agentsclimarketplace

Engineering

98,234 rows, by stacks then stars

  • Backend design

    itssungho17/ssdam/templetes/backend-design Skill

    no license0★ repo

    Backend-specialised design skill in the SSDAM pipeline. Reads architecture-design (and optionally schema-design) to produce a DDD-structured backend specification per domain. Mandatory components per domain are domain/entity, domain/facade, api/controller, and service/store. All other sub-layers (vo, event, exception, shared, request, response, mapper, proxy, config, application service) are optional and included only when needed.

  • Wiki init

    graypirate/Alexandria/.agents/skills/wiki-init Skill

    no license0★ repo

    Initialize a brand-new wiki for the user. Use ONLY when the user explicitly says they want to create, set up, or start a new wiki — never auto-trigger. Asks for path, name, and purpose, then scaffolds folder structure, schema, config, and an empty search index.

  • Engineer

    ty13r/skillforge/.claude/skills/engineer Skill

    no license0★ repo

    Assembles winning variants into a composite skill. Foundation skeleton plus trait merge with conflict resolution and one refinement pass. Use when merging variants or building a final skill from atomic winners.

  • Prompt injection defense

    bensonmaxai/minis-security-skills/skills/prompt-injection-defense Skill

    no license0★ repo

    Use when browsing websites, reading PDFs or docs, processing OCR text or screenshots, inspecting repositories, or handling any untrusted content that may contain adversarial instructions. Focuses on prompt-injection resistance for Minis on iOS: treating external content as data, separating user intent from content instructions, blocking secret exfiltration, preventing unsafe tool use, and keeping browsing/research/document workflows safe.

  • Uip methodology

    cprima-agents/cpm-agent-skills/skills/uip-methodology Skill

    no license0★ repo

    UiPath RPA project design skill — guides BA, Solution Architect, and PM through authoring and amending all project artefacts: PDD, SDD, Architecture Review, Estimation, ROI, TDD, DSD, Glossary. Three workflows: (A) Guided Interview — full structured elicitation driven by rpa-methodology.yaml, produces any artefact; (B) PDD Creation — focused section-by-section PDD authoring for BAs; (C) SDD Creation / Amendment — infers architecture decisions from PDD, patches existing SDDs idempotently. Trigger phrases: "start interview", "guided interview", "interview me", "help me document this process", "create a PDD", "fill out a PDD", "start a PDD", "document a process for RPA", "create an SDD", "design the solution", "generate SDD", "amend SDD", "update SDD", "fill in the PDD", "let's do the arch review", or when a PDD is available and the next step is technical design.

  • Review architecture

    PeytonLi/skills/review-architecture Skill

    0★ repo

    Use when you need a complete top-down architecture audit of any codebase, including full exploration of major paths, endpoint mapping, current-vs-target user journeys from documentation, and deep issue remediation plans with step-by-step fixes. Trigger phrases: architecture audit, full codebase walkthrough, map all endpoints, user journey analysis, current vs desired product flow, find and fix project issues, end-to-end architecture review.

  • Falsification gauntlet

    narainio/context-daemon/skills/falsification-gauntlet Skill

    0★ repo

    Adversarial stress-testing framework for product ideas. Use when the user wants to rigorously evaluate a product thesis before building—identifying load-bearing assumptions, interrogating moats, testing technical feasibility, and mapping competitive landscape. Designed to KILL weak ideas early or REFINE them into stronger theses. Triggers on phrases like "stress-test this idea", "should I build this", "kill list", "validate my thesis", "is this worth building", or when a user presents a product concept and wants rigorous evaluation before committing resources.

  • Diagnose

    abijith-suresh/skills/skills/diagnose Skill

    0★ repo

    Investigates production and QA defects through a persistent, evidence-driven loop across code, data, service contracts, configuration, and infrastructure. Use only when the user explicitly invokes the diagnose skill. Do not trigger from ordinary bug reports or requests to implement a fix.

