agentsclimarketplace

Engineering

98,276 rows, by stacks then stars

  • Agent

    lyoneel/ly-agent-skills/agent Skill

    0★ repo

    Load and activate a custom agent from the agents folder. Use when you need to switch to a specialized agent definition for focused task execution.

  • Super ai ml ops

    arpitexplores/super-ai-ml-ops Skill

    0★

    AI/ML operations: evaluation, monitoring, cost control, and reliability. Use for productionizing AI systems.

    The same file is in 1 other repository

  • Railway deploy

    changyuanbao6-prog/railway-deploy Skill

    0★

    Railway.app 云平台部署指南。当用户需要将 Node.js 应用部署到外网、分享给朋友访问、或询问如何免费托管 Web 应用时使用此 skill。典型场景:(1) 用户想把本地开发的系统放到网上,(2) 用户询问 Railway 部署流程,(3) 用户遇到 Railway 部署报错需要排查。

  • Prd for agents

    sanketsao/prd-for-agents Skill

    no license0★

    Use this skill whenever an agent or user asks to write, draft, create, or produce a PRD, product requirements document, product spec, or feature spec — especially when the output will be consumed by an AI coding agent, developer agent, or multi-agent pipeline rather than a human PM. Also trigger when asked to "write requirements for X", "spec out X", "define what needs to be built for X", or "create a handoff doc for Developer". This skill produces agent-optimized PRDs that include quantitative success metrics, user stories, open questions, risks, dependencies, and a sequenced build order that a Developer agent can execute directly without clarification. Always use this skill in preference to writing a PRD from scratch — it enforces completeness gaps that generic PRDs miss.

  • Dolphindb

    tradercjz/dolphindb-agent-skills/skills/dolphindb Skill

    no license0★ repo

    The ONE skill for anything DolphinDB — covers BOTH running queries against the user's live DolphinDB server AND offline reference / syntax lookup. Use this whenever the user mentions DolphinDB, ddb, .dos, DFS, or anything database-related for DolphinDB. Runtime side: the connection info (host/port/user/password) embedded below was written by the `dolphindb-agent-skills` installer and is the user's REAL server — use it verbatim, do NOT fall back to localhost:8848 or any other default. Runtime capabilities: one-shot queries via Python API (`import dolphindb`), executing .dos files, uploading pandas DataFrames, parameterized queries, listing DFS databases/tables (`getClusterDFSDatabases`, `getTables(database(…))`), checking table disk usage (`getTableDiskUsage`), bulk-inserting into DFS tables (`tableInsert`), robust long-lived connections (`keepAliveTime`, `reconnect`), error-safe execution. Reference side: DolphinDB SQL dialect (context by / pivot by / asof join / window join), DFS partitioned tables on TSDB / OLAP / PKEY / IMOLTP engines, stream computing (streamTable, subscribeTable, reactiveStateEngine, timeSeriesEngine, CEP, replay), strategy backtesting (Backtest plugin, MatchingEngineSimulator, simulatedExchangeEngine, OME) for stock / future / option / bond / crypto, factor computation with @state + @jit, client APIs (Python, Java, C++, JDBC, ODBC, Go, Rust), ingestion (loadText, HDF5, Parquet, Arrow, Kafka, MQTT), 70+ plugins, performance tuning, cluster ops, and lookup of any RefId Sxxxxx error code or built-in function. Keywords: DolphinDB, ddb, .dos, DFS, 回测, 策略, 因子, 我的数据库, 有哪些库, 有哪些表, 列出数据库, 列出表, list databases, list tables, show tables, run dolphindb script, connect to dolphindb, query dfs.

