agentsclimarketplace

Engineering

98,234 rows, by stacks then stars

  • Implementation plan

    BlizzardBlast/frey-skills/implementation-plan Skill

    0★ repo

    Use when the user asks to plan, scope, design, review, refine, or sequence an implementation, feature, known bug fix, refactor, migration, dependency/toolchain change, or other codebase change before editing. Produces a read-only, evidence-backed, implementation-ready plan grounded in the current repository, with affected boundaries, ordered file-level steps, verification, risks, and READY_TO_IMPLEMENT/READY_WITH_ASSUMPTIONS/NOT_READY status. Do not use for direct implementation, code review or merge decisions, root-cause-only debugging, or post-review remediation unless the user explicitly asks for a plan.

  • Xcratch extension debug auto

    xcratch/xcratch-skills/skills/xcratch-extension-debug-auto Skill

    no license0★ repo

    Autonomously debug an Xcratch extension by loading it via the ?extension= query parameter into either the public xcratch.github.io editor or a local scratch-editor dev-server, with the extension served from a local HTTPS live server (https://0.0.0.0:5500/*). Use when: verifying an extension loads, checking console errors, inspecting extension blocks in the Scratch editor UI, or reproducing runtime failures with a specific extension URL — against the published editor (no local checkout needed) or against a local scratch-editor build on port 8601.

  • Prisma schema naming convention best practices

    lazuee/agent-skills/skills/prisma-schema-naming-convention-best-practices Skill

    0★ repo

    Naming conventions for Prisma schemas that map to MySQL tables using snake_case tables, PascalCase columns, id primary keys, ReferencedTableID foreign keys, explicit unique constraints, and idx_ index names.

  • Mcp configure

    launchdarkly/experimental-agent-skills/skills/onboardingV2/mcp-configure Skill

    no license0★ repo

    Configure the LaunchDarkly hosted MCP server during onboarding. Use when the parent LaunchDarkly onboarding skill reaches Step 4 (MCP). Supports Cursor, Claude Code, Windsurf, GitHub Copilot, and other MCP-compatible agents. OAuth authentication; no API keys for the hosted server.

  • Chunked impl

    tnagatomi/skills/skills/chunked-impl Skill

    no license0★ repo

    Implement a feature or fix incrementally by splitting the work into small chunks and building each chunk test-first with the tdd skill's red-green-refactor loop, then committing once tests are green. Depends on the tdd skill (https://github.com/mattpocock/skills/tree/main/skills/engineering/tdd) for the per-chunk red-green-refactor discipline. Use this skill whenever the user asks to implement, build, or fix something with phrases like "implement X chunk by chunk", "commit as you go", "test and commit each step", "incremental implementation", "split this into small commits", or any time the user wants steady, verifiable progress with a clean git history rather than a single big change. Prefer this skill for non-trivial changes that have (or should have) automated tests.

  • Ref sp agents instructions authoring

    swiftpostlabs/agentic-tools/.agents/skills/ref-sp-agents-instructions-authoring Skill

    0★ repo

    Guidance for structuring and maintaining repository instruction files across major agent entry points such as Copilot, Gemini, and Claude. Use when: designing the repo's instruction system, choosing a source of truth, or updating AGENTS.md, GEMINI.md, and .claude/CLAUDE.md together.

  • Brain harness

    0SxD/agent-skills-plugin-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.

  • Codebase audit

    fxckcode/skills-kit/skills/codebase-audit Skill

    0★ repo

    Systematic codebase audit — gap analysis against specs (PRD/SDD), architecture review, code quality assessment, and migration readiness checks. Use when the user asks to review a codebase, compare it to a spec, or assess a project.

  • Vpn toggle

    ng4567/ng-msft-workflow-skills/vpn-toggle Skill

    no license0★ repo

    Ensures the Microsoft corporate VPN is connected before invoking any whitelisted MCP server (plugin) or tool. Reads the user-defined whitelist in vpn-toggle/whitelist.yaml, checks whether the MSFT-AzVPN-Manual connection is up, and runs `rasdial "MSFT-AzVPN-Manual"` to bring it up if it is not. Use whenever about to call a tool from a plugin/MCP server that requires corpnet access (e.g., mcaps-iq, msx).

  • Handoff save

    iTofu/handoff-skills/handoff-save/skills/handoff-save Skill

    0★ repo

    Use when user requests a handoff document before /compact, asks to save current session state for later resumption, or says phrases like "给我一份 handoff", "保存 handoff", "compact 前", "记录当前进度", "save handoff", "before compact". Designed for the handoff → /compact → resume workflow.