  • Development frontend

    litingyes/skills/skills/development-frontend Skill

    0★ repo

    Define baseline frontend engineering standards and legacy project audits. Use when users need project setup/configuration for Node.js + vite-plus workflows, commit/release governance, or compliance gap analysis against the frontend baseline.

  • Codebase safety

    agykit/agykit/.agent/skills/codebase_safety Skill

    no license0★ repo

    Guide for safely navigating and modifying an existing codebase. Use this skill when: (1) Onboarding to a new project or context, (2) Planning complex changes that might have side effects, (3) Ensuring modifications don't break existing functionality across different languages and frameworks.

  • Vibe sql

    PayEz-Net/vibesql-skills/claude/vibe-sql Skill

    no license0★ repo

    Talk to a VibeSQL database — query, create tables, manage data via natural language

  • Openl tablets deploy

    SzTk/openl-tablets-tool/skills/openl-tablets-deploy Skill

    0★ repo

    Use when deploying an Excel file created or edited with openl-tablets-create / openl-tablets-edit to an OpenL Tablets instance on Azure and verifying it works as a REST API.

  • Memory refiner

    artyom-88/codex/skills/memory-refiner Skill

    no license0★ repo

    Use this skill when the user asks to refine Codex memory, improve Codex instructions or config, analyze session or history patterns, optimize context efficiency, or update global or project-local Codex guidance based on repeated interaction patterns.

  • Release readiness checklist

    tomkraaij/ai-skills-librarian/examples/skill-pack-example/skills/release-readiness-checklist Skill

    no license0★ repo

    Run release readiness checks before shipping team changes.

  • Healthsync

    BRO3886/agent-skills/healthsync Skill

    no license0★ repo

    Queries Apple Health data stored in a local SQLite database. Use this skill to read heart rate, steps, SpO2, VO2 Max, sleep, workouts, resting heart rate, HRV, blood pressure, active/basal energy, body metrics, mobility, running metrics, mindful sessions, wrist temperature, and more. Can query via the healthsync CLI or directly via SQLite. Read-only — never write to the database.

  • Python project setup

    ThiagoPanini/aidriven/.claude/skills/python-project-setup Skill

    0★ repo

    Configure modern Python development tooling for any Python project — library, backend, CLI, or otherwise. Invoke this skill whenever a user wants to set up or improve Python tooling, configure pyproject.toml, add pre-commit hooks, set up linting or formatting, configure a type checker or test runner, or any request like "set up my Python project", "configure Python tooling", "add pre-commit to my project", "set up ruff and mypy", or "bootstrap Python dev tools". This skill works on both empty repositories and existing projects with partial configuration. It produces ONLY configuration files — no source code, no test logic.

  • Macos sandbox testing

    zhutao100/macos-sandbox-testing-skill/macos-sandbox-testing Skill

    no license0★ repo

    In-process macOS Seatbelt sandbox/tripwire safety boundary for local dev/test commands (SwiftPM, Xcode/xcodebuild, Cargo, Go, Node, Python venv), so direct invocations like `swift test`, `xcodebuild test`, or `cargo test` cannot accidentally write outside the repo workspace. Installs a Seatbelt (`sandbox_init_with_parameters`) write guard plus optional filesystem/network mutation logging into supported executables and test runners.

  • Meta mcp wizard

    arterialist/mcphero-skills/skills/meta-mcp-wizard Skill

    no license0★ repo

    Use the MCPHero Meta-MCP server inside AI clients (Claude Desktop, Cursor, etc.) to create, deploy, and manage MCP servers through the wizard pipeline. Use this skill when the user wants to connect the Meta-MCP server, build MCP servers interactively via MCP tools, or asks about the meta-mcp endpoint at api.mcphero.app.

  • Token manager

    jquigley3/session-keeper/skills/token-manager Skill

    no license0★ repo

    Manage tokens and secrets for Claude Code sessions. Use this skill whenever the user mentions an API key, token, secret, password, credential, or wants to store/retrieve/audit sensitive values. Triggers on phrases like "save my token", "add this API key", "where did I use that token", "find secrets in my sessions", "audit my credentials", "store this key", "what tokens do I have", or any time the user pastes or references a sensitive value. Also use when the user wants to know if a secret has leaked into chat history.