  • Skill

    shihabshahrier/softco/skill Skill

    0★ repo

    Build, deploy, and ship any software product end-to-end as a complete autonomous software company inside Claude Code. Triggers on: "build me a...", "create an app/API/SaaS", "design the architecture for...", "set up CI/CD", "dockerize", "kubernetes", "terraform", "integrate LLM/AI/GPT/Claude/Gemini/ RAG/agent", "deploy to AWS/GCP/Azure/Fly/Render", "review my code", "audit this repo", "fix this bug", "scaffold a project", or any open-ended request to create, extend, or ship software. SoftCo acts as PM, architect, senior engineer, DevOps, QA, security engineer, and tech writer. Docs and tests before code. Do not invoke for one-line edits, trivial single-file questions, or pure conceptual Q&A that needs no product output.

  • E2e testing methodology

    tianchong1980/e2e-testing-methodology Skill

    no license0★

    Comprehensive E2E testing methodology for web applications. Covers complete data flow testing, boundary testing, error handling verification, and visual validation patterns. Use when testing web applications end-to-end, verifying UI behavior, testing CRUD operations, or debugging navigation/display issues.

  • Golang benchmark

    guynhsichngeodiec/cc-skills-golang/skills/golang-benchmark Skill

    0★ repo

    Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while golang-performance provides the optimization patterns.

  • Project indexer

    pccly/project-indexer Skill

    0★

    Use when the user asks to "index this project", "map the codebase", "generate a project index", "create PROJECT_INDEX.md", "refresh/update the project index", or wants any AI coding agent (Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Copilot, Cline, etc.) to understand the codebase layout without using Glob/Grep every turn. Also use when navigating an unfamiliar repo where file search is expensive and a structured index would cut tool calls. Always trigger when the user mentions indexing, cataloging, summarizing, or documenting a project's file structure — even phrased casually.

  • Ai native foundation

    Sepi0l-brd/ai-native-foundation Skill

    0★

    Use when the user wants to set up the "AI Native Foundation" framework on their Claude Code - positions AI as a senior tech lead so juniors and PMs ship production-grade code. Installs CLAUDE.md (operational rules), hooks (security guardrails), architectural skills (webhook design, identity coordination, atomic transactions, decision categorization, AI collaboration), memory conventions, working-style manifesto, senior traps catalog, and optional Obsidian vault. Triggered by phrases like "set up AI Native Foundation", "install this framework", or when the user references this repo by name.

  • Skill creator

    fermeridamagni/skills/.agents/skills/skill-creator Skill

    0★ repo

    Create 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

  • Release manager skill

    jovd83/release-manager-skill Skill

    0★

    Validate and prepare GitHub releases. Trigger for: SemVer changelogs, version bumps, release commits, CI/CD monitoring, and repo bootstrap.

  • Backend fastapi

    sonhaicoder/haiclaudeskill/skills/backend-fastapi Skill

    0★ repo

    Backend FastAPI skill cho multi-tenant SaaS với SQLAlchemy 2.0 async + PostgreSQL + Alembic. AUTO-TRIGGER khi: chạm file backend/app/**/*.py, file có `from fastapi`, `from sqlalchemy`, file Alembic migration, hoặc user nói "viết API/endpoint/model/migration/service" + "backend/route/schema/repository". Force apply 7 luật cứng: shop_id filter mọi query, Decimal money KHÔNG float, async/httpx KHÔNG requests, atomic stock update, order state machine validate transitions, JWT auth + permission check, env vars qua settings KHÔNG hardcode. Distilled từ Commerce Platform production patterns (60K+ lines, 100 commits). KHÔNG dùng cho: Express/Node backend, Django, frontend, mobile, infra/docker.

  • Clean code

    rerelurelu/skillbox/skills/clean-code Skill

    0★ repo

    Polishes code quality after implementation by running simplify and deslop, then auditing for dead code and stale comments. Use after completing a feature, before committing, or when the user asks to clean up uncommitted changes.

  • Claude api

    Montesplenic117/CC/src/skills/bundled/claude-api Skill

    no license0★ repo

    Rebuild Claude Code CLI source from source maps into runnable TypeScript for study, debugging, and local development

  • Super security

    arpitexplores/super-security Skill

    0★

    Security audits, threat modelling, testing, and remediation across apps, APIs, and infrastructure.

