Context & AI engineering
25,610 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
aoli0919/prompt-debugging-skills/skills/system-prompt-review Skill
0★ repoReview system prompts for ambiguity, conflicts, missing outputs, and unsafe delegation.
swd3k/skills/agent-skills/ui/design-first-ui-prompting Skill
0★ repoTurn vague UI ideas into tight design-first specs for consistent generation. Use when prompting for screens, dashboards, marketing sections, or desktop chrome; covers hierarchy, constraints, variants, and negative prompts.
swd3k/skills/agent-skills/workflows/agent-skill-authoring Skill
0★ repoAuthor portable agent skills (SKILL.md) compatible with Codex, Claude, Cursor, and Grok. Use when creating or refining skills in this repo.
arclabshq/arc-labs-studio-team/skills/swarm Skill
0★ repoDivides a broad problem into bounded expert tracks and merges their evidence into one decision or deliverable. Use when independent research, review, design, or implementation tracks can run in parallel or as sequential specialist lenses.
msilich/openshift-skill/.agents/skills/openshift-mcp Skill
0★ repoConfigure, operate, and troubleshoot OpenShift through openshift/openshift-mcp-server with MCP-first execution and controlled oc fallback. Use for read-only OpenCode or DevSpaces bootstrap, CA-aware kubeconfig creation, MCP configuration, cluster inspection, incident diagnosis, workload or administrative Day-2 changes, target-context and RBAC verification, rollout or recovery work where namespaces, secrets, credentials, or destructive actions must be handled safely.
MyAiFreedomSystems/incredagents/hooks-guide Skill
no license0★ repoComprehensive guide to agent lifecycle hooks across platforms. Covers what hooks are, when they fire, safety rules, universal patterns (pre-dispatch validation, post-converge logging, compaction survival), platform-specific adapters for Hermes, Claude Code, Codex, Cursor, OpenCode, and others, and registration/installation instructions per platform. Use when designing governance enforcement, pre-flight checks, audit trails, or any hook-based automation.
MyAiFreedomSystems/incredagents/provision-agent Skill
no license0★ repoProvision a new AI agent with identity overlays, scoped skills, tool constraints, handler profile, and memory structure. Creates SOUL.md, TOOLS.md, MEMORY.md, and USER.md files on top of the project scaffold. Extends provision-project with agent-specific identity. Use when creating a named agent, standing up an agent identity, or binding skills and tools to a new agent instance.
MyAiFreedomSystems/incredagents/provision-project Skill
no license0★ repoProvision a project folder for AI agent work with governance files, directory skeleton, session ledger, and platform-specific agent overlays. Produces a fully scaffolded workspace that agents on any platform (Hermes, Claude Code, Codex, Cursor, OpenCode, etc.) can use immediately. Use when creating a new project, initializing a workspace, or standing up a fresh agent-ready folder.
MyAiFreedomSystems/incredagents/provision-team Skill
no license0★ repoProvision a new agent team with identity, composition, governance, and orchestration protocol. Creates TEAM_IDENTITY.md, TEAM_COMPOSITION.md, TEAM_GOVERNANCE.md, and registers the team in the governance nucleus. Use when assembling multiple agents into a coordinated team for a shared purpose — code review squads, build teams, research panels, or any multi-agent workflow.
lhbsaa/apex-discovery/skills/arbor Skill
0★ repoAutonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/autoskill Skill
0★ repoObserve the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/bgpt-paper-search Skill
0★ repoSearch scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/dispatching-parallel-agents Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
lhbsaa/apex-discovery/skills/pi-agent Skill
0★ repoBuild with and use Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings, creating Pi skills/extensions/packages/themes/prompt templates, embedding Pi through the SDK, integrating over RPC or JSON event streams, parsing sessions, developing custom Pi providers and TUI components, or using ecosystem packages such as pi-subagents (delegation/orchestration), pi-mcp-adapter (MCP servers), pi-interview (interactive forms), and pi-web-access (web search, fetching, video understanding).
The same file is in 3 other repositories
lhbsaa/apex-discovery/skills/subagent-driven-development Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
lhbsaa/apex-discovery/skills/tamarind Skill
0★ repoAccess a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. Tamarind bundles popular open-source models for structure prediction (AlphaFold, Boltz, Chai, ESMFold), protein, binder, and de novo design (RFdiffusion, ProteinMPNN, BoltzGen), antibody and nanobody design and developability, protein-ligand docking (DiffDock, Autodock Vina), binding-affinity prediction, MSA generation, and molecular dynamics. Use when the user mentions Tamarind or tamarind.bio, wants to run any of these open-source tools in the cloud, references app.tamarind.bio/api or the x-api-key header, or needs to submit batches of sequences for structural or biophysical characterization.