  • Panno canvas

    Panno-ai/skills/skills/panno-canvas Skill

    0★ repo

    Interact with a Panno infinite canvas via REST API using curl. Use this skill whenever the user wants to create, read, update, or delete shapes on a Panno canvas — including markdown content, geometric shapes, notes, and file editors. Also handles canvas authentication (guest session, API key, OAuth sign-in), layout, responding to comment threads, and the diff/patch workflow for proposing content changes.

  • Deweight coverage scan

    kkunkunya/academic-deweight-suite/plugins/academic-deweight-suite/skills/deweight-coverage-scan Skill

    no license0★ repo

    学术降重的全量 AI 模式扫描门。长文必须启用 subagent 并行隔离扫描,生成 Pattern Coverage Matrix,确保每段都有 clean/suspect/format-exempt 状态和 A-code 证据。触发关键词:长文扫描、模式门控、Pattern Coverage Matrix、A-code 扫描、反漏检、母骨架诊断、subagent 并行扫描。

  • Ai regression testing

    Lukk17/agent-standards/.agents/skills/ai-regression-testing Skill

    0★ repo

    Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

  • Android aso

    appalize/aso-skills/skills/android-aso Skill

    0★ repo

    When the user wants to optimize their Google Play Store listing — title, short description, full description, keywords, ratings, or Play Store-specific features. Use when the user mentions "Google Play", "Android", "Play Store", "Play Console", "short description", "full description indexed", "Google Play ASO", or wants Google Play-specific keyword, creative, or ratings strategy. For iOS App Store optimization, see aso-audit and metadata-optimization.

  • Nonfunctional requirements

    chrisVillanueva/ai-skills-registry/data-engineering/nonfunctional-requirements Skill

    no license0★ repo

    [WHAT] Guides the agent through trade-off analysis for data engineering systems using nonfunctional requirements: performance, reliability, scalability, and maintainability. Provides layered decision frameworks for system properties, pipeline design, and data operations. [WHEN] Activate when the user is defining SLOs/SLAs for data systems, evaluating pipeline latency vs throughput, choosing batch vs streaming, assessing fault tolerance strategies, planning capacity, or reasoning about ETL vs ELT, error handling, idempotency, or data quality trade-offs. [KEYWORDS] nonfunctional requirements, performance, reliability, scalability, maintainability, SLO, SLA, latency, throughput, percentiles, fault tolerance, batch, streaming, ETL, ELT, idempotency, data quality, observability, trade-off analysis, pipeline design.

  • Eval verdict write

    0SxD/advisor-trackable-eval-skills-v01/skills/eval_verdict_write Skill

    0★ repo
  • Debug session

    SpencerGoss/agent-engineering/debug-session Skill

    0★ repo

    Use when something is broken and the cause isn't obvious. Trigger on: "it's not working", "tests are failing", "the build is broken", "nothing is running", "something weird is happening", "it worked before", "I don't know what changed", "rollback this", any error, crash, unexpected output, or regression. Also trigger when an agent made autonomous changes that need auditing or reversing. NOT for design reviews or refactoring — use code-review-session or refactor-session instead. Never assume cause — always diagnose before fixing.

  • Skill a from a

    lythos-labs/lythoskill-test-stubs/skill-a-from-a Skill

    0★ repo

    BDD test stub — alias-collision fixture. Not consumable.

  • Made json setup

    itsbdell/made-json-agent-skills/skills/made-json-setup Skill

    0★ repo

    Use when bootstrapping a made.json feed for a creator or workspace by looking across local repositories, identifying creator-made apps, skills, prompts, workflows, agents, CLIs, MCP servers, extensions, and templates, drafting item entries, and validating the resulting feed.

