Pipedream, Airflow, browser automation, or checking MCP tool configs for prompt-injection and side-effect risks.
Agentic workflow guard auditor
guorunjie/agentic-workflow-guard/.hermes/skills/agentic-workflow-guard-auditor Skill
1★ repoUse before granting AI automation write access, reviewing agentic GitHub Actions, Bitbucket Pipelines, GitLab CI, Travis CI, Drone CI, TeamCity, Harness CI/CD, Tekton Pipelines, Argo Workflows, AWS CodeBuild, Google Cloud Build, CircleCI, Azure Pipelines, Jenkins, Buildkite, auditing n8n, Dify, Flowise, Langflow, Node-RED, Make, Pipedream, Airflow, browser automation, or checking MCP tool configs for prompt-injection and side-effect risks.
Agentic workflow guard auditor
guorunjie/agentic-workflow-guard/.openclaw/skills/agentic-workflow-guard-auditor Skill
1★ repoUse before granting AI automation write access, reviewing agentic GitHub Actions, Bitbucket Pipelines, GitLab CI, Travis CI, Drone CI, TeamCity, Harness CI/CD, Tekton Pipelines, Argo Workflows, AWS CodeBuild, Google Cloud Build, CircleCI, Azure Pipelines, Jenkins, Buildkite, auditing n8n, Dify, Flowise, Langflow, Node-RED, Make, Pipedream, Airflow, browser automation, or checking MCP tool configs for prompt-injection and side-effect risks.
almasumdev/awesome-mobile-performance-agent-skills/.github/skills/memory/memory-profiling Skill
no license1★ repoCapture and analyze heap dumps on Android (Android Studio Profiler, LeakCanary) and iOS (Instruments Allocations/Leaks). Use when memory-related crashes or growth are suspected.
zoidbergclawd/coherence/skills/manual-compaction-reset Skill
1★ repoUse when context is long, automatic compaction is likely, a session resumes after time away, direction changes, or the agent appears to be carrying stale assumptions, to perform a hard context reset by writing and reloading curated project context instead of relying on accumulated chat history.
taleshagn-horushub/thoth/skills/llm-council Skill
1★ repoRun any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
The same file is in 2 other repositories
endalk200/skills/skills/handoff Skill
no license1★ repoCompact the current conversation into a handoff document for another agent to pick up.
The same file is in 11 other repositories
fmind/agent-evolutions/skills/run-agent-evolution Skill
1★ repoRun phase of an agent evolution — plan a batch of up to `budget.parallel` variants, dispatch sub-agents in parallel to materialize and evaluate them, learn from results, repeat until budget / wall-clock / plateau. Writes `winner` on a clean stop. Requires an evolution captured via `/new-agent-evolution`; `/apply-agent-evolution` lands the winner afterward.
MustaphaSteph/agent-bus-plugins/skills/agent-bus-cli Skill
1★ repoUse when running or explaining agent-bus CLI commands, dashboards, setup checks, exact message fetches, team chat, Kanban, web cockpit, or manual MCP configuration.
MustaphaSteph/agent-bus-plugins/skills/agent-bus-coordinator Skill
1★ repoUse when this session should act as the project manager/coordinator for an agent-bus team: create a team, recruit helper sessions, delegate work, keep the board honest, and produce final reports.