The same file is in 3 other repositories
menot-you/n-soul/skills/handoff Skill
0★ repoPersist exact continuation state so a cold engineer can resume safely without relying on chat history or reconstructing hidden decisions.
blakebauman/skillist-validator/skills/skill-validation Skill
0★ repoValidate agent skills against the Agent Skills specification (agentskills.io) — SKILL.md frontmatter, name and description rules, character limits, directory layout, bundled file references, and progressive disclosure. Use when the user asks to validate, lint, check, or verify a skill or a directory of skills; when they ask whether a SKILL.md is spec-compliant or why a skill fails to load; before publishing or packaging skills; or when they are debugging a skill that an agent will not pick up. Applies to skills for any client — Claude Code, Cursor, Codex CLI, Gemini CLI — not just Claude.
rolson24/cad-sim-agent-skills/skills/cad-sim-project-intake Skill
0★ repoStep 1 of the reset CAD workflow. Use first when the user gives a rough product, CAD part, robotics, electromechanical, fixture, simulation, optimization, or software-connected hardware prompt and Codex must grill the user before authoring. Produces the run root, source boundary when needed, open questions, captured answers, autonomy-after-grill contract, maturity/analysis/external-capability envelopes, prototype handoff intent, primary_outcome_surface intent, project_brief.yaml review_contract, next_action_worthiness, stage_frontier, design/option-space coverage, and exemplar_calibrated_handoff intent, and review_rubric. Also use in narrow surface re-intake mode when a review loop cannot infer audience, depth, decision target, or tradeoff priority for an existing primary outcome surface. After initial intake, use cad-sim-design-orchestrator; do not revise an existing annotation_view except to update intake/review-contract state during surface re-intake.
rolson24/cad-sim-agent-skills/skills/cad-sim-quality-harness Skill
0★ repoInternal reset CAD helper for bootstrapping and auditing project-specific Quality Harness rows before serious CAD, simulation, optimization, prototype handoff, A+ review, or repeated fuzzy complaints. Use when intake, design orchestration, review/revise, reviewer lenses, or tooling scout need a small falsifiable evidence contract in quality/quality_harness.yaml, quality_harness_results.json, quality_harness_trace.md, or a Quality Reset seed.
rolson24/cad-sim-agent-skills/skills/cad-sim-rehearsal-agent Skill
0★ repoAct as a bounded smoke rehearsal operator for the reset experiment. Use for fresh-folder bootstrap rehearsals, global skill availability checks, front-door CAD intake, user grill answer, brief, CAD handoff, build/use readiness, autonomy-envelope or maturity-ladder behavior, reviewer-thread topology checks, and review-revise flow without launching solvers, optimization, old-project workers, or migration.
TyrantLucifer/awesome-skills/skills/polish-tyrant-tech-writing Skill
0★ repo精修、润色、校正 TyrantLucifer 的中文技术文章,尤其适用于 Agent/LLM 生成的博客草稿、源码解析、架构分析、教程、开源项目体验和技术复盘。去除模板化 AI 腔,同时复现 tyrantlucifer.com 历史原创文章中稳定的个人表达:从真实问题或实践切入,跟随代码和现象逐步推演,穿插克制的第一人称判断与轻微吐槽,并诚实说明局限。保留并校验代码、命令、API、产品名、版本、数字、链接、引用和不确定性;也可仅审阅 AI 痕迹、技术表达和文风偏差而不改写。
wildcard/codex-to-claude-coordinator/skills/coordination-conformance Skill
0★ repoTest and compare agent-harness coordination capabilities with privacy-safe evidence. Use to record, redact, validate, and summarize whether Codex, Claude, Cursor, Copilot, Goose, OpenHands, or another coordinator or worker can start, steer, inspect, stop, review, preserve scope, expose usage, or produce a trustworthy handoff.
sorinLupaIonut/digital-fte/.claude/skills/mcp-builder Skill
no license0★ repoGuide 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).
