agentsclimarketplace

Engineering

98,276 rows, by stacks then stars

  • Agentic dev loop

    dimsedra/moatcraft-skills/.agents/skills/agentic-dev-loop Skill

    1★ repo

    Orchestrate the continuous agentic development loop. Routes between brand-product-alignment, front-end-designer, backend-architect, progress-mapper, implementation-tdd, alignment-audit, code-review, and explain-and-teach. Manages the state machine, cascade protocols, rollback, and Loop Summary. Use when guiding a feature, refactor, or iteration through the full development loop. Do NOT use as a direct implementation skill (delegate to implementation-tdd instead).

  • Agent stack

    14BryanEspinoza/agent-stack Skill

    1★

    Meta-skill de orquestación — cómo el agente debe pensar, detectar, decidir y actuar en proyectos frontend, evitando redundancia y alucinación.

  • Prompt triwizard

    HiMyNameIsDavidKim/prompt-triwizard-skill/skills/prompt-triwizard Skill

    1★ repo

    Use when writing, refactoring, or evaluating LLM prompts (system prompts, user prompts, few-shot examples, or tool-call schemas) for agent pipeline nodes or stages. Triggers on: "write a system prompt for this agent", "improve this LLM instruction", "evaluate this prompt", "add few-shot examples to this node". Does NOT trigger for general coding, debugging, tests, or non-LLM tasks.

  • Add skill

    Paldom/github-skills/.claude/skills/add-skill Skill

    1★ repo

    Authors or improves an Agent Skill in this repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, iterate. Use when the user asks to create, add, write, refine, or fix a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repository or editing infrastructure (hooks, CI, the validator/scripts, docs).

    The same file is in 11 other repositories

  • Agent config reference

    2702207741-dev/agent-skills-pipeline/agent-config-reference Skill

    1★ repo

    Use when the user asks about config.yaml, CLAUDE.md, .cursor/rules, .codex config, agent setup, or skill installation. Use when the user says 配置agent, 安装skill, 迁移skill, or needs to understand platform-specific config differences across Hermes Agent, Claude Code, Codex CLI, and Cursor.

  • Bootstrap sdd tdd

    kxdds/sdd-tdd/skills/bootstrap-sdd-tdd Skill

    1★ repo

    Use when a project needs the OpenSpec + Superpowers sdd-tdd (spec-to-plan-to-TDD) workflow checked, installed, and configured -- or cleanly removed -- in any coding agent (Codex, Claude Code, Cursor, Antigravity, OpenCode, Gemini CLI, Copilot CLI, or others).

  • Humanizer cs

    ranxi2001/humanizer-cs/skills/humanizer-cs Skill

    1★ repo

    Revise AI-assisted software-engineering communication without changing its technical claims. Use for GitHub issues, pull request titles and bodies, code review comments, review replies, maintainer discussions, engineering summaries or status updates, and English-Chinese translation when the text must sound like a precise, credible developer rather than a chatbot or article writer. Also use to audit drafts for fabricated verification, vague evidence, inflated certainty, unclear review severity, status drift, terminology drift, excessive politeness, or generic AI phrasing. Do not use it to evade AI-detection systems or bypass repository disclosure and authorship policies.

  • Adopt existing project

    notwld/engineering-baseline/skills/adopt-existing-project Skill

    1★ repo

    Safely adopt, audit, production-harden, restructure, or refactor an existing application after Engineering Baseline is installed. Use on first run when `.engineering-baseline-lock.json` has `adoption.status: pending`, and whenever a user asks to make an existing repository production-ready, apply all baseline/security frameworks, correct its directory structure, reduce complexity with Ponytail, or introduce Superpowers without breaking behavior. Begin with read-only context gathering, present findings and required questions, and make no project changes until the user explicitly approves a proposed plan.

