The catalog
608,119 rows, by stacks then stars
SID-SURANGE/cursor-team-ops/skills/community/ci-cd-pipeline Skill
0★ repoSet up or fix a CI/CD pipeline with quality gates — lint, type check, tests, build, security audit, and deployment. Triggered by "set up CI", "fix the pipeline", "add GitHub Actions", "ci-cd-pipeline", "automate deployment", "set up quality gates".
loredotlink/lore-plugin/skills/fork Skill
no license0★ repoDistill a Lore thread into handoff context for continuing work. Use when the user asks to continue work from a Lore thread, fork from a thread, pick up from a thread, or use a Lore thread as context for a new task.
jboczek/skills/skills/big-picture Skill
0★ repoBuild or update a concise Big Picture document for an IT product, feature, or technical solution. Use when the user wants a high-level, product-minded view of what is being built, why it matters, and where it could go next.
PARS-DOE/doe-skills/doe-branding Skill
no license0★ repoDOE brand compliance for documents, presentations, and communications. Use when creating or reviewing any DOE-branded content: slide decks, reports, fact sheets, memos, or any deliverable that needs DOE logos, colors, typography, or layout compliance. Triggers on: DOE branding, brand guide, brand colors, DOE template, DOE logo, DOE style guide, brand compliant, on-brand.
Mohrimn/legacy-dotnet-agent-kit/skills/legacy-dotnet-agent-kit Skill
0★ repoUse when modernizing, rewriting, or assessing legacy .NET systems with coding agents, especially WPF, WinForms, ASP.NET, custom server-call layers, old reporting stacks, cache-heavy clients, sync-over-async risks, or incomplete build/test environments. Helps produce source-backed architecture maps, risk registers, migration slice plans, and verification handoffs before implementation.
saphid/Build-Skill/skills/planning-slices Skill
0★ repoWrites persistent bottom-up implementation slice plans for coding agents. Use when the user asks to plan a feature, create planning slices, prepare a docs/plans implementation plan, or make a feasible plan for /build or /goal to execute later.
Auditing derived artifact claude md
Fearvox/derived-claude-md/skills/auditing-derived-artifact-claude-md Skill
0★ repoUse when an existing CLAUDE.md in a derived or projected directory (symlink view, build cache, mirror, generated docs, materialized projection) needs to be re-checked against current upstream governance — e.g., upstream rules document was updated, sibling artifact added/removed, manifest schema evolved, or a pre-deploy sanity check is needed on the derived file's guidance.
MoaidHathot/Zakira.Conduit/example/local-skill-sample Skill
0★ repoA tool that mirrors agent skills from GitHub or local directories into your agent folders, driven by a conduit.json manifest.
dtussupbayev/flutter-agentic-skills/skills/dart-comments Skill
0★ repoUse when writing, changing, or reviewing documentation comments, inline comments, TODOs, or FIXMEs in Dart and Flutter source code.
Influship/influship-skills/skills/building-with-influship Skill
0★ repoBuild, integrate, and debug applications on the Influship creator-discovery API and its official TypeScript SDK (npm `influship`). Use when installing or setting up the Influship SDK, authenticating with an Influship API key, or writing code that calls Influship — semantic creator search, match/fit scoring, lookalike discovery, autocomplete, profile or post lookups, and raw Instagram/YouTube data — and when handling Influship pagination, errors, retries, or credit costs. Also use when calling the Influship REST API directly from a non-TypeScript language (curl, fetch, Python). Not for operating the Influship MCP server (separate skill), and not for general influencer-marketing strategy with no API work.