    The same file is in 1 other repository

  • Claude code docker sandbox

    okayus/okayus-skills/skills/claude-code-docker-sandbox Skill

    0★ repo

    Set up a Docker Compose-isolated development environment where dependency installs and agent-run code execute behind a default-deny network firewall, never touching the host. Use when you want to run `npm install` / `cargo build` / `cabal build`, untrusted dependencies, or Claude Code itself in a container to contain supply-chain attacks (npm postinstall, Rust build.rs, Haskell Setup.hs) — without depending on VS Code. Reuses Anthropic's published devcontainer Dockerfile + init-firewall.sh, driven by a plain docker-compose.yml so any host editor works via bind mount; Rust/Haskell toolchains are opt-in build args on the node:20 base. Covers the egress allowlist (fatal vs OPTIONAL non-fatal domains), build-time-vs-runtime network, keeping Claude Code current inside the firewall (native updater's host is blocked — update via npm at start), why the /model picker hides flag-gated models until DISABLE_TELEMETRY is unset, bypassPermissions-by-default (container-scope, not repo-shared), and host-side git hygiene.

  • Copilot cloud agent

    SoulFaro/copilot-cloud-agent/skills/copilot-cloud-agent Skill

    0★ repo

    Create, assign, and track GitHub Copilot cloud coding agent tasks via gh agent-task. Handles task creation, model selection, issue assignment, and live log streaming.

  • Floop mcp tools

    peak6-labs/floop-skills/floop-mcp-tools Skill

    0★ repo

    Use when connecting to Floop through MCP, calling Floop tools, proposing tasks without an API key, authenticating with a Floop key, discovering workers, creating tasks, approving proof, or managing task lifecycle through model tools.

  • Design extractor

    PatNoO/design-extractor/.claude/skills/design-extractor Skill

    0★ repo

    Extracts the ENTIRE design system from an existing codebase (repo) and exports it to a single runnable Figma plugin script that automatically creates tokens, components, AND frames. Always use this skill when the user wants to: move their design from code to Figma/Pencil, extract design tokens from a repo, sync a codebase design to a design tool, generate a design system from existing code, reverse-engineer their app design, export colors/typography/spacing/components/pages from their app, or get their entire app design into Figma automatically. Triggers on phrases like: "design to figma", "extract design", "design tokens", "code to figma", "export design", "design system from repo", "reverse design", "get my design into figma", "components to figma", "frames to figma", "whole design to figma".

  • Zama fhevm security review

    thericardoli/zama-dev-skills/skills/zama-fhevm-security-review Skill

    0★ repo

    Use for audits, reviews, threat modeling, or fixes involving Zama FHEVM confidential contracts and SDK/frontend integrations. Covers encrypted input proofs, ACL/handle permissions, user/public decryption, async callback replay, silent failures, unchecked encrypted arithmetic, transient allowances, account abstraction/reorg/finality risks, HCU, ERC7984/wrappers, Relayer SDK, React/wagmi, Node services, deployment issues, and testing gaps.

  • Claude rc

    himynameisben/claude-rc Skill

    0★

    Manage Claude Code Remote Control (RC) sessions via tmux with a per-session YAML registry. Use when the user wants to start a new RC session, list existing sessions, attach to a running session, kill a session, clean up dead sessions, or mentions claude-rc, remote control session, RC session, tmux session for Claude Code, 開 rc session, 新開 session, 列出 session, attach session, 清理 session, 殺掉 session.

  • Agents

    mj-deving/pai-skills/skills/Agents Skill

    no license0★ repo

    Compose CUSTOM agents from Base Traits + Voice + Specialization for specialized perspectives. USE WHEN create custom agents, spin up agents, specialized agents, agent personalities, available traits, list traits, agent voices, compose agent, load agent context, agent profile, spawn parallel agents, launch agents. NOT for agent teams/swarms (use Delegation skill → TeamCreate) or Codex delegation (use Delegation skill → CodexBridge).

