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
sairam0424/MindForge/.mindforge/skills/delegation-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/embedding-systems 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/eval-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/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/.mindforge/skills/llm-cost-optimization 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/llm-orchestration 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/mcp-server-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/multi-llm-consult 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/prompt-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.
sairam0424/MindForge/.mindforge/skills/rag-architecture 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/skill-creator-meta 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/subagent-driven-development Skill
0★ repoExecute plans via Agent subagents (2-stage review).
Mindforge parallel mesh extended
sairam0424/MindForge/plugins/mindforge/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/plugins/mindforge/skills/mindforge-protocol Skill
0★ repoThe MindForge operating protocol — swarm orchestration, sharded memory, the adversarial decision loop, quality gates, and the session-start governance checklist. Use at the start of any MindForge session, or whenever coordinating multi-agent work, planning/executing phases, or enforcing security/verification gates.
sairam0424/MindForge/plugins/mindforge/skills/mindforge-swarm-execution Skill
0★ repoUse when executing implementation plans with independent tasks in the current session
navelphotochemistry3605/VRCUdonSkills-for-Codex/skills/vrc-udon-unity-mcp Skill
0★ repoUnity 2022.3.22f1 前提の VRChat UdonSharp プロジェクトで CoplayDev の unity-mcp を使うときに使う。Scene / Prefab / Builder / Editor 状態の読解や補助操作を Codex から行いたい場合に、Unity MCP を Runtime 依存ではなく Editor 支援として扱うための Skill。
rdzehtsiar/agent-skill-auditor/fixtures/compatibility/host/copilot-path-layout Skill
0★ repoPortable root package outside Copilot preferred paths.
rdzehtsiar/agent-skill-auditor/fixtures/compatibility/matrix/.claude/skills/claude-pass Skill
0★ repoClaude preferred path fixture.
rdzehtsiar/agent-skill-auditor/fixtures/compatibility/matrix/.github/skills/copilot-pass Skill
0★ repoCopilot preferred path fixture.
rdzehtsiar/agent-skill-auditor/fixtures/security/prompt-injection Skill
0★ repoFixture with explicit prompt-injection-like text.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/nested-paths/.agents/skills/agent-style Skill
0★ repoFixture under the .agents skill path convention.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/nested-paths/.claude/skills/claude-style Skill
0★ repoFixture under the .claude skill path convention.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.agents/skills/artifacts Skill
0★ repoAgent path representative artifact package.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.agents/skills/broken-reference Skill
0★ repoAgent path representative broken reference.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.agents/skills/missing-description Skill
0★ repoOffline security and compatibility auditor for AI agent skills
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.agents/skills/triage Skill
0★ repoAgent path representative skill.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.claude/skills/planning Skill
0★ repoClaude path representative skill.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/.claude/skills/unknown-frontmatter Skill
0★ repoClaude path representative unknown metadata.
rdzehtsiar/agent-skill-auditor/fixtures/spec/phase1/representative-corpus/deep/products/alpha/.agents/skills/nested-agent Skill
0★ repoDeeply nested host-convention representative skill.
NDDev-it-com/rldyour-mimocode/.mimocode/skills/serena-memory-sync Skill
0★ repoИспользуй для sync Serena memories и MiMoCode MEMORY.md projection. EN: memory sync.
jpoindexter/wireframe-skills/skills/wireframe-handoff Skill
0★ repoUse when presenting wireframes to stakeholders, clients, or executives; when wireframes are ready for build and developers need a handoff; when a developer asks "what happens when..."; when annotating behavior, states, data sources, validation, or edge cases; when built screens drift from the wireframes during development; or when deciding what to spec in the wireframe versus leave to the build team. Also fires when preparing design alternatives for a sign-off meeting.
xiehuacheng/skills/skills/wiki/init-llm-wiki Skill
0★ repoInitialize and maintain an Obsidian-first, Google Cloud OKF 0.1–compatible Karpathy-style LLM Wiki for a given domain. Use when the user wants to build or maintain a Karpathy-style LLM wiki for a new domain.
asong56/skills/00-foundation/context-engineering Skill
0★ repoOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
asong56/skills/00-foundation/handoff Skill
0★ repoCompact the current conversation into a handoff document for another agent to pick up.
asong56/skills/00-foundation/session-state Skill
0★ repoCross-session state management: save/restore context checkpoints, manage SSOT decisions.md and patterns.md, and initialise each work session with memory + state. Use /context-save, /context-restore, /session.
asong56/skills/03-build/agents/MAF-orchestration Skill
0★ repoOrchestrate multi-agent coding tasks via Claude MAF — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
asong56/skills/03-build/agents/MPX-workflows Skill
0★ repoMulti-agent orchestration using MPX (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agen...
asong56/skills/03-build/agents/RFP-pipeline Skill
0★ repoRFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.
asong56/skills/03-build/agents/agentic-engineering Skill
0★ repoOperate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.