Glaicer/skill-picker Skill
0★Use when a project needs selected local agent skills wired into its repository, especially requests to pick named skills, install shared project skills, create an industry-standard .agents/skills folder, mirror skills for installed non-.agents-compatible coding agents, expand a skill bundle, or select a nested skill such as roadmap-importer.
vibesec-advisory/skills/skills/agent-tool-access-policy Skill
no license0★ repoUse when deciding what an AI agent, assistant, automation, connector, MCP server, browser session, or workflow tool may read, write, send, delete, execute, approve, or trigger before granting access.
oceanfsdfsvfdsvs/chargeback-evidence-pack/.claude/skills/chargeback-evidence-pack Skill
0★ repoAssemble reason-coded merchant dispute evidence packs from local order, receipt, tracking, support, and policy evidence without exposing secrets or private logs.
The same file is in 1 other repository
zacfire/creative-logic-reconstruction-skill/creative-logic-reconstruction Skill
0★ repoUse when the user asks why a product, work, creator, team, company, or strategy is shaped the way it is, what logic drove it, or what can be learned from it. Covers product logic, creative intent, presentation logic, creator/team context, interviews, tradeoffs, and transferable lessons.
tsaijamey/claude-session-rescue/skills/claude-session-rescue Skill
0★ repoThis skill should be used when a Claude Code session becomes permanently stuck and cannot continue because the model returned a malformed response that the client cannot parse. It explains how to repair the session by editing its raw JSONL transcript file and then resuming. Trigger phrases: "The model's tool call could not be parsed (retry also failed)", "tool call could not be parsed", "Your tool call was malformed and could not be parsed", "session stuck and won't resume", "claude code session frozen", "rescue a broken claude code session", "fix corrupted session jsonl", "resume a dead claude session", "empty thinking block stop_reason tool_use".
cogine-ai/local-ultra-review Skill
no license0★Use when the user explicitly asks for a deep local code review, PR review, bug hunt, pre-merge review, or Ultra Review style review with high confidence findings.
peternicholls/Charm-Skills/charm-bubbletea-components Skill
0★ repoAdd, configure, test, and compose Charm Bubbles components in Bubble Tea applications. Use when Codex needs text input, text area, table, list, viewport, spinner, progress, paginator, timer, stopwatch, help, key bindings, file picker, focus management, or reusable Bubble Tea component patterns.
zzyyfff/span/skills/span/span-receive Skill
0★ repoPost-/clear handoff receiver. Verifies world-state THIS session, opens the canonical docs with evidence, reports orientation in the three-section template, and runs the open categorial probe (defended / inherited / unverified). Fire as the FIRST action after /clear, compaction, or session start when a span handoff exists.
mohammaddaoudfarooqi/agent-engineering-skills/skills/doc-authoring Skill
0★ repoDocumentation authoring for AI coding agents. Analyzes a repo and generates docs classified by Diataxis type (tutorial, how-to, reference, explanation), kept synchronized with the code. Handles greenfield, brownfield (refresh, enhance, rewrite), and doc audits. Use when the user requests project documentation: a README, API reference, architecture doc, developer guide, contributing guide, changelog, ADR, or onboarding doc, or when existing docs need an audit, refresh, or restructure. Triggers on phrases like "write a README", "document this project", "API reference", "developer guide", "audit our docs", or "Diataxis", and when creating or editing `README.md`, `CONTRIBUTING.md`, `CHANGELOG.md`, files under `docs/`, or doc tooling config (`mkdocs.yml`, Docusaurus, Sphinx). Also triggers when a public API, CLI flag, or config option changes and docs must stay in sync. Do NOT use for standalone prose, marketing copy, blog posts, or design documents unrelated to a codebase.
lj22503/mangoview/backend/core/data Skill
0★ repoMangofolio 核心数据层 - 统一数据获取与缓存
Kofiloski/app-store-review-risk Skill
0★Review Apple-platform app repositories and pull-request diffs for likely App Store Review, TestFlight, and notarization risks. Use when someone asks whether Apple may reject a build or wants evidence-backed checks for privacy manifests, permission strings, entitlements, StoreKit and subscriptions, account deletion, Sign in with Apple, user-generated content, private APIs, placeholder content, metadata, review notes, demo access, or platform-specific submission concerns across iOS, iPadOS, macOS, watchOS, tvOS, and visionOS.
balevdev/agentique/skills/anakin Skill
0★ repoRun the ANAKIN software factory — turn everyday engineering tasks (tickets, features, hardening) into reviewed diffs through small autonomous ticks, with all memory in a global SQLite database and zero traces in the repo. Use when the user asks for an anakin run, says "anakin init" or "anakin task", wants a repo built or hardened autonomously via /loop, or wants hands-off task-after-task work where the factory never commits and the human reviews each finished task.