  • Fly postgres

    Tyr0/agent-skills/plugins/fly-expert/skills/fly-postgres Skill

    0★ repo

    Use this skill whenever the user asks about setting up, connecting to, or managing Postgres on Fly.io, including creating a Fly Postgres cluster, attaching a database to a Rails or other app, DATABASE_URL configuration, running database migrations on Fly, proxying to a Fly Postgres database locally, connection pooling, backing up or restoring a Fly Postgres database, scaling a Postgres cluster, or troubleshooting database connection issues on Fly.io. Also use it for questions about Fly Managed Postgres (fly mpg) vs unmanaged Postgres clusters, or local development workflows that connect to a remote Fly Postgres database.

  • Access review coverage auditor

    sisodiabhumca/agent-skills/skills/access-review-coverage-auditor Skill

    0★ repo

    Vendor-neutral skill to audit access review coverage and flag stale grants or missing attestations.

  • Hono

    escwxyz/skills-re/.agents/skills/hono Skill

    no license0★ repo

    Use when building Hono web applications or when the user asks about Hono APIs, routing, middleware, JSX, validation, testing, or streaming. TRIGGER when code imports from 'hono' or 'hono/*', or user mentions Hono. Use `npx hono request` to test endpoints.

  • Architecture drift check

    rynhardt-potgieter/sprint_workflow/plugins/sprint-workflow/skills/architecture-drift-check Skill

    0★ repo

    Detect architectural drift and erosion by comparing implemented or planned work against the project's Linear "Architecture & Roadmap" document. Use this skill in /sprint-plan and /sprint-enrich (planning-time drift), in /sprint-start Phase 3 QA and code review (implementation-time drift and erosion), and in /sprint-retro (sprint-level drift summary). Defines drift vs erosion, the reflexion-modeling comparison method, severity rules, the standard report format, and the conditions under which the check is skipped gracefully.

  • Scribeless api integration

    scribeless/skills/skills/scribeless-api-integration Skill

    0★ repo

    Build public Scribeless API and automation workflows for creating recipients, including custom HTML recipient rendering. Use when a user needs API authentication guidance, X-API-Key examples, POST /api/recipients payloads, POST /api/recipients/html payloads, product_key selection, HTML front/back rendering, Zapier/Make/Pipedream/n8n/CRM/ecommerce mappings, error handling, webhook-to-recipient mapping, or implementation review.

  • Plan

    WillowRyu/agent-handoff/skills/plan Skill

    0★ repo

    Use when starting a new feature, fix, or refactor that needs explicit planning before code changes. Reads .handoff/config.md (and backlog if present) and writes a structured plan.md to .handoff/. Supports multi-phase plans for large work, and risk tags on change list items. Does NOT modify code or run build commands. Pair with /execute and /verify. Part of the agent-handoff bundle (4 skills) — install /setup-handoff, /plan, /execute, /verify together.

  • Notebooklm research lane

    0SxD/notebooklm-research-protocol/skills/notebooklm-research-lane Skill

    0★ repo

    Role-aware NotebookLM research skill. Any Claude session can use this to query NotebookLM, run web research, ZCR-sanitize, apply the Trinity Dialectic, and save to the correct lane. Output routing follows a strict precedence: (1) user-provided paths override everything, (2) invoking agent's role lane defaults, (3) this skill's built-in defaults from <project-root>/. Never auto-selects a notebook.

  • Tdd sentinel

    rogerchappel/skillforge/examples/tdd-sentinel Skill

    0★ repo

    Forge portable coding-agent skills with linting, activation tests, render adapters, and local-first packaging.

  • Patronum dev setup

    emaarco/hogwarts/plugins/agento-patronum/.claude/skills/patronum-dev-setup Skill

    0★ repo

    Set up the agento-patronum development environment. Check prerequisites, install docs dependencies, validate plugin structure.

  • Test runner

    Liber1917/agent-skill-infra/skills/test-runner Skill

    no license0★ repo

    Guide for writing behavior test cases (evals.json) for Agent Skills. Defines the eval schema, judgment criteria (trigger/flow/output), and snapshot testing conventions. Use when creating test cases for Skills or teaching others how to test Agent Skills.

  • Brain harness

    0SxD/agent-plugin-skills-v01/skills/brain-harness Skill

    0★ repo

    Full session bootup sequence. Triggered when user asks about accessing memory, putting on the harness, checking the brain, or any similar phrase indicating they want full session initialization. Reads all memory files across all active projects and reports session state before asking what we're working on today.