  • Mcp mutating tool

    Gowrav-M/agent-skillguard/examples/skills/mcp-mutating-tool Skill

    0★ repo

    Example skill with a bundled MCP descriptor that mutates tools.

  • Python debugger

    xcl1989/CrabAgent/src/crabagent/skills/python-debugger Skill

    no license0★ repo

    Systematically debug Python code using structured error analysis, logging inspection, and test-driven fixes

  • Zh CN

    asdlem/pr-workflow/docs/i18n/zh-CN Skill

    no license0★ repo

    使用项目原生模板、仓库语言/风格一致性、提交前预览和安全的 gh/glab CLI 操作,准备并可选择性创建 GitLab Merge Request 或 GitHub Pull Request。当用户要求准备、编写、预览、创建、提交或打开 MR/PR、合并请求、拉取请求或就绪分支时使用。

  • Empower

    PARS-DOE/doe-skills/empower Skill

    no license0★ repo

    Empower documentation including User Manual and Tech Notes. Use when asked about Empower concepts, EVMS/earned value management, cost/schedule variance analysis, BAC/EAC/ETC forecasting, publevel logic, data quality indicators (DQIs), VAR narratives, CAM responsibilities, WBS/OBS structures, project reporting, charts, dashboards, data uploads/downloads, recalculation, user administration, SSO/authentication, or system configuration.

  • Writing derived artifact claude md

    Fearvox/derived-claude-md/skills/writing-derived-artifact-claude-md Skill

    0★ repo

    Use when initializing CLAUDE.md for a derived or projected directory — symlink view, build cache, mirror, generated docs, materialized projection — where the directory's content is regenerated from an upstream source by a tool or script.

  • Github actions

    mohammaddaoudfarooqi/agent-engineering-skills/skills/github-actions Skill

    0★ repo

    GitHub Actions workflow authoring for AI coding agents. Analyzes a repo's project type, language, and deployment targets, then generates production-grade CI/CD workflows with security hardening, caching, and optimization. Handles greenfield, brownfield, and audits. Use when the user requests GitHub Actions workflows: CI pipelines, CD deployments, release automation, or scheduled jobs, or when existing workflows need auditing, optimizing, or hardening. Triggers on phrases like "set up CI", "add CI/CD", "deploy on tag", "publish to npm/PyPI", "harden this pipeline", "pin actions to SHA", "OIDC", or "audit my workflows", and when creating or editing files under `.github/workflows/`, `action.yml`/`action.yaml`, or `.github/dependabot.yml`. Also triggers when migrating from GitLab CI, CircleCI, Travis, Jenkins, or Drone to GitHub Actions. Do NOT use for non-GitHub CI systems unless migrating TO GitHub Actions, or for general bash scripting, Makefiles, or local build config.

  • Repomap

    balevdev/agentique/skills/repomap Skill

    0★ repo

    Index, search, and graph-traverse multi-repo workspaces with the repomap CLI/MCP tool so every claim about code comes with a repo/file:line citation. Use this whenever work spans more than one repository in a folder: finding where a symbol, table, endpoint, env var, or package is defined or used; impact analysis before a change (who imports this file, who calls this function, who reads or writes this table); orienting in an unfamiliar workspace or microservice fleet; or any moment you are about to grep, glob, or read files across repos to answer a question. Also use it when a folder contains a .repomap directory, when the user mentions repomap, a code index, a call graph, a knowledge graph of their repos, or cross-repo or cross-service research, or when long flows are burning tokens on repeated file reading.

  • Audit loop

    Mercer8964/audit-loop/platforms/claude-code/audit-loop Skill

    0★ repo

    Verify a draft answer by having an independent subagent re-solve the same problem from scratch and a second subagent probe via a different method, then mechanically compare. The subagents never see the draft. Use before delivering any answer where being wrong would be costly AND the claim cannot be fully tested empirically — algorithm correctness, mechanism design, non-measurable numeric estimates, safety/optimality assertions, reasoning on non-obvious invariants. Triage gate routes empirically testable claims to tests (and partially testable claims to test + audit on the uncovered surface). Hard cap 2 spawns. Reports honest disagreement; never silently picks.

  • Ci fix

    bakerstreetco/skills/ci-fix Skill

    0★ repo

    Diagnose and repair failing CI checks with the smallest safe change. Use when asked to fix GitHub Actions, GitLab CI, local test failures, lint failures, typecheck failures, build failures, or release pipeline errors.