asong56/skills/03-build/agents/agentic-os Skill
0★ repoBuild persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
asong56/skills/03-build/agents/autonomous-agent-FRM Skill
0★ repoTransform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP...
asong56/skills/03-build/agents/autonomous-loops Skill
0★ repoPatterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. Includes quality gates, evals, recovery controls, and loop selection flow (sequential/continuous-pr/rfc-dag/infinite). Merged with former continuous-agent-loop skill.
asong56/skills/03-build/agents/cost-aware-llm-pipeline Skill
0★ repoCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
asong56/skills/03-build/agents/team-orchestration Skill
0★ repoTwo-phase team agent workflow: (1) Team Builder — interactively browse and compose agent teams from your agent library, dispatch them in parallel, and synthesize results; (2) Team Agent Orchestration — manage running squads with work items, agent Kanban state, branch isolation, merge gates, and control pane visibility. Incorporates former team-builder and team-agent-orchestration.
asong56/skills/03-build/orchestration/master-orchestrator Skill
0★ repoUnified engineering orchestrator. Route any build intent — bootstrapping an MVP, adding a feature, changing behavior, fixing a defect, or refining structure — to the correct internal Mode, then drive the shared Research → Plan → TDD → Deliver pipeline to a gated commit. Incorporates former: orch-build-mvp, orch-add-feature, orch-change-feature, orch-fix-defect, orch-refine-code.
asong56/skills/03-build/universal/FRM-loop Skill
0★ repoLong-running task loop using /loop (Claude Code dynamic mode) and ScheduleWakeup to re-enter with fresh context on each wake-up. Internally invokes FRM-work through Agent. Trigger: long-running, loop, wake-up, autonomous. Do NOT load for: one-...
asong56/skills/03-build/universal/benchmark-optimization-loop Skill
0★ repoUse when the user asks to make something faster, try many variants, run recursive optimization, benchmark latency/throughput/cost, or choose the best implementation by repeated measured tests.
asong56/skills/03-build/universal/parallel-agents Skill
0★ repoParallel agent execution: dispatch independent tasks to isolated subagents, with two-stage review (spec then quality). Use for multi-task plans with parallel workstreams.
asong56/skills/03-build/universal/regex-vs-llm-structured-text Skill
0★ repoDecision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
asong56/skills/04-assure/agent-architecture-audit Skill
0★ repoFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-fi... Use when auditing an AGENT APPLICATION's overall design and stack. Do NOT use for: comparing agent tools (→ agent-eval), debugging a single agent run (→ agent-introspection-debugging), or rating completed task output (→ agent-self-evaluation).
asong56/skills/04-assure/agent-eval Skill
0★ repoHead-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when COMPARING multiple agent tools. Do NOT use for: evaluating one agent's task output (→ agent-self-evaluation), diagnosing why an agent failed (→ agent-introspection-debugging), or auditing an agent-based application architecture (→ agent-architecture-audit).
asong56/skills/04-assure/agent-introspection-debugging Skill
0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent produced wrong, incomplete, or hallucinated output in a SINGLE run. Do NOT use for: comparing multiple agents (→ agent-eval), auditing the overall architecture of an agent app (→ agent-architecture-audit), or rating output quality after success (→ agent-self-evaluation).
asong56/skills/04-assure/agent-self-evaluation Skill
0★ repoUse after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvemen... Do NOT use for: comparing multiple agent tools (→ agent-eval), debugging why an agent failed (→ agent-introspection-debugging), or auditing agent application architecture (→ agent-architecture-audit).
asong56/skills/04-assure/benchmark Skill
0★ repoUse this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
asong56/skills/04-assure/codehealth-mcp Skill
0★ repoReal-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit/PR.
asong56/skills/04-assure/eval-FRM Skill
0★ repoFormal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
asong56/skills/04-assure/llm-trading-agent-security Skill
0★ repoSecurity patterns for autonomous trading agents with wallet or transaction authority. Covers prompt injection, spend limits, pre-send simulation, circuit breakers, MEV protection, and key handling.
asong56/skills/04-assure/prompt-optimizer Skill
0★ repoAnalyze and rewrite a draft prompt to maximize effectiveness within the SKC skill ecosystem. Triggers: 'optimize this prompt', 'improve my prompt', 'help me write a better prompt for...', 'how should I use SKC for...', or when the user pastes a draft prompt and asks for feedback. Advisory only — outputs an optimized prompt, never executes the underlying task.
asong56/skills/04-assure/security-scan Skill
0★ repoScan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
asong56/skills/07-share/vibe-trading Skill
0★ repoProfessional finance research toolkit — backtesting (8 engines + benchmark comparison panel), factor analysis, Alpha Zoo (460 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 87 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract → backtest → render) across 20 market-data sources (tushare, yfinance, okx, akshare, baostock, tencent, mootdx, ccxt, futu, local, eastmoney, sina, stooq, yahoo, india_broker, qveris, plus optional-key finnhub/alphavantage/tiingo/fmp).