  • Architecture

    shuakami/paperchart/skills/architecture Skill

    0★ repo

    Render a system-architecture diagram. Services are grouped into labeled panels (client, edge, backend, data, observability, …); each panel stacks its services vertically. Connections draw smooth cubic bézier curves between services and can be marked accent, dashed, or bidirectional. Use for architecture posts, design documents, onboarding diagrams.

  • LLM

    ploteddie-bit/skills/LLM Skill

    no license0★ repo

    Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.

  • Github issue create

    MauricioPerera/agent-skills-pack/skills/github-issue-create Skill

    0★ repo

    Creates a new GitHub issue in a specified repository. v2 ships a pack-distributed CustomCommand (command.js) that calls the GitHub REST API directly — no host gh CLI required. Authentication via $GH_TOKEN; the agent never sees the credential.

  • Setup intake

    0SxD/ce-rd-os/ce-rd-os/skills/setup_intake Skill

    0★ repo

    Use this skill immediately after system_directive at session start. Captures the irreducible parameters needed to run any CE_RD_OS workstream: mission, role, sources, rubric mode, sub_agent profile, memory option, ML backend option, loop bound, output target. Trigger when the user says "set up", "let's begin", "what do you need from me to start", or when the agent recognizes a new workstream is being initiated. Asks at most three questions per turn.

  • Kozen etl mk

    kozen-labs/agentic/.agents/skills/kozen-etl-mk Skill

    0★ repo

    Reference skill for @kozen/etl-mk — a Kozen module that runs bi-directional ETL pipelines between MongoDB and Apache Kafka. Covers when and why to use this npm package, prerequisites, the MK (MongoDB→Kafka) and KM (Kafka→MongoDB) pipelines, the delegate pattern for transforming data in both directions, all CLI commands (etl-mk:start, etl-mk:validate, etl-mk:help), all environment variables, IoC service registrations, DLQ routing, retry logic, best practices for production, and how to build runnable demos using .env files and ESM delegate files.

  • Init project

    cristianorj22/arthus-harness/core/.claude/skills/init-project Skill

    0★ repo

    Use this skill when the user says "init this project", "bootstrap with arthus-harness", "set up arthus-harness here", or otherwise asks to initialize a fresh project with the arthus-harness baseline. Runs `npx create-arthus-harness` after a short interview.

  • Next react fixing patterns

    idimsh/tdds-frontend-skills/next-react-fixing-patterns Skill

    no license0★ repo

    Pre-delivery checklist and diagnostic guide for UI work in Next.js, React, and other web projects. Use when building, reviewing, or debugging visual components — especially when a project has multiple themes, locales, brands, modes, or responsive states. Trigger with "check UI", "UI review", "pre-delivery check", "theme check", or when delivering any visual component.

  • Agents md sync

    lyoneel/ly-agent-skills/agents-md-sync Skill

    0★ repo

    Audit AGENTS.md files for duplication and correct placement. Use when syncing user-level and project-level AGENTS.md files.

  • Release publisher

    fermeridamagni/skills/skills/release-publisher Skill

    0★ repo

    Automate releasing packages/apps/products to GitHub repositories. Use this whenever the user asks to release, publish, ship a new version, bump a version, create tags, generate changelog/release notes, or prepare a GitHub Release. Always use this skill for release automation requests, including npm/GitHub Packages/VS Code Marketplace/Open VSX publishing and release workflow setup.

    The same file is in 1 other repository

  • Azure devops changelog generator

    Oglaf/skills/azure-devops-changelog-generator Skill

    no license0★ repo

    Generate release notes and cards from Azure DevOps TFVC changesets or Git commits. Trigger this skill whenever the user mentions TFVC changesets, Git commits, Azure DevOps work items, 'generate changelog', 'cards.md', or 'release notes'. The skill asks for the Azure DevOps organization name, fetches work items via Azure DevOps APIs (requires $DEVOPS_PAT), analyzes descriptions and discussion, and produces cards.md and changelog.md grouped by Azure DevOps project name.