  • Openclaw

    kira-0521/agent-skills/railway-openclaw-troubleshoot/openclaw Skill

    0★ repo

    Railway上にデプロイされたOpenClawの接続・起動トラブルシューティング。 gatewayが起動しない、ポート占有(EADDRINUSE)、lsof/fuser not found、 TIME_WAIT、device pairing required、disconnected (1000)、 接続後即切断、モデル設定が反映されない、Slackメンションが届かない、 scope upgrade pending approval、などRailway+OpenClaw固有の問題に対応する。 ユーザーがRailway上のOpenClaw、openclaw gateway、ws://127.0.0.1:18789、 ペアリング、コンテナ内のopenclawなどに言及した時に使用すること。

  • Contract cartographer

    bluefeet/skills/contract-cartographer Skill

    no license0★ repo

    Diagnose the real contract around a user-pointed code target in an existing codebase. Use when the user asks to understand, audit, map, clarify, or review a contract, interface, API, module boundary, subsystem, workflow, or service boundary, especially when callers know too much, tests need awkward mocks, behavior is misused, inputs are broad, side effects are surprising, or the target feels hard to change safely. Do not use for ordinary bugfixes, generic code review, broad architecture brainstorming, or implementing an already chosen refactor.

  • Context engineering

    ashishgoswami01/claude-skill-manager/community-skills/context-engineering Skill

    0★ repo

    Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

    The same file is in 2 other repositories

  • Codex claude handoff

    siglernir-ai/codex-claude-handoff/.agents/skills/codex-claude-handoff/assets/package/templates/.agents/skills/codex-claude-handoff Skill

    0★ repo

    Turn Codex and Claude Code into an accountable engineering pair on one Git task: one agent leads or implements, a different agent challenges and reviews, rejected work can return for bounded correction, and neither ships alone. Durable project-local state preserves scope, decisions, evidence, and the next actor across windows and CLI turns; exact-scope and fail-closed checks stop unsafe or inconsistent progress, while the user retains approval over sensitive actions. Roles can be swapped with explicit user approval. Use when the user explicitly selects or names codex-claude-handoff, requests cross-agent implementation and independent review, setup, diagnosis, role reassignment, or the full supervised workflow. Do not trigger for ordinary project tasks. On first use, request approval before installing the bundled protocol.

  • Test plan generate

    mayashavin/agent-skills/skills/test-plan-generate Skill

    no license0★ repo

    Generate an automation-first test plan for the given feature with a focus on speed, accessibility, and reliability.

  • Choice architecture audit

    walterkken/nobel-process-skills/choice-architecture-audit Skill

    no license0★ repo

    Run a Thaler-inspired choice architecture audit for products, policies, forms, onboarding, pricing, defaults, incentives, and user workflows. Use when Codex is asked to reduce friction, improve decisions, design ethical nudges, identify sludge, or create an intervention plan without removing user choice.

  • Scaffold report

    skyswordw/skillmatrix/examples/scaffold-report/skills/scaffold-report Skill

    0★ repo

    Scaffold a small report tree. Use whenever asked to scaffold the report.

  • Debugging dataverse plugins locally

    xrmghost/xrmghost-skills/skills/debugging-dataverse-plugins-locally Skill

    no license0★ repo

    Run and debug Dataverse / Dynamics 365 / Power Platform server-side C# code on the local machine using the XrmGhost CLI (the `xg` command), instead of deploying to an online instance and reading trace logs. Although named for plugins — the most common case — this applies equally to Custom APIs and any other C# object that runs through the Dataverse pipeline. Use this skill when a plugin or Custom API implementation has just reached a working milestone and could be tried locally, when investigating a reported or production bug in plugin behavior, or when the output of an `xg` run needs to be interpreted and acted on. Part of the XrmGhost toolset.

  • Nodejs cli best practices

    pawel-up/lupa/.agents/skills/nodejs-cli-best-practices Skill

    0★ repo

    Guide and audit Node.js CLI application development against 37 established best practices covering UX, distribution, interoperability, accessibility, testing, error handling, development setup, analytics, versioning, and security. Use this skill when building, extending, reviewing, or scaffolding a Node.js CLI — including when someone says "audit my CLI", "review my CLI code", "I'm building a CLI tool", or asks about adding argument parsing, error handling, color output, STDIN, --json flags, exit codes, --version flags, or npm publishing. Applies even when best practices are not explicitly mentioned. Also trigger for "how should I implement X in my CLI" or "what's the right way to do Y in a Node.js CLI". Do NOT use for Node.js backend or API development with no CLI entry point.