  • Trooly ai skill

    Alpha-Park/trooly-ai-skill Skill

    no license0★

    Qualitative Research Automator — Orchestrates AI-driven qualitative interviews at scale using Trooly.ai's Empathy Engine to gather, analyze, and synthesize user feedback.

    The same file is in 1 other repository

  • Anti hallucination

    fbsmna-coder/karpathy-pro-max/skills/anti-hallucination Skill

    0★ repo

    Never invent APIs, file paths, line numbers, library functions, CLI flags, or framework features. Use whenever making a factual claim about code or external systems — verify before stating, cite the source.

  • Claude code safety hooks

    0SxD/claude-code-safety-hooks Skill

    no license0★

    Two deterministic Claude Code hooks: a PreToolUse Bash command guard against destructive operations, and a PreToolUse research-output validator that requires approved-source citations on Write/Edit calls.

  • Pike debugging

    TheSmuks/pike-ai-kb/skills/pike-debugging Skill

    0★ repo

    How to diagnose Pike errors, introspect the runtime, navigate the stdlib source, and debug Pike code on the CLI

  • Codex new agent

    sekachev/codex-new-agent-skill/codex-new-agent Skill

    0★ repo

    Create a new adaptive Codex-native agent workspace from a reusable template. Use when the user asks to create, scaffold, initialize, bootstrap, or install a personal/project agent with onboarding, durable memory, daily logs, Codex hooks, and dreaming-style memory consolidation.

  • Modular tool integration

    xuluoforcainiao/modular-tool-integration/modular-tool-integration Skill

    no license0★ repo

    Guide for integrating independently-developed tool modules into cohesive offline-deployable workflows. Use when the user needs to connect multiple standalone Python tools or exes, bundle separate utilities into a unified workflow, design extensible architecture for colleague-facing tool suites, or decide how tightly or loosely to couple different automation modules. Covers workflow orchestration, state passing, inter-process communication, and progressive integration strategies.

  • Fastapi best practices

    Malikasadjaved/skills/fastapi-best-practices Skill

    no license0★ repo

    Use when building or reviewing FastAPI applications — async route design, asynccontextmanager lifespan for DB/Qdrant/Redis startup, Pydantic v2 with model_config and model_validator, Annotated+Depends injection, JWT with OAuth2PasswordBearer, structured AppException hierarchy, CORS, background tasks, and OpenAPI config. Python 3.11+, pydantic>=2.0.

  • Architecture review

    eooo-io/ai-native-engineering-doctrine/04-agent-skills/architecture-review Skill

    0★ repo

    Review architecture decisions, boundaries, trade-offs, scalability, and operational risk.

  • Architecture blueprint generator

    scikrikci/skills/skills/architecture-blueprint-generator Skill

    no license0★ repo

    Comprehensive project architecture blueprint generator that analyzes codebases to create detailed architectural documentation. Automatically detects technology stacks and architectural patterns, generates visual diagrams, documents implementation patterns, and provides extensible blueprints for maintaining architectural consistency and guiding new development.

    The same file is in 1 other repository

  • Sunday letter

    selinayfilizp/sunday-letter/skills/sunday-letter Skill

    0★ repo

    Write a grounded weekly Sunday Letter from dated local agent conversations. Use when the user asks for a Sunday Letter, a weekly reflection, what changed this week, or when the sunday-letter schedule fires. The supported reference paths are Codex local and Claude Code local. The runtime validates provenance, enforces default silence, sanitizes HTML, updates an atomic ledger, and rebuilds a private local archive.