  • Harness optimization loop

    hideaway007/codex-self-improvement-skills/skills/harness-optimization-loop Skill

    0★ repo

    Use when improving an agent harness, prompt, workflow, tool order, retrieval strategy, subagent routing, or evaluation loop where multiple candidate approaches can be compared against observable results.

  • Cloudflare api token permissions

    okayus/okayus-skills/skills/cloudflare-api-token-permissions Skill

    0★ repo

    Agent Skills for Claude Code / agentskills.io-compatible agents. Cloudflare Workers + Discord integration patterns.

  • Julia development

    jacobleft/techang/skills/julia-development Skill

    no license0★ repo

    This skill should be used when the user asks to "write Julia code", "refactor Julia", "explain multiple dispatch", "optimize Julia performance", "Julia types", "Julia Pkg management", or "idiomatic Julia". Covers Julian style, type system, performance, Pkg, environment detection, repld-first execution, optional MCP server integration (Kaimon.jl and julia-mcp), and JETLS for static analysis. Not for non-Julia tasks. For package docs, load docs-style-preferences.

  • Floop rest api

    peak6-labs/floop-skills/floop-rest-api Skill

    0★ repo

    Use when integrating directly with the Floop REST API, calling Floop HTTP endpoints, proposing tasks without auth, creating tasks with Bearer API keys, rotating keys, handling API errors, or building server-side Floop clients.

  • Copilot issue image

    sujithq/skills/skills/copilot-issue-image Skill

    0★ repo

    Prepare GitHub Copilot issue-assigned workflows to generate images with Azure OpenAI using non-interactive authentication. Use when the user wants Copilot assigned to an issue to create images, wire image generation into a repository, or replace local az login with GitHub-safe Azure authentication.

  • Mcp server

    bbismm/ibitlabs/mcp-server Skill

    0★ repo

    Build/maintain the iBitLabs MCP server that exposes the $1k → $10k experiment as callable tools (live balance, contributor ledger, saga). Five tools: 3 wired to live public endpoints, 2 stubbed pending Cloudflare Pages functions.

  • Brain harness

    0SxD/openrouter-swarm-orch-agent/agentic_auto_buildX_ai_bundle_repos/sagex_plugin_v0.1_example_copy/skills/brain-harness Skill

    0★ repo

    Full session bootup sequence. Triggered when user asks about accessing memory, putting on the harness, checking the brain, or any similar phrase indicating they want full session initialization. Reads all memory files across all active projects and reports session state before asking what we're working on today.

  • Bootstrap

    mj-deving/pai-skills/skills/Beads/Bootstrap Skill

    no license0★ repo

    Audit or initialize repo Beads workflow and files. USE WHEN bootstrap Beads, adopt Beads, standardize Beads workflow, initialize a new repo onto Beads, or verify whether a repo already has mature Beads doctrine.

  • Onboarding

    sekachev/codex-new-agent-skill/codex-new-agent/assets/agent-template/.agents/skills/onboarding Skill

    0★ repo

    First-run or reconfiguration workflow for the generated adaptive Codex agent. Use when onboarding_status is pending, when the user says begin onboarding, first run, configure yourself, create my agent, change your role, change your personality, or update what you remember.

  • Autoresearch

    frodo2647/triptych/.claude/skills/autoresearch Skill

    0★ repo

    Autonomous self-improvement loop after Karpathy — define a metric, iterate, keep what works, revert what doesn't. Use when the user asks to optimize, tune, benchmark, or iteratively improve a system against a measurable metric. Triggers: "optimize", "tune", "benchmark", "improve performance", "self-improve", "auto-tune", "sweep", "beat baseline".

  • Corp add agent

    mithraeums/skills/corp/skills/corp-add-agent Skill

    0★ repo

    Scaffolds a new corp agent file and wires it into the org. Use when a domain grows large enough to deserve its own agent (auth, infra, ML, data pipeline, payments, etc.). Trigger: /corp:add-agent, "add agent", "new agent", "create agent for X".