  • Small skill

    barryroodt/refine-skill/e2e/fixtures/small-skill Skill

    0★ repo

    Minimal skill used to exercise the refine loop end-to-end with a real model.

  • Office live ppt

    binle11/live-office-ppt/integrations/openclaw/office-live-ppt Skill

    0★ repo

    Create, edit, and debug PowerPoint decks with the Live Office PPT workflow: write a JSON slide spec, optionally generate bitmap assets first, then run a PowerShell COM renderer that opens desktop PowerPoint and draws native editable shapes, text, connectors, and pictures live. Use for PPT/PPTX tasks that require visible Office drawing, PowerPoint COM automation, live deck review, or native editable PowerPoint objects.

  • Release readiness

    Dokuganrryu/ai-agent-skills-and-subagents/skills/release-readiness Skill

    no license0★ repo

    Use when preparing, auditing, or unblocking a software release, package, final gate, handoff, release notes, changelog, CI/test failure, or docs checklist needed for shipping. Also use when the user says release-ready, business-ready, final ZIP, final package, publish, ship, technician handoff, customer handoff, or release blockers.

  • Sre runbook executor

    medzin/sre-runbook-agent-skills/skills/sre-runbook-executor Skill

    0★ repo

    Execute production SRE runbooks step by step during incidents or operational tasks. Use when the user asks an agent to follow, run, execute, apply, or walk through a runbook safely with read-only diagnostics first, evidence capture, verification, ambiguity stops, escalation, and approval gates for risky actions.

  • Adk agent builder

    danielvogler/ai-skills-library/.agents/skills/adk-agent-builder Skill

    0★ repo

    Central hub for building, testing, and iterating on ADK agents. Trigger this skill when the user wants to create a new agent, configure modes (task, single-turn), or build graph-based workflows.

  • Handoff

    zhpy2004/claude-codex-handoff/codex/skills/handoff Skill

    0★ repo

    Hand off the current work to another AI coding tool (Claude Code), or resume work that another tool handed off, via a structured HANDOFF.md document in the project root. Use when the user wants to switch between Codex and Claude Code mid-task, "hand off", "交接", "save progress for the other tool", "pick up / resume / 接续 where the other tool left off", or runs /handoff save or /handoff resume.

  • Meson build system

    krxecs/meson-skills/skills/meson-build-system Skill

    0★ repo

    Entry point for Meson questions. Use this skill for general Meson syntax, project structure, build directory basics, and the standard setup-compile-test-install flow. Route option setup, target building, testing, cross-compilation, subprojects, CI, debugging, version compatibility, packaging, and pattern examples to the specialized skills below.

    The same file is in 1 other repository

  • Dragble config

    Dragble/dragble-skills/dragble-config Skill

    0★ repo

    Configure the Dragble editor appearance, features, merge tags, special links, fonts, localization, display conditions, collaboration, branding colors, and editor behavior.

  • Agent tools

    marktantongco/opencodelinux/skills/agent-tools Skill

    no license0★ repo

    Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

  • Coding

    JurnLoryu/claude-code-starter-kit/coding Skill

    0★ repo

    Integrated software-engineering skill that fuses the user's configured engineering skills into one. Two scales: a SOLO/daily coding loop (source-driven → incremental → TDD → simplify → debug) for fast-but-solid work, and a LARGE-PROJECT lifecycle (plan → spec → docs/ADR → context → git → security → performance → CI/CD → ship → deprecate) for work that must scale, ship, and be maintained — plus a quality bar (five-axis review, adversarial verification, interface contracts, production UI) and the user's own coding rules. Use whenever writing, modifying, debugging, refactoring, or reviewing code, or picking up a codebase. Triggers: write code, implement, build feature, fix bug, debug, refactor, review, ship, large project, 写代码, 改代码, 修bug, 重构, 代码审查, 上线, 大项目, 接手代码.

  • Postmortem

    dunkeln/skills/skills/postmortem Skill

    no license0★ repo

    Evidence-chain RCA for production failures, regressions, incidents, broken deploys, CI failures, data issues, and engineering workflow failures.

  • Cavecrew

    cmdecker95/skills/skills/cavecrew Skill

    no license0★ repo

    Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

    The same file is in 7 other repositories

  • Debug off

    ievo-ai/skills/plugins/ievo/skills/debug-off Skill

    0★ repo

    Use this skill when debugging is complete and the user wants to stop accumulating large trace logs — trigger words "turn off debug", "stop verbose", "disable trace", "debug off". Disables verbose / trace-level logging for the iEvo pipeline. Reverts to normal logging (concise `.ievo/log/init-*.md` only).