  • Agent llm

    ksed8/cc-loopkit/.claude/skills/agent-llm Skill

    1★ repo

    Patterns for building on the Claude/Anthropic API — agent loops, tool design, prompt structure, structured output, context management, prompt caching, and evals. Use when writing code that calls Claude, designing an agentic loop, defining tools for an LLM, building RAG or an LLM-judge, or debugging refusals, truncation, streaming, or tool-call failures.

  • Octopus cli

    olsh/octopus-deploy-skills/plugins/octopus-cli/skills/octopus-cli Skill

    no license1★ repo

    Drive the Octopus Deploy CLI (`octopus`) for releases, deployments, runbooks, task logs, projects, environments, tenants, spaces, deployment targets, packages and variables. Use this whenever the user mentions Octopus Deploy, pastes a `*.octopus.app` URL, asks why a deployment failed, wants to cut/promote/deploy a release, run a runbook, check deployment or task status, read a task log, or push packages and build information — even if they never say "CLI". Read this before running any `octopus` command: the CLI prompts interactively by default and has hard gaps (no task list, no log retrieval, no approvals) that require a documented REST escape hatch.

  • Deai zh gpt style

    YanhanLi/deai-zh-gpt-style/skills/deai-zh-gpt-style Skill

    1★ repo

    Use when editing Chinese or mixed Chinese-English/number text to reduce GPT-5.5/GPT-5.4 style habits, formulaic AI phrasing, over-structured wording, unnatural chat phrasing, or unwanted spaces between Chinese and English/digits.

  • Ib suite

    luyangkk/ib-suite/skills/ib-suite Skill

    1★ repo

    Read-only Interactive Brokers toolchain index and onboarding. Use when orienting across the ib-suite skills, running first-run setup (venv + live/paper config), or deciding which IB skill to run and in what order: ib-sync ingestion, live account/positions/daily-P&L/options overviews, Flex trade or dividend history, or the offline ib-analyze report. It runs nothing itself — the sub-skills do the work and never place, modify, or cancel an order.

  • Skillxray

    munzzyy/skillxray/skills/skillxray Skill

    1★ repo

    Scan an AI agent skill, plugin, or MCP bundle for security and hygiene problems before installing or trusting it - prompt injection in the instructions, hidden/invisible Unicode, dangerous commands (curl-pipe-sh, reverse shells), data exfiltration, hardcoded secrets, and auto-running hooks. Use before adding a third-party skill or plugin, before wiring up an MCP server someone else wrote, or whenever you're about to trust a SKILL.md you didn't write. Returns an A-F grade and a per-finding report.

  • Groundwork

    harsh220601/groundwork-agent-skill/groundwork Skill

    1★ repo

    Evidence-first engineering methodology that makes a coding agent work and verify like a senior engineer. Use for ANY software task - writing code, building features, debugging, fixing bugs or failing tests, repairing broken builds or red CI, refactoring, code review, investigating errors, exploring or onboarding onto an unfamiliar codebase, researching a library/API/framework, scripting, configuration, performance work. Also use when about to state facts about code or APIs, when tests pass but confidence is low, when a task seems done, or on first contact with any repository. Provides a verification loop, an anti-hallucination protocol with claim tagging, a debugging playbook, a deep-research protocol, and a project map + learnings log that make every session smarter than the last. Includes the standing-orders reasoning layer for any answer, code or not: intent reading, Certain/Likely/Assumption markers, self-attack, completeness, refusal rules, and a final gate before sending.

  • Clics

    P-Essonam/clicsdev/skills/clics Skill

    1★ repo

    Query Clics analytics and manage projects, goals, funnels, and sessions through the Clics MCP server (`@clicsdev/mcp`), with the `clics` CLI (`@clicsdev/cli`) as a fallback. Use when a user asks about their analytics, mentions Clics, works with the Clics toolset, verifies Clics manually, or needs to choose between MCP and CLI.

  • Skill

    Odinary-AI/ai-system-engineer-skill/skill Skill

    1★ repo

    Use as a proportional lifecycle control layer for AI-assisted system development when Greenfield or existing system work crosses product intent, architecture, authority, lifecycle, cross-module implementation planning, validation claims, system refactoring, migration, recovery, or release boundaries. Do not use for routine coding, mechanical local refactors, or a single prompt unless they expose a system-level boundary or claim.