The same file is in 42 other repositories
sorinLupaIonut/digital-fte/.claude/skills/neon-postgres Skill
no license0★ repoGuides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK. Use when users ask about "Neon setup", "connect to Neon", "Neon project", "DATABASE_URL", "serverless Postgres", "Neon CLI", "neon", "Neon MCP", "Neon Auth", "@neondatabase/serverless", "@neondatabase/neon-js", "scale to zero", "Neon autoscaling", "Neon read replica", or "Neon connection pooling".
sorinLupaIonut/digital-fte/.claude/skills/skill-creator Skill
no license0★ 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 md and folder standards
ProstDev/skills/plugins/general/skills/claude-md-and-folder-standards Skill
0★ repoStandards for editing any CLAUDE.md (each repo's root CLAUDE.md included — it lives outside .claude/ but these rules still govern it) and any file under .claude/ (skills, settings.json, hooks). Invoke before modifying any of them.
euphoriawolf/ai-assisted-app-kit/skills/new-app/templates/project-kit/build-phase Skill
0★ repoWork the {{APP_NAME}} build ledger in TODO.md — pick the next phase/task, implement it end-to-end, keep CLAUDE.md + AGENTS.md current, and check items off. Use when building the next piece of {{APP_NAME}} or asking "what's next".
martonpaulo/skills/handoff Skill
0★ repoWrite a compact durable handoff containing the exact context, decisions, modified files, verification, risks, and next action another agent or later session needs to continue safely.
martonpaulo/skills/setup-agent-docs Skill
0★ repoConfigure lightweight per-repository conventions for optional domain glossaries, ADRs, research notes, handoffs, and disposable prototypes. Use when the user directly requests these artifact paths or when setup-project delegates this step after establishing root guidance. Do not use for complete project setup, ordinary documentation edits, personal-skill configuration, trackers, tickets, labels, or backlog workflows.
martonpaulo/skills/setup-project Skill
0★ repoInitialize or align one of the owner's repositories with its durable project identity, Git and release policies, root AGENTS.md rules, CLAUDE.md alias, public documentation, licensing, ignore rules, GitHub metadata, and applicable CI or release foundations. Use only when the user explicitly asks to set up a new personal project or adopt this complete baseline in an existing repository; do not use for ordinary implementation, a single documentation edit, or artifact-path configuration alone.
martonpaulo/skills/skill-authoring Skill
0★ repoCreate, review, or simplify Agent Skills with precise triggers, focused workflows, explicit safety boundaries, useful completion criteria, valid frontmatter, and minimal unnecessary context.
VJDiPaola/skill-forge/api-prompt-optimizer Skill
0★ repoSystematic prompt optimization for image/video generation APIs (Runway, Midjourney, DALL-E, Flux, etc.). Trigger on: 'optimize this prompt', 'A/B test prompts', 'improve generation quality', 'prompt iteration', 'eval my prompts', 'systematic prompt comparison', or when scoring generation outputs is mentioned, comparing before/after results, or building a prompt testing pipeline.
VJDiPaola/skill-forge/behavior-spec-canvas Skill
0★ repoDefine the behavioral contract for an AI component using a Behavior Spec Canvas covering guardrails, tone, confidence thresholds, and edge cases. Trigger on "how should this behave," "what are the guardrails," "spec out this AI feature," "what should this AI always/never do," or when an eval framework exists and the behavioral rules come next. Based on the "No Vibes, Just Evals" methodology by Shankha Dey.
VJDiPaola/skill-forge/eval-framework Skill
0★ repoBuild an eval framework for an AI feature before writing code. Use when planning an AI component, defining test scenarios, or setting up evals. Trigger on "eval framework," "test scenarios," "edge cases for AI," "how do I know if this works," "what should I test," or when someone shares an AI feature idea without saying how they'd evaluate it. Based on the "No Vibes, Just Evals" methodology by Shankha Dey.
stella-dust/autoxeo-marketplace/skills/autoxeo-prompt-set Skill
0★ repoAI platform question-set design skill for brand, category, competitive, and purchase-intent GEO visibility testing.
gabros20/ai-skill/skills/ai Skill
0★ repoBuild model-powered behavior — model routing, context engineering, structured outputs, tools/MCP, agents, RAG, memory, evals, guardrails, and cost/observability — across chat, agent, RAG, batch, and multi-agent systems, any provider or language. Use to route a model, engineer context, build an agent or tool loop, add RAG or memory, write evals, or add guardrails. Not for system/threat design (→ architecture), serving or MCP hosting (→ backend), data pipelines (→ data), chat UI (→ frontend), independent QA (→ quality), deploy (→ operate), or deterministic workflows (→ automation).