  • Cleantest pipeline

    jimmy0717/cleantest-agent/skills/cleantest-pipeline Skill

    0★ repo

    Orchestrates the CleanTest data cleaning pipeline for unit test training datasets. Sequentially invokes syntax-filter, relevance-filter, and coverage-filter skills to remove noisy samples, then generates a noise report. Triggers: "clean test data", "filter noisy tests", "run cleantest pipeline", "remove noisy samples", "data quality", "clean training data", "unit test cleaning", "数据清洗", "过滤噪声测试", "运行 CleanTest", "清洗训练数据"

  • Thoth memory backup to github

    LegionForge-Agent-8209/agent-skills/skills/thoth-memory-backup-to-github Skill

    0★ repo

    Use this skill when a user wants to design, create, review, or troubleshoot a backup workflow for Thoth memory and local Thoth state to a private GitHub repository. It helps inventory Thoth data under the user's data directory, exclude secrets and volatile files, create encrypted backup archives, validate restore readiness, and document a safe GitHub-based retention process without exposing private data.

  • Debug helper

    pbans-agent/skillpack/skills/debug-helper Skill

    0★ repo

    Systematically diagnoses and resolves software bugs through structured debugging. Use when the user reports an error, asks to fix a bug, needs help understanding a crash, wants to trace through code execution, or needs to identify the root cause of unexpected behavior.

  • Memory as files

    Edward4226/codex-maxxing/skills/memory-as-files Skill

    0★ repo

    Use this skill when the user wants persistent, cross-session, reviewable memory for an ongoing project, set of people, or domain knowledge. It initializes a versioned file vault (TODO.md + people/ + projects/ + notes/), defines maintenance rules so memory stays current at natural beats, and treats the vault's git diff as the periodic memory-review surface.

  • Codex

    ist-j-ichikawa/skills/skills/codex Skill

    0★ repo

    Call the OpenAI Codex CLI from Claude Code, auto-routing between a fast foreground query and a hardened background delegation. Use whenever the user mentions Codex, GPT, or OpenAI, wants another AI's perspective, wants to fact-check against live web data, or wants to hand a substantial coding task to Codex — even without saying "codex". Foreground mode (read-only, seconds) covers web search, fact-check, second opinion, Q&A, and substitutes for WebSearch on Bedrock Claude Code. Background mode (write-capable, long-running) covers multi-file refactors, deep analysis, reviews, and anything that would blow the Bash tool's 10-minute timeout — surviving hangs and orphaning where the official codex-plugin does not. Triggers: /codex, "Codexに聞いて", "Codexで調べて", "GPTで調べて", "別のAIに聞いて", "セカンドオピニオン", "ファクトチェックして", "web検索して", "Codexに任せて", "Codexでリファクタ", "ask Codex", "delegate to codex", or any /codex:rescue timeout.

  • Write agents md

    sdhong0609/agents-md-skill/skills/write-agents-md Skill

    0★ repo

    Use when Codex needs to create, rewrite, audit, slim down, or install AGENTS.md/CLAUDE.md agent instruction files for a repository, especially when avoiding /init-style generated context, reducing context debt, adding repo-specific pitfalls, or setting nested AGENTS.md guidance.

  • Database content crud

    codezelat/codezela-web-skills/skills/database-content-crud Skill

    0★ repo

    Use when designing, migrating, seeding, or fixing database-backed content, catalogs, categories, articles, CMS data, Postgres, Neon, Supabase, migrations, slugs, ordering, search, pagination, safe deletes, or data verification.

  • Agent memory patterns

    m00kk/agent-skills-playbook/skills/agent-memory-patterns Skill

    0★ repo

    Implements short-term and long-term memory for agents: conversation buffers, summarization, vector memory, and user preference stores. Use when building agent memory, pgvector recall, persistent context, or reducing context bloat.

  • Fable orchestrator

    Aetheris-Solutions-LLC/aetheris-claude-skills/plugins/aetheris/skills/fable-orchestrator Skill

    0★ repo

    Use when running on an expensive orchestrator model (Fable, Mythos, or Opus 5) and the task is substantive parallelizable multi-step work — building features, research sweeps, audits, incident fixes — where the user wants the agent team pattern ("spawn the team", "use opus/sonnet/codex", "orchestrate this", "keep my orchestrator context clean") or invokes /fable-orchestrator. Not for single-file changes or undiagnosed bugs.