  • Writing gpt 5 6 prompts

    CodingCossack/writing-gpt-5-6-prompts Skill

    1★

    Use when creating, rewriting, optimising, reviewing, or handing off prompts, system prompts, developer instructions, agent briefs, delegation prompts, task specifications, or reusable prompt templates for GPT-5.5 or GPT-5.6, especially when wording is procedural, repetitive, over-scaffolded, vague about success, or unclear about evidence, autonomy, tools, validation, output, or stopping.

  • Refine prompt

    basuev/pi-prompt-refiner/skills/refine-prompt Skill

    1★ repo

    Refines a rough prompt into a precise, ready-to-send Codex prompt. Use when the user asks to refine, improve, rewrite, optimize, or make a prompt more effective.

  • Clean skill python

    RudrenduPaul/skillguard/examples/clean-skill-python Skill

    1★ repo

    A second minimal, well-behaved fixture skill (Python hook) used to test SkillGuard's happy path (zero findings, exit code 0).

  • Project code study

    1bkunnn-cyber/project-code-study Skill

    1★

    This skill should be used when a user asks to study a software or ML repository step by step, "按调用顺序读源码", "逐个类/函数学习", connect code with a paper, trace tensor shapes, reproduce or modify a project, preserve questions across sessions, or discover related methods and extension ideas.

  • Prove it

    loyalmemories/prove-it/skills/prove-it Skill

    1★ repo

    Require concrete, task-relevant evidence before declaring coding work complete. Use when implementing, fixing, refactoring, migrating, reviewing, or preparing software for release; when a user asks to verify, validate, test, prove, double-check, or show that a change works; or when completion claims should be backed by tests, builds, static checks, runtime checks, screenshots, or other observable results. Apply to code and configuration changes across ecosystems, including agent-authored work. Do not use evidence from an earlier revision as proof of the current revision.

  • Business idea evaluation

    gordonling-labs/skills/skills/business-idea-evaluation Skill

    1★ repo

    Critically evaluates business ideas, startup concepts, product directions, and market-entry plans using market, competition, business-model, unit-economics, execution-risk, and validation lenses. Use when a user asks whether an idea is viable, requests a neutral critique or stress test, compares opportunities, or says "should I build this?", "評估這個商業想法", or "分析這個創業點子". Produces steelmanned arguments for and against, labeled assumptions, a scored rubric, concrete validation tests, and a calibrated verdict. Do not invoke for standalone idea brainstorming, business-plan writing for an already approved concept, technology-stack selection after the product decision, or specific contract advice without a business evaluation. When a business-evaluation request also asks for personalized investment allocation, specific legal advice, or illegal optimization, invoke only to apply the boundary and redirect safely; do not provide that advice.

  • Opencode commander

    stone623101-cloud/opencode-commander/plugins/opencode-commander/skills/opencode-commander Skill

    1★ repo

    Orchestrate multiple OpenCode CLI workers from Codex, Claude Code, Cursor, or another coding agent. Use when the user explicitly asks to split a complex research, analysis, planning, review, or implementation task across OpenCode agents; requests parallel OpenCode execution; wants iTerm split-pane visibility; or asks the host agent to act as the overall coordinator and synthesize worker results.

  • Ai incident analyst

    anmolg1997/prepostmortem-skills/ai-incident-analyst Skill

    1★ repo

    Use when analyzing failures of AI/LLM/agentic systems, an agent took a destructive or unintended action, a chatbot hallucinated with real-world consequences, prompt injection or jailbreak, model-quality or behavior regression after an update, reviewing an agent system design for failure modes before launch, writing a postmortem for an AI incident, or when the user mentions AI incidents, agent safety review, guardrails, prompt injection precedent, or "has an AI system done this before".