  • News fetch setup

    GeniusTrader-Harry/news-fetch/skills/news-fetch-setup Skill

    0★ repo

    Walks the user through end-to-end setup of the news-fetch Telegram markets brief. Use when the user has cloned the news-fetch repo and is installing it for the first time, OR hits errors during Telegram bot creation, FT/WSJ cookie export, scheduled-task registration, or folder trust. Triggers include phrases like "set up news-fetch", "configure the markets brief", "install the Telegram brief", "I cloned news-fetch, what now", "help me wire up the FT/WSJ fetcher", "the scheduled task isn't firing", "my FT cookie expired". Do NOT use for customising the brief CONTENT (theme dictionary, geography rule, view question style — point the user at CUSTOMISATION.md instead) or generic Claude Code setup unrelated to this repo.

  • Renovate coverage

    iwamot/skills/skills/renovate-coverage Skill

    0★ repo

    Detect Renovate Dependency Dashboard coverage gaps in a git repo. Cross-references version-like strings in Renovate-managed files (`.github/workflows/*.{yml,yaml}`, `Dockerfile*`, `compose*.{yml,yaml}`, `mise.toml`, `package.json`, `*.tf`, `go.mod`, `pyproject.toml`, `requirements*.txt`, etc.) against the open "Dependency Dashboard" issue's "Detected Dependencies" listing, and reports lines whose dependency is not tracked by Renovate. Use when the user asks to audit Renovate detection coverage or find dependencies that Renovate is not tracking.

  • Xcratch extension create

    xcratch/xcratch-skills/skills/xcratch-extension-create Skill

    no license0★ repo

    Use when setting up a new Xcratch extension project and local development environment. Trigger phrases: xcratch-create, scaffold extension, setup-dev, initialize extension repo, local extension setup.

  • Bim software dev

    isaddiq/Claude-BIM-development-skill/plugins/bim-software-dev-plugin/skills/bim-software-dev Skill

    no license0★ repo

    BIM software development and BIM data engineering skill. Use when designing, coding, debugging, reviewing, or extending software related to BIM, IFC, OpenBIM, Revit API, Unity, XR, Unreal, Archicad, IfcOpenShell, Speckle, web BIM viewers, BIM databases, graph databases, digital twins, AI/ML datasets, robotics, SLAM, model checking, quantity takeoff, facility management, semantic validation, construction data pipelines, or BIM integration with other technologies. Strongly apply this skill for C# Revit add-ins, C# Unity BIM applications, BIM metadata binding, BIM geometry processing, BIM API development, and BIM data validation. Do not use for general architectural writing, non-BIM 3D graphics, generic Unity games, or ordinary software tasks without BIM data.

  • Ux ui design engineering

    andrzejdelgado/ux-ui-design-engineering Skill

    0★

    This skill guides creation of unique, production-grade frontend UIs that avoid generic "AI slop" looks, and help introduce design engineering principles for building interfaces that feel excellent. It helps to apply 33 principles usually omited in design/coding process.

  • Prompt optimizer skill

    vaibhav-khattar/prompt-optimizer-skill Skill

    no license0★

    Use this skill whenever the user wants to improve, optimize, rewrite, or generate a better version of any prompt they are writing for Claude or another LLM. Trigger on phrases like "improve this prompt", "make this prompt better", "optimize my prompt", "rewrite this prompt", "help me write a good prompt", "how do I prompt Claude to...", "turn this into a proper prompt", "my prompt isn't working", "generate a prompt for me", or any time the user shares a rough idea or instruction and wants it turned into a high-quality Claude prompt. Also trigger when the user says "prompt engineer this", "make Claude do X better", or asks for a system prompt. Always use this skill — even for casual prompt requests — because applying the right techniques transforms mediocre prompts into consistently excellent ones.

  • Pie pieui

    Swarm-AI-Labs/pie-skills/skills/pie-pieui Skill

    no license0★ repo

    Use for any task in the Pie ecosystem — the Python `pie` CLI and FastAPI backend, the TypeScript `pieui` CLI and Next.js/React frontend, or both together. Covers project scaffolding, cards and pages, ajax handlers and the `stored` prop, backend↔frontend metadata sync, the card preview harness and pie-show MCP server, Centrifuge realtime, MongoDB/Beanie, Cloudflare Workers, the Express backend, remote component storage, and PieUI style isolation.