seroneyemmanuel4-afk/fullstack-forge-skill/src/fullstack-forge/commands/forge-ai Skill
0★ repoAudit model boundaries, prompt injection, tool authority, data handling, output validation, evaluation, fallback, and cost. Use for llm, embedding, classifier, agent, retrieval, or generative-media features.
lubochka/xiigen-mvp-engine/.agents/skills/agent-output-format Skill
0★ repoEnforces that deliverables produced during web sessions (Codex.ai with Opus or Sonnet) are formatted for their STATED CONSUMER — typically Codex (Opus). Prevents the failure mode where deep analysis in a web session produces human-readable reports instead of agent-executable instructions. Must be invoked at the START of any web session that will produce plans, skills, or instructions for Codex.
lubochka/xiigen-mvp-engine/.agents/skills/pipeline Skill
0★ repoEnforces that deliverables produced during web sessions (claude.ai with Opus or Sonnet) are formatted for their STATED CONSUMER — typically Claude Code (Opus). Prevents the failure mode where deep analysis in a web session produces human-readable reports instead of agent-executable instructions. Must be invoked at the START of any web session that will produce plans, skills, or instructions for Claude Code.
lubochka/xiigen-mvp-engine/.claude/skills/universal/agent-output-format Skill
0★ repoSelf-building AI code generation engine that generates application flows instead of implementing them. AGPL-3.0.
sairam0424/MindForge/.agent/skills/kanban-orchestrator Skill
0★ repoDecomposition playbook + anti-temptation rules for an orchestrator profile routing work through Kanban. The "don't do the work yourself" rule and the basic lifecycle are auto-injected into every kanban worker's system prompt; this skill is the deeper playbook when you're specifically playing the orchestrator role.
sairam0424/MindForge/.agent/skills/kanban-worker Skill
0★ repoPitfalls, examples, and edge cases for Kanban workers. The lifecycle itself is auto-injected into every worker's system prompt as KANBAN_GUIDANCE (from agent/prompt_builder.py); this skill is what you load when you want deeper detail on specific scenarios.
sairam0424/MindForge/.agent/skills/llm-wiki Skill
0★ repoKarpathy's LLM Wiki: build/query interlinked markdown KB.
sairam0424/MindForge/.agent/skills/mindforge-neural-orchestrator Skill
0★ repoUse when starting any conversation - establishes how to find and use skills, requiring MindForge Skill tool invocation before ANY response including clarifying questions
Mindforge parallel mesh extended
sairam0424/MindForge/.agent/skills/mindforge-parallel-mesh_extended Skill
0★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
sairam0424/MindForge/.agent/skills/mindforge-swarm-execution Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
sairam0424/MindForge/.agent/skills/skill-authoring Skill
0★ repoAuthor in-repo SKILL.md: frontmatter, validator, structure.
sairam0424/MindForge/.agent/skills/subagent-driven-development Skill
0★ repoExecute plans via Agent subagents (2-stage review).
sairam0424/MindForge/.agent/skills/video-orchestrator Skill
0★ repoPlan, set up, and monitor a multi-agent video production pipeline backed by a Kanban pipeline. Use when the user wants to make ANY video — narrative film, product/marketing, music video, explainer, ASCII/terminal art, abstract/generative loop, comic, 3D, real-time/installation — and the work warrants decomposition into specialized profiles (writer, designer, animator, renderer, voice, editor, etc.) coordinated through a kanban board. Performs adaptive discovery to scope the brief, designs an appropriate team for the requested style, generates the setup script that creates agent profiles + initial kanban task, then helps monitor execution and intervene when tasks stall or fail. Routes scenes to whichever rendering / audio / design skill fits each beat (`ascii-video`, `manim-video`, `p5js`, `comfyui`, `touchdesigner-mcp`, `blender-mcp`, `pixel-art`, `baoyu-comic`, `claude-design`, `excalidraw`, `songsee`, `heartmula`, …) plus external APIs for TTS, image-gen, and image-to-video as needed.
sairam0424/MindForge/.mindforge/skills/agent-architecture-audit Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-evaluation-framework Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-introspection-debugging Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-loops Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-memory-design Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-orchestration-patterns Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/agent-tool-selection Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/ai-agent-deployment Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/autonomous-agent-harness Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.
sairam0424/MindForge/.mindforge/skills/context-engineering Skill
0★ repoMindForge: The Enterprise Agentic Framework for Claude Code & Antigravity. High-performance autonomous execution, wave-parallelism, and multi-tier governance for production-grade AI engineering.