  • Agentify

    avnath13/agentify/agentify Skill

    1★ repo

    Design production-grade agentic AI systems from a natural-language use case. Runs a clarification loop, walks grounded decision trees (workflow vs agent, RAG vs fine-tuning, single vs multi-agent, autonomy tiers), and emits a detailed enterprise system design document with embedded interactive architecture, sequence, and data-flow diagrams. Every decision cites authoritative sources (Anthropic, OpenAI, OWASP, NIST, cloud well-architected frameworks, peer-reviewed surveys). Supports a production mode (buildable design) and an interview mode (system design interview framing with tradeoffs and probes). Use when the user wants to design, architect, review, or plan an AI agent, agentic workflow, RAG system, LLM application, copilot, or GenAI product, or asks "how should I build" an AI-powered system, or wants agentic system design interview practice.

  • Fde copilot

    inbusiness23/fde-skill/skills/fde-copilot Skill

    1★ repo

    Start here for a practical forward-deployed engineering workflow. Help a small or midsize organization improve one costly workflow at a time, coordinating discovery, solution design, safe deployment, and value review with a cautious 30-day payback target. Use for FDE work, workflow improvement, AI-agent project selection, rollout planning, ROI review, or deciding whether a process needs AI at all.

  • Project orchestrator

    code-wahaha/project-orchestrator-skill/skill/project-orchestrator Skill

    1★ repo

    Guide any software project from an idea or existing codebase to an approved specification, governed implementation, verification, and handoff. Use for creating, extending, migrating, refactoring, or taking over mini programs, web apps, mobile or desktop apps, APIs, backend services, automations, and other software; for both 0-to-1 projects and 1-to-100 existing or legacy projects. Trigger when a user says they have an idea, wants to build or change a product, asks to plan before coding, needs project rules or architecture, wants an existing repository audited, or wants guided, assisted, or automatic project execution with reusable preferences.

  • Change with proof

    CodingCossack/agent-systems/skills/change-with-proof Skill

    1★ repo

    Use when implementing, debugging, refactoring, testing, reviewing, or completing non-trivial changes to software — bugs, flaky tests, regressions, refactors, migrations, API or schema changes, auth, permissions, secrets, payments, webhooks, persistence, uploads, routing, exports, UI and user-visible surfaces, external integrations, dead-code or legacy removal, and long-running or resumed multi-step work. Do not use for pure explanation or Q&A, greenfield scaffolding with no existing behaviour at stake, prompt writing, dedicated security audits, or visual design.

  • Claude remote control server

    T0mSIlver/skills/claude-remote-control-server Skill

    1★ repo

    Install, update, inspect, or troubleshoot persistent Claude Code Remote Control servers for repositories. Use when the user asks to run `claude remote-control`, create a repo-specific remote-control server, make it survive reboots, manage user systemd services such as `claude-rc-skills.service`, configure `--spawn worktree`, service names, session names, prefixes, capacity, lingering, or add another repo to claude.ai/code remote control.

  • Codebuddy acp bridge

    yesman-engineer/codebuddy-acp-bridge Skill

    1★

    Delegate execution from Codex, Claude Code, or another AI coding agent to a local CodeBuddy Code HTTP server through ACP. Use when the user asks for "Codex plans, CodeBuddy executes", "use CodeBuddy as executor", "交给 CodeBuddy 跑/执行", "强模型规划便宜模型执行", or wants an AI agent to plan a task, send a bounded subtask to CodeBuddy, wait for login if needed, collect the result, and validate it.

  • Ctx adopt

    motiful/ctx/skills/ctx-adopt Skill

    1★ repo

    Bring an EXISTING project (brownfield) under ctx with minimal disruption. Decides where the /ctx folder lives (in-repo directory by default, or a gitignored symlink to an external sibling store named project-name-ctx when the context must not ship with public code), which pointer file announces it (respect the project's existing AGENTS.md/CLAUDE.md; else the running agent's native one), and ROUTES the actual doc-writing to the domain skills (ctx-merge / ctx-spec / ctx-progress / ctx-report) rather than writing shallow versions itself. Use when a user says "apply ctx to this existing repo / bring this repo under ctx", when deciding whether ctx must stay separable from published code, or when onboarding a messy existing repo.