  • Shakedown

    belousov-petr/shakedown Skill

    0★

    Full-stack review of any project - multi-agent systems, pipelines, codebases, or applications. Dynamically discovers project structure, reads all config/code/data, queries databases, tests backup integrity, and analyzes architecture, reliability, efficiency, and security. Produces ranked actionable recommendations. Use when asked to review a project, do a project health check, stress-test a codebase, do a gap analysis, or assess technical debt. Also when user asks 'how solid is this project', 'what is missing', 'find the weak spots', 'what would break first', 'where does this need tightening', 'what's wrong with this project', or 'how mature is this project'. Do NOT activate for simple code reviews, PR reviews, or single-file analysis.

  • Aws s3

    Aryan1718/developer-agent-skills/skills/aws-s3 Skill

    0★ repo

    Handles AWS S3 bucket decisions and operations safely. Use when deciding whether to create a bucket, adopt an existing bucket, manage S3 infrastructure with Terraform, or perform runtime object operations with AWS CLI or SDK. Use when S3 work requires explicit branching between infrastructure management and object operations, with credential checks, region verification, and confirmation gates for destructive deletes.

  • Architect cc workflow

    SizovOleg/project-dna/skills/architect-cc-workflow Skill

    0★ repo

    Universal workflow protocol для пары architect (Claude.ai) + Claude Code в DNA/RNA проектах. Используй ВСЕГДА при: формулировании commands к Claude Code, написании DevPrompt'ов, ревью workflow между sessions, обнаружении систематических ошибок architect-side, планировании phase transitions. Триггеры: «напиши команду Claude Code», «напиши DevPrompt», «как мне дать задачу», «почему architect ошибается», «как валидировать решение», «что architect решает что Claude Code», «верификация спеков», «verification protocol», «error budget», «assumptions section», «boundaries Claude Code architect». Скилл кодифицирует уроки из Phase 1-2 sat-revisit-tool: ~10% architect error rate из-за LLM structural limits, защиты через verification + probe-first + assumption declaration + state refresh + hard iteration limits. НЕ для DNA creation (project-dna) или PRD writing (prd-coauthoring) или scientific methodology (research-with-ai).

  • Cloudflare deploy rules

    motiful/cloudflare-deploy-rules Skill

    0★

    Cloudflare deployment hard constraints. MUST authenticate via scoped API Token in CLOUDFLARE_API_TOKEN env var (loaded from git-ignored .env), MUST bypass HTTP proxy on every Cloudflare API call (curl --noproxy '*', wrangler with NO_PROXY="*" no_proxy="*"), MUST extract account ID from /zones?name=<domain> when token lacks Account:Read and persist as CLOUDFLARE_ACCOUNT_ID. NEVER run `wrangler login` (OAuth breaks behind proxies/VPN), NEVER let a Cloudflare request traverse the local ClashX/HTTP proxy, NEVER commit credentials. Activates on any wrangler command, api.cloudflare.com call, or CLOUDFLARE_* env edit. MUST read SKILL.md BEFORE running wrangler commands, calling Cloudflare API, or editing CLOUDFLARE_* env vars.

  • Mobile webview testing

    wimi321/mobile-webview-testing/mobile-webview-testing Skill

    0★ repo

    Test Capacitor, Ionic, and WebView hybrid apps on real Android devices using Chrome DevTools Protocol (CDP) via ADB. Use when the user wants to test a mobile app on a physical device, debug WebView content, interact with React or Vue state on a real phone, take device screenshots, or test offline and network scenarios. Handles the core challenge that uiautomator cannot see WebView content by using CDP for web elements and uiautomator for native system dialogs.