ModelBound/modelbound-cursor-extension/.github/skills/ci-smoke Skill
0★ repoSmoke-test skill for ModelBound CI — triggered when validating GitHub Actions skill checks.
The same file is in 4 other repositories
jovd83/skill-yaml-cleanup Skill
0★Audit and reduce YAML frontmatter bloat in SKILL.md files. Trigger to: scan skill directories, identify oversized frontmatter, propose deduplication/flattening/migration optimizations, and apply approved changes. Requires user approval before writing.
TTech-Xin/TTech-SKILLs/SKILLs/ttech-query-company-zh Skill
0★ repo当用户询问科技公司实时动态、股票数据或公司相关新闻时调用本 SKILL。触发场景包括:(1)询问公司专属的实时动态,**特定公司**的近期新闻聚合(区别于行业通用新闻),了解该实体的最新动向;(2)询问科技公司的实时/历史股价,如日线/月线/年线;(3)询问科技公司间的竞争与合作关系;(4)询问公司全称、上市地点、股票代码。
fengluisobel/ask-dongfeng-hermes/optional-skills/autonomous-ai-agents/blackbox Skill
0★ repoDelegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
The same file is in 1 other repository
suranyami/uncloud-skill Skill
no license0★Use when managing an Uncloud homelab cluster — deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes with the `uc` CLI.
xuluoforcainiao/dws/dws Skill
no license0★ repo管理钉钉产品能力(AI表格/日历/通讯录/群聊与机器人/待办/审批/考勤/日志/DING消息/开放平台文档/钉钉文档/钉钉云盘/AI听记/邮箱/在线电子表格/知识库等)。当用户需要操作表格数据、管理日程会议、查询通讯录、管理群聊、机器人发消息、创建待办、提交审批、查看考勤、提交日报周报(钉钉日志模版)、读写钉钉文档、上传下载云盘文件、查询听记纪要、收发邮件、读写在线电子表格(axls)、管理钉钉知识库时使用。
LuiccianDev/eda-skouries-composite-vulcan-2026/.agents/skills/create-readme Skill
0★ repoCreate a README.md file for the project
The same file is in 3 other repositories
SystemicVoid/agentic-research-skills/skills/clean-room-framing-options Skill
0★ repoGenerate and stress-test six evidence-specific research framings from an evidence pack before a project story is chosen.
95-yn/tuttikit/.claude/skills/greet-test Skill
0★ repo演示 skill 加载流程的最小例子;用户问候时按指引回应
accolver/annuity-life-insurance-sales-skill/skills/annuity-life-insurance-sales Skill
0★ repoGuides licensed insurance agents and financial professionals through compliant annuity and life-insurance sales workflows. Use when creating discovery questions, suitability framing, retirement-income analysis, product-positioning language, objection handling, meeting prep, client follow-up, policy review, or servicing guidance for annuities, life insurance, QLACs, retirement income, guaranteed income, or protection planning.
toorcn/next-step-buttons Skill
0★Use when a response has real actionable suggested next steps, follow-up choices, or quick controls. Add a concise "Suggested next" list with enough detail in the message body and matching short clickable buttons when the channel supports them, especially Telegram. Do not use for tiny factual answers, pure explanations with no action, or decorative choices.
misalazeem/coding-task-verifier-sample Skill
no license0★Sample coding task with a skill spec, reference solution, pytest