  • Prompt master for anything

    jasperkong1996xx/prompt-master-for-anything/skills/prompt-master-for-anything Skill

    1★ repo

    Compile rough or incomplete requests into two copy-ready AI prompts: Concise Universal and Advanced Max. Use when a user asks to create, improve, rewrite, translate, structure, or adapt a prompt for ChatGPT, Claude, Gemini, Codex, Copilot, DeepSeek, Qwen, or an unspecified AI in English, Mandarin Chinese, or bilingual form.

  • Skill monitor

    wei63w/skill-monitor/skills/skill-monitor Skill

    1★ repo

    Monitor local Agent Skill usage, Rules/AGENTS.md context bloat, and Task / sub-agent startup cost (starts × system-prompt volume). Use for skill frequency, skill token estimates, unused skills, context bloat, AGENTS.md / rules size, subagent cost, backfill from transcripts, or project skill tracking. Also use for skill 监控, skill 统计, skill 频率, Rules 膨胀, AGENTS.md 体积, 子 Agent / Task 成本.

  • Founder debugger

    1elasmarjad/yc-founder-skills/plugins/yc-founder-skills/skills/founder-debugger Skill

    1★ repo

    Diagnose why an early-stage startup is stuck and route to the earliest broken link across problem, user, MVP, activation, retention, pricing, positioning, distribution, execution, runway, and fundraising. Use before recommending tactics when the founder presents ambiguous symptoms, conflicting advice, weak growth, stalled sales, or low runway.

  • Codex windows sandbox troubleshooting

    h8nc4y/codex-windows-sandbox-troubleshooting Skill

    1★

    Triage Codex sandbox startup failures on Windows by failing layer — config load, sandbox setup helper, process creation, in-sandbox runtime — instead of guessing. Use on symptoms like "windows sandbox: runner error: CreateProcessAsUserW failed: 5" (often only on the agent execution path via codex mcp-server), Git Bash / MSYS2 failing only inside the sandbox with "CreateFileMapping ... Win32 error 5" or "couldn't create signal pipe", the elevated setup helper's "SetNamedSecurityInfoW failed: 5", every session bricked by "data did not match any variant of untagged enum FilesystemPermissionToml" after a config.toml permissions edit, or denied writes outside the workspace despite a config write grant, including a permission profile ignored because legacy sandbox settings are loaded. Covers the codex sandbox CLI bisect, PowerShell fallback for Git Bash, config editing, and least-privilege recovery without disabling the sandbox.

  • Access triage

    ymedlop/kuberoutectl-skills/skills/access-triage Skill

    1★ repo

    Diagnose why Kubernetes access is not working, and check credential health. Handles prompts like 'kubectl says unauthorized', 'I cannot reach this cluster', 'my login expired', 'a cluster disappeared from the list', 'what version am I on'. USE FOR: baseline status (version, current selection, cache freshness, doctor), credential health and action hints, renewing an expired identity, telling a permissions boundary from a deleted cluster. DO NOT USE FOR: first-time provider setup (use inventory-discovery), or choosing which cluster to switch to (use target-selection).

  • Byteplus cloud

    Straits-AI/byteplus-cloud-skill/skills/byteplus-cloud Skill

    1★ repo

    Plan, provision, deploy, inspect, and troubleshoot applications on BytePlus using the official bp CLI, BytePlus Cloud Control Terraform provider, Edge Functions nest CLI/MCP, and product SDKs. Use for BytePlus architecture selection, authentication, infrastructure changes, application deployment, ModelArk Seed/Seedream/Seedance, Seed Speech TTS, TOS, ECS, VPC, VKE, veFaaS, API Gateway, databases, monitoring, or migration work.