  • Super engineering devops

    arpitexplores/super-engineering-devops Skill

    0★

    Engineering and DevOps delivery: architecture, build, test, deploy, and operate reliable systems.

    The same file is in 1 other repository

  • Super cloud

    arpitexplores/super-cloud Skill

    0★

    Cloud platform engineering across AWS/Azure/GCP, IaC, networking, containers, and cost optimisation.

    The same file is in 1 other repository

  • Dependabot triage

    akshayrao14/dependabot-triage Skill

    0★

    Triage and fix Dependabot vulnerability alerts in JavaScript/TypeScript repos (Node.js services AND browser frontends). v2.1 workflow with Standard (defensive) and Fast-Track (low-risk) modes — defensive minimal-patched versioning, exposure mapping (Public/API · Client-Bundle · Internal/Dev), CI workflow inspection to detect every PM in play, mandatory lockfile parity check across every PM that touches package.json, changelog scrape with BREAKING/DEPRECATED/MIGRATION flagging, and safety interlock before applying bumps. Fast-Track mode skips changelog + detailed exposure for Internal/Dev or CVSS<7 alerts, but parity check + dual-write are non-negotiable. Covers npm, pnpm, yarn, bun lockfiles. Use when the user shares a Dependabot URL, asks to fix CVEs, or asks which vulnerability to pick first.

  • Agent test with report

    tnagatomi/skills/skills/agent-test-with-report Skill

    no license0★ repo

    Drive the agent-browser CLI to exercise the features a pull request changes, then post an evidence-only findings report back to the PR. Depends on the agent-browser skill (https://github.com/vercel-labs/agent-browser) for the actual browser operation. Use this skill when the user wants an agent to manually test a PR in a real running app and leave a report on the PR, with phrases like "agent-test this PR", "browser-test the PR and comment results", "run exploratory testing and post a report", "check this change in the running app and report on the PR". The report collects evidence (operations, screenshots, findings, unverified scope) for a human reviewer — it never produces a pass/fail verdict.

  • Ref sp agents hooks

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-agents-hooks Skill

    0★ repo

    Author agent lifecycle hooks that run deterministic shell commands at session, prompt, tool, and stop events across Claude Code, GitHub Copilot CLI, VS Code, and Gemini CLI. Use when: creating or editing a hook, choosing a lifecycle event, writing a hook script that reads stdin JSON and returns an allow/deny/context decision, making a hook portable across agents, or debugging why a hook does not fire or block.

  • PromptSkill4image

    Ahaaad3759/PromptSkill4image Skill

    0★

    Universal prompt engineering assistant. Deconstructs complex prompts into structured variables, generates bilingual vocabulary banks, identifies domain, evaluates quality, learns new terms, compares prompts, and optionally outputs PromptFill-compatible JSON. Use when a user wants to analyze, split, translate, learn from, compare, or template-ify any AI image/text prompt. Trigger phrases include: "analyze prompt", "split prompt", "extract variables", "create template", "learn vocabulary", "compare prompts", "词库", "提示词拆分", "提示词分析", "创建模板", "学习新词", "对比提示词".

  • Data migration

    geoffsdesk/portage/skills/data-migration Skill

    0★ repo

    Plan and (with confirmation) execute data migrations from AWS data services to GCP equivalents — RDS to Cloud SQL or AlloyDB, ElastiCache to Memorystore, S3 to GCS, MSK to GCP Kafka or Confluent Cloud — and the secrets/config moves that go with them. Produces per-data-system runbooks, replication plans, validation gates, and cutover scripts. Use after storage-translation, when "plan our RDS migration", "migrate Redis to Memorystore", or "data layer plan for the GKE move".

  • Triz contradiction

    christianmerkwirth/triz-skills/skills/triz-contradiction Skill

    no license0★ repo

    Resolves software engineering contradictions by identifying conflicting parameters and suggesting principles.