  • Agent skills

    whiteknightonhorse/aipush-agent-skills/skills/agent-skills Skill

    0★ repo

    Free, open, security-verified agent skills for AEO (Answer Engine Optimization) — make any site ready for AI agents. Live: aipush.app

  • Multi agent dispatch

    xuluoforcainiao/multi-agent-dispatch/multi-agent-dispatch Skill

    no license0★ repo

    Coordinate tasks between multiple AI agents (wukong and qoderwork) using a shared DingTalk AI spreadsheet as the message bus. Use when dispatching tasks across agents, checking pending agent tasks, or setting up inter-agent collaboration workflows.

  • Diagnose hard bugs

    hesprs/harness/skills/diagnose-hard-bugs Skill

    0★ repo

    Disciplined diagnosis loop for hard bugs and performance regressions. Use only when user instructs or other skill references.

  • Pixi container

    soappp9527/micromamba-container/pixi-container Skill

    no license0★ repo

    How to package projects into Docker/Podman containers using pixi for fast, reliable dependency management. Use this skill ANY time the user mentions or implies any of the following: containerizing a project, building a Docker image, creating a Dockerfile, packaging an app for deployment, making a container for a Python/R/Node project, pixi in Docker, containerization, pixi.toml or pyproject.toml for builds, optimizing container size, setting up non-root users in containers, or building images for data science/ML/bioinformatics projects. Also trigger when the user asks about Docker best practices for pixi environments, troubleshooting pixi package resolution in containers, or mentions bioinformatics tools that need to go into a container. Even if the user just says 'dockerize this' or 'make a container for my project' without specifying pixi, trigger this skill if the project appears to use pixi, has a pixi.toml or pyproject.toml with pixi config, or involves data science/ML/bioinformatics dependencies.

  • Room

    Randomguy01/claudekit/plugins/androidx-room/skills/room Skill

    no license0★ repo

    Build and maintain an Android Room persistence layer. Use this skill when the user works with Room or on-device SQLite storage on Android — defining entities, DAOs, and queries; setting up the database and DI wiring; schema migrations; entity relationships; type converters for custom column types; views, FTS, and prepopulated databases; or testing and debugging the database. Applies even when the user doesn't say "Room" by name — e.g. "save this data locally on Android," "persist app state to a database," "@Entity / @Dao / @Query won't compile," or "migrate my SQLite app." Skip for server-side or non-Android databases and for plain ORMs on other platforms.

  • One2rule them all skills

    yakhandler/one2rule_them_all/.claude/skills/one2rule_them_all-skills Skill

    0★ repo

    Merge and sync Agent Skills across every skill-capable tool on the machine (Claude Code/Desktop, Codex, Antigravity, Gemini CLI, and optionally Cursor) so each tool ends up with the full union of skills — each skill's whole directory (SKILL.md + scripts + references + assets) copied in faithfully, with nothing lost. Use this whenever the user wants to reconcile, sync, merge, consolidate, copy, share, or "install everywhere" their skills between tools/apps — e.g. "I made a skill in Claude but Codex doesn't have it", "get all my skills into every tool", "my skills are out of sync across CLIs", "one config to rule them all but for skills", or any request about skill folders drifting apart. Trigger even if the user names only one or two tools or doesn't say "reconcile." This is the SKILLS counterpart to one2rule_them_all-mcps (which does the same for MCP servers).

  • Good skill

    Sparvovic/agent-skill-foundry/examples/good-skill Skill

    0★ repo

    Use when the user asks an AI coding agent to turn a git diff into concise release notes with risks, validation evidence, and reviewer-ready wording.

  • Impeccable

    skillrig/skillrig.github.io/.agents/skills/impeccable Skill

    0★ repo

    Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

    The same file is in 4 other repositories

  • Setup

    jrausercisco/trmnl-agent-bridge/plugins/claude/trmnl-agent-bridge/skills/setup Skill

    0★ repo

    Help a user install the trmnl-agent CLI, configure a TRMNL Private Plugin webhook, and verify a safe dry-run payload for Claude Code.

  • Mina deployment upgrade security

    mysteryon88/skills/mina-protocol/skills/mina-deployment-upgrade-security Skill

    0★ repo

    Use when preparing, reviewing, or hardening Mina zkApp deployments, upgrade policies, verification keys, permission matrices, key management, network configuration, or release procedures.