  • Assemble agent team

    miraclefeb/assemble-agent-team/skills/assemble-agent-team Skill

    1★ repo

    Dynamically assemble and orchestrate AI workstreams for complex tasks, cross-functional research, and consequential decisions. Use when users ask for multi-agent analysis, an agent team, expert-team mode, subagent collaboration, parallel research, explicit handoffs, or a lead synthesis; when three or more decision-changing perspectives are needed; or for 多 Agent 协作、专家编队、自主编队、跨部门方案、复杂决策、并行调研、接棒分析. Do not use for simple edits, single-fact lookups, narrow summaries, or already-specified implementation tasks.

  • Examples

    sohangujari/fable-to-opus-skills/examples Skill

    1★ repo

    A disciplined phase-gated workflow for any non-trivial coding task - implementing features, refactoring, bug fixing, or building modules. Use this skill whenever a coding task involves more than a trivial one-line change, whenever correctness matters, whenever the task touches multiple functions or files, or whenever you are about to write code without a written plan. Especially use it when tempted to "just start coding," when a fix didn't work the first time, or when deciding whether something is actually done.

  • Wolverine skill

    zetroot/wolverine-skill Skill

    1★

    Comprehensive guidance for building .NET applications with the Wolverine framework (v6.x). Covers sagas, message transports (RabbitMQ, Kafka, AWS, Azure, GCP, NATS, MQTT, Redis, Pulsar, SignalR, TCP, gRPC), HTTP endpoints, durable messaging with inbox/outbox, health checks, Marten event sourcing, error handling, validation, testing, code generation/AOT, rate limiting, message batching, node agents, observability, and migration from MediatR/MassTransit. Use when building, configuring, or troubleshooting Wolverine applications, setting up messaging infrastructure, implementing long-running workflows, or creating HTTP APIs. Part of the "critter stack" with Marten.

  • Codex safe workflow

    KevinBigham/codex-safe-starter/.agents/skills/codex-safe-workflow Skill

    1★ repo

    Use inside Codex Safe Starter for repo-local setup, portability, safety, validation, eval, and public Git workflow changes. Do not use for unrelated app coding tasks.

  • Agentic coverage report

    jpbaking/agentic-tests/skills/shared/agentic-coverage-report Skill

    1★ repo

    Read-only report of where the agent-generated tests (*.agentic.spec.ts, *AgenticTest.java, test_agentic_*.py, ...) stand — agent-tests-only coverage, goal MET/NOT MET from agentic-test-plan.md, and any failing agent tests. Use when asked how the agent tests are doing, what coverage the agent tests reach, or whether the recorded goal is met. Never creates, edits, or deletes files.

  • Add component

    IntelliHelper/agent-skills/skills/add-component Skill

    1★ repo

    Install IntelliHelper UI components into a project correctly: init components.json, resolve dependencies, run CLI add, verify imports, and audit. Use when the user wants to add, install, scaffold, update, or diff IntelliHelper/shadcn-style components, fix missing components.json, or wire the registry. Triggers: "add button", "install dialog", "npx @intellihelper/cli", "init components.json", "update components", "registry add".

  • Agent face

    fcavalcantirj/agent-faces/skill/agent-face Skill

    1★ repo

    Gives an AI agent a talking, animated, lip-syncing voice face. You speak, it transcribes (in-browser Whisper), a pluggable brain replies, the reply is spoken back and drives a 12-emotion particle face with real audio-driven lip-sync. Ships as a Next.js web app you run on localhost, deploy to Vercel, or self-host next to your agent. USE WHEN the user wants to give their agent a face, talk to their agent by voice and watch it lip-sync, or deploy a voice face UI. Trigger phrases include "give my agent a face", "talk to my agent by voice", "deploy a face UI", "lip-sync face", "voice face for my agent", and "put a face on Hermes/openclaw". The brain can be a fresh hosted API OR your own already-running agent.