  • Bruno cli

    Tusquito/skills/bruno-cli Skill

    0★ repo

    Use when the user is running, testing, importing into, or CI-integrating Bruno API collections — anything involving `bru`, `bru run`, `bru import`, `@usebruno/cli`, `.bru` files, Bruno environments, or Bruno HTML/JSON/JUnit reports. Also trigger when they ask to wire API tests into GitHub Actions or Jenkins, convert an OpenAPI/WSDL spec into a Bruno collection, data-drive requests from CSV/JSON, filter requests by tags, configure mTLS/client certs or proxies for API tests, or debug Bruno scripts that broke after upgrading (safe vs developer sandbox). Trigger even when the user doesn't say "Bruno" explicitly but mentions `bru run`, `bruno.json`, a `.bru` file path, or `@usebruno/cli`.

  • Hearing adr design docs

    tuki0918/skills/skills/hearing-adr-design-docs Skill

    no license0★ repo

    Convert rough engineering notes, spoken requirements, architecture memos, issue comments, meeting transcripts, or bullet lists into an ADR or design document. Use when Codex should structure an ambiguous technical decision into background, problem, goals, constraints, assumptions, options, decision, rationale, risks, rollout, migration, and unresolved questions, and when the output may need to fit repository docs, issues, RFCs, or PR descriptions. Trigger on requests such as "ADRを書いて", "設計書にして", "Design Docに落として", "選択肢を整理したい", "設計の背景と判断理由をまとめたい", "口頭メモから設計文書を作りたい", or "雑なメモをADRにしたい".

  • Api test skill

    fxckcode/skills-kit/skills/api-test-skill Skill

    0★ repo

    Protocol-first, client-agnostic skill for testing REST APIs end-to-end from the terminal. Detects OS and HTTP client automatically, constructs requests with env var references for secrets, interprets responses, infers auth and Content-Type, diagnoses errors, supports request chaining and response assertions. All output is secret-redacted before display. Trigger: When user says "test API", "HTTP request", "curl", "REST call", "API E2E", "testear API", "llamada HTTP", "probar endpoint", "API test", "call endpoint", "send request", "make request", "hit endpoint", "enviar request", "probar API", "test this endpoint", "call this endpoint", "hit this URL".

  • Trivy security scan

    sokratisg/trivy-security-scan/skills/trivy-security-scan Skill

    0★ repo

    Run local Trivy CLI security scans and summarize remediation for severe findings. Use when an AI agent needs to scan projects, repositories, container images, SBOMs, root filesystems, or IaC/config files with Trivy for vulnerabilities, misconfigurations, secrets, or license findings; prioritize HIGH and CRITICAL findings; explain mitigations or fix actions; generate SARIF/SBOM-style reports; or advise on Trivy MCP without requiring an Aqua subscription.

  • Goal prompt generator

    srinitude/hermes-goal-prompt-generator/skills/goal-prompt-generator Skill

    0★ repo

    Generate isolated optimized Markdown goal prompts plus a paired ANALYSIS/BOOTSTRAP/RED/GREEN/REFACTOR TDD task list YAML that any coding agent can dynamically update through its building process. Use when a user asks to enhance, structure, validate, or save a goal prompt without executing it. Do NOT use as an automatic `/goal` preflight, slash-command interceptor, goal-loop hook, or to execute the generated goal or its task list; this skill only produces and validates the standalone prompt file and its companion task list YAML.

  • Handoff resume

    iTofu/handoff-skills/handoff-resume/skills/handoff-resume Skill

    0★ repo

    Use when user wants to resume work from a previously saved handoff document, typically after running /compact, or when starting a session that continues earlier work. Triggers on "/handoff-resume", "从 handoff 恢复", "继续上次的工作", "resume handoff", "compact 之后继续".

  • Analyze code

    lgtm-hq/ai-skills/skills/analyze-code Skill

    0★ repo

    Code-level quality analysis. Use when asked to review code for smells, security issues, implementation quality, or test coverage.