A native MeTTa decision gate that ranks agent actions against explicit goals, policy norms, and graded evidence.

Agent skill for Locus MCP, free tools, and x402 property-context workflows

Codex 设计类 Skill 自动编排与一键安装套件

A debugging reflex for AI assistants: when a third-party tool breaks, search the community before guessing. The bug is usually external state that moved, not your code.

Agent Skills for Wassenger — automate WhatsApp Business (official WABA) by chatting with Claude, Cursor, Codex or any Agent Skills client. 22 skills + the Wassenger MCP server.

Primevue skills for ai agents

THE definitive curated resource for gamification-agent-skills | GenCreator 6-Pillar CoE • Starlight Intelligence • Arcanea Creative Execution • Agentic Passive Income Systems

Team coding-standards plugins for Claude Code (Agent Skills marketplace) · 面向 Claude Code 的团队代码规范插件(技能 marketplace)

Claude Code skill/plugin that rewrites a raw question into a high-performing LLM prompt by auto-selecting research-backed prompt-engineering strategies.

Codex plugin for handing off near-full context threads to fresh continuation sessions

Practical agent skills for vibe coders: move fast, verify faster, ship cleaner.

A security skills pack for Claude Code, Cursor, Codex and Gemini CLI: secrets pre-flight, dependency audit, secret rotation, STRIDE threat modeling, secure code review, Dockerfile hardening and env hygiene.

Agent Kaizen skill for Claude Code & Codex: faithful, identifier-preserving reference for Tauri v2 development, tauri.conf.json, calling Rust/frontend, state management, resources & sidecar binaries, app icons, plugin & mobile development, debugging (VS Code/RustRover/Neovim), and testing (mocking, WebDriver). Not Tauri v1.

Model-agnostic Agent Skills covering the entire public Discogs API (api.discogs.com).

Local-first CLI to index and search your Claude Code, Codex, and Cursor chat history from one place. 100% offline, read-only.

Declarative event-fired triggers for agent skills — compile a triggers: frontmatter field in any SKILL.md into Vanta and Claude Code hooks.

My personal skills for agentic GitHub development workflows

apify-expert - Claude Code Agent Skill (target LLM: Claude). Part of the mr-bridge.com toolkit.

Turns a topic or a body of source material into a full, pedagogically-sound course or curriculum — learning objectives, module map, lessons, assessments aligned to objectives, and exports to LMS/SCORM/Markdown.

Governs API evolution across producer and consumers: detects breaking changes, blocks them at the gate, and orchestrates a versioned deprecation lifecycle nobody can short-circuit.

CLI to author, validate, and convert skills for the Nous Research Hermes Agent (SKILL.md) — lint, scaffold, and convert agentskills.io/Claude skills.

Hermes Agent skills

Agent skill for building conflict-free rowing regatta heat sheets

Claude/agent skill for checkpointing progress into Handoff.md and distilling sources into a cited, confidence-rated evidence log inside an agent-managed knowledge vault.

The Forge - an unbounded recursive multi-agent methodology (diverge -> adversarial critique -> verify -> handoff -> repeat). Vendor-neutral spec + Claude Code skill, installable via skills.sh.

Agent skill that helps coding agents build agent-ready software. By Ora.

Agent Skill for optimizing Apache Hive on MapReduce — 26 actionable best-practice rules covering storage, query, JOIN, data skew, and MR parameter tuning. Works with Cursor & Claude Code.

Manual-invoke orchestration gate: picks the lightest credible execution mode for a task (inline / few-subagents / dynamic-workflow / loop / hybrid / do-not-automate). Verdict + shape only.

Solana-first agent commerce and x402 skill for building paid APIs, paid MCP servers, and buyer agents that use Solana USDC/SPL/Token2022 payments. Use when implementing x402 on Solana, monetizing API endpoints or MCP tools, adding agent spend policies, pricing paid agent workflows, testing Solana devnet x402

English hub of method-neutral legal AI skills (verification core, content quality, EU law) - bundle model. Polish-jurisdiction skills live in awesome-matematic-skills-pl.