  • Llm wiki

    brantshin/super-dev/skills/llm-wiki Skill

    1★ repo

    Maintain a Git-native, LLM-curated project knowledge base that compounds across tasks. Use when initializing or restructuring a project Wiki, staging source material in an inbox, ingesting verified documents into cross-linked Markdown, querying project knowledge with source paths, promoting reusable findings from engineering work, or linting indexes, metadata, provenance, links, and stale content. Keep transient task state and private memory outside the Wiki.

  • Breakdown connectivity

    PeaceCraft-LLC/breakdown-agent-connectivity/skills/breakdown-connectivity Skill

    1★ repo

    Diagnose Internet, DNS, Wi-Fi, packet loss, latency, endpoint reachability, browser navigation, API, upload, download, MCP, and cloud-tool failures with Breakdown on macOS. Use when connectivity may explain a failed or flaky agent task, before long or unattended network-dependent work, after a user-visible outage, or when producing a connectivity readiness report. Also use to install Breakdown, connect its local MCP server, or discover the evidence tools it provides.

  • Hyper cloaking

    alpoxdev/hyper-cloaking/skills/hyper-cloaking Skill

    no license1★ repo

    Use this skill when the user asks an MCP-capable agent to install, configure, or drive authorized CloakBrowser browsing through the stateful `hyper-cloaking-mcp` server, including setup repair, server build/registration, typed tool execution, provider actions, lifecycle cleanup, and evidence-backed completion. Do not use for ordinary stock-browser automation, generic Playwright tests, or unauthorized bot-detection evasion.

  • Yw skill foundry

    yuwen-cool/yw-skill-foundry Skill

    1★

    Use when creating, optimizing, reviewing, or extracting reusable Agent Skills, SKILL.md, AGENTS.md, prompts, or agent instructions; or when designing instruction architecture and evals. Triggers on 写/改/审查 skill, skill 质量, 提示词工程, 指令设计, create/optimize/review skill, prompt engineering, instruction design. Not for application code, multi-agent runtime architecture, general prose, or explanation/summary/translation requests that do not create or change instructions.

  • Agent skills manager

    ccckfg/agent-skills-manager/skill/agent-skills-manager Skill

    no license1★ repo

    Manage local AI Agent Skills with the dependency-free scripts bundled inside this Skill. Use when inspecting, comparing, importing, or synchronizing Skills across Claude Code, Codex, Cursor, Antigravity, Gemini CLI, GitHub Copilot CLI, Windsurf, opencode, Kiro, Pi, Qoder, Trae, CodeBuddy, Kimi Code, iFlow, Qwen Code, Lingma, MiMo Code or the shared ~/.agents directory; listing their MCP servers; or safely reviewing MCP and other agent configuration. The bundled script works without installing the optional TUI.

  • Future regret

    acost1a/future-regret/skills/future-regret Skill

    1★ repo

    Use when the user is about to commit to an architecture, data-model, dependency, or design decision on an existing codebase (picking a database or schema shape, build vs buy, adopting a library or pattern, locking an API contract, or "let's just do X for now"), or asks what they'll regret later ("will I regret this", "what will bite us", "future-proof this"). Run BEFORE writing the code or agreeing. Do NOT use for brand-new product ideas, routine bug fixes, or trivially reversible choices.

  • Reflect

    LorcanChinnock/reflect Skill

    1★

    Use at the end of a session, or when the user says "/reflect", "reflect on this session", "save what you learned", or "update your memory". Reviews the session for token-wasting detours, reusable workflows, blockers, corrected assumptions, and undocumented quirks, filters hard, then routes each survivor to its home: lean personal auto-memories (editing, merging, and deleting as readily as adding) or, for a durable convention the whole repo needs, a proposed edit that lands via a normal PR — amending a fitting existing doc (an @-referenced sub-file, or an AGENTS.md section) when one exists, otherwise a lean .claude/memories/ note @-imported from CLAUDE.md, never inlined into CLAUDE.md's own body. Proposes a concise change list before writing. Works best with Claude Code auto-memory, but the project-instructions route also works with it off; needs no other skill.

  • Ship codex max orchestrate

    smkuxi71-hash/skill-ship-max/core/.agents/skills/ship-codex-max-orchestrate Skill

    no license1★ repo

    Implementation-only release-slice G3 loop for ship-codex-max v2 with TDD, medium-only adaptive Coach, hard budgets, build leases and a committed review ledger.

  • Computer

    vivekkartha/terminal-computer-use/skills/computer Skill

    1★ repo

    Terminal-first Computer Use: control files, folders, apps, clipboard, notifications, screenshots, and multi-step desktop workflows via shell scripts (bash/Python). Works with Claude Code, Cursor, Codex, Grok, Gemini CLI, and any agent with a terminal. Reuse scripts next to this SKILL.md. Use when the user wants computer use, desktop control, open/quit apps, organize files, Finder automation, or runs /computer.

  • Nestjs caching queues

    dkmqflx/nestjs-best-practices-plugin/plugins/nestjs-best-practices/skills/nestjs-caching-queues Skill

    1★ repo

    NestJS caching and background-job queue best practices. Use when adding caching or async job processing to NestJS — CacheModule, cache-manager, Redis, or BullMQ/Bull queues. Triggers on CacheModule, @InjectQueue, @Processor, cache TTL, or background jobs.

    The same file is in 1 other repository

  • Pw playwright fieldkit

    jpbaking/playwright-fieldkit/skills/shared/pw-playwright-fieldkit Skill

    1★ repo

    Playwright FieldKit: gives coding agents hands and eyes on the web — crawl, debug, record, and test live sites via deterministic scripts; portable Agent Skill for Codex, Claude Code, Antigravity, and Cline

  • Add skill

    Paldom/skillskit/skills/add-skill Skill

    1★ repo

    Authors or improves an Agent Skill in the current repo via the eval-first workflow - scope one purpose, write trigger evals, draft SKILL.md, validate, benchmark. Use when the user asks to create, add, write, refine, fix, or benchmark a skill ("add a skill for X", "improve triggering of Y"). Not for scaffolding a new repo (create-skill-repo) or distilling research packs (skill-from-research).

  • Handoff spec

    cskwork/handoff-spec-kit/skills/handoff-spec Skill

    no license1★ repo

    기획-개발 핸드오프 기획서를 표준 형식(12개 섹션, 간이/전체 경로)으로 인터뷰하여 작성하거나, 작성된 기획서에서 명확화 질문 추출과 Jira 티켓 분할을 수행한다. Use when 사용자가 기능 기획서·핸드오프 문서·스펙 작성을 요청할 때, 스펙을 티켓으로 분할할 때, 기획서 리뷰·명확화를 요청할 때, 또는 handoff-spec을 언급할 때.

  • Debug with evidence

    himanshi-28/coding-agent-skills/skills/debug-with-evidence Skill

    1★ repo

    Explicit-invocation workflow for systematic debugging that reproduces failures, forms falsifiable hypotheses, collects runtime evidence, proves root causes, adds regression tests, and verifies targeted fixes. Use only when the user directly invokes the debug-with-evidence skill.

  • Prompt compile

    v60samurai/agent-skills/skills/workflow/prompt-compile Skill

    1★ repo

    Compile a high-quality task brief before executing a medium-or-larger task, then execute against it and verify. Pairs with the prompt-compile-gate hook for deterministic triggering; define-do-verify in one pass.

  • Geo content optimizer

    Nightflight6/open-agent-skills/skills/en/geo-content-optimizer Skill

    1★ repo

    Create, optimize, or audit evidence-backed content for generative answer and search experiences by improving answerability, claim traceability, entity clarity, and original value. Use for GEO content briefs, answer maps, citation-ready claim review, answer-surface-informed optimization, or GEO audits. Do not use as the primary skill for deep question research, ordinary SEO planning, technical SEO implementation, rank or visibility monitoring, generic article editing, fact checking alone, keyword research, or answering a single question.