Project structure analysis and development logging for AI agents — project-onboard + project-docs

A stateful pricing & packaging system that goes from value-metric discovery through tier design, WTP testing, and a safe live price-migration plan.

Turn a fuzzy idea into a tight talk: narrative spine, scripted beats, speaker notes, rehearsal loop, and ruthless Q&A prep.

Claude Code skill: turn a fuzzy initiative into an RFC + ADRs + 3-point estimates + trade-off matrix + risk register + rollout/backout plan before any code. Staff-engineer planning discipline, gate-sequenced.

Claude Code skill: a principal-engineer architecture review board — C4 model, ADRs, adversarial review, and evolutionary-architecture fitness functions wired into CI to catch drift.

Design a resilient data ingestion/ETL pipeline from source to warehouse: contracts, idempotency, quality gates, lineage, backfill, and run-time observability.

Agent Kaizen skill for Claude Code & Codex: implementation-ready CLI/terminal UX guidance, argument & flag design, subcommands, help text, exit codes, stdout vs stderr, piping & JSON output, color, prompts, TTY/CI detection. Unix/POSIX and Windows/PowerShell aware. Covers argparse, click, typer, cobra, clap, commander, oclif.

Agent Kaizen skill for Claude Code & Codex: faithful, task-routed reference for Turso, Turso Database, libSQL & Turso Cloud: CLI, Platform API, SDKs (JS/TS, Python, Rust, Go, Java, +more), SQL reference, sync, vector search, embedded replicas, local development, AgentFS, and org/billing. Routes to 7 area sub-skills.

An Agent Skill that teaches your AI to diagnose and durably fix failing CI/CD pipelines. Built from Latchkey Learn.

32 agent skills for writing correct, portable, modern standard SQL (ISO/IEC 9075) — vendor-neutral, with per-feature portability across PostgreSQL, MySQL/MariaDB, SQLite, and more.

A collection of Agent Skills that teach AI coding agents the architecture and conventions for building NestJS backends.

A leaner alternative to GitHub Spec Kit

Claude Code skill: run NIST AI RMF (Govern/Map/Measure/Manage) on your LLM/ML feature — named failure modes, metric thresholds, an offline eval gate, and signed-off residual risk.

Agent skills for cleaning up codebase drift — stale comments, duplicate code, and inconsistent imports. Two-phase inventory-then-execute workflow for Claude Code, Cursor, and other AI coding agents.

Take a working LLM prototype to production: evals, guardrails, cost/latency, fallbacks, and an observability harness — phase-gated, not a one-shot prompt.

Agent Skills for WhatsTeam — automate WhatsApp Business (official API) by chatting with Claude, Cursor, Codex or any Agent Skills client. 23 skills + the WhatsTeam MCP.

Copy-only local media ingest for creators using a Codex skill

Ready-to-install Agent Skills for analyzing Intelligems experiments, segments, pricing, and reporting through MCP and API.

Agent skill: run system-upgrade meta-prompts on your own setup. Adapted from Daniel Miessler's Fable prompts.

Portable automation agent skills for the Starlight substrate — scheduling, pipelines, and fleet ops.

Coding Agent skill for scaffolding Solana Anchor projects, recovering missing Anchor CLI setup, and generating comprehensive runnable tests for Anchor programs.

Dameng DM8 database skill for migration, SQL/MyBatis adaptation, triage, operations, and performance tuning

Design a resilient web-scraping/automation system end-to-end: legality + strategy, anti-bot tactics, schema extraction, self-healing selectors, scheduling, and monitoring.

Turns 'it feels slow' into a measure-first, hypothesis-driven optimization campaign that refuses to change code without a profile and proves every win against a budget.

CLI to validate, scaffold, and install Agent Skills for Cursor and agentskills.io-compatible agents

YLF agent skills for disciplined coding tasks and persistent project instructions

Agent skills that make smaller coding-agent models reason like a frontier model: interrogate, decompose, compete candidates, adversarial self-review, verify, insight pass. Plus persistent codebase memory.

Agent skill for safe, evidence-driven coding-agent fleet orchestration

Agent skill for managing Fundus assets in Svelte mobile app projects

Turn real Agent failures into verifiable Skill boundaries and correct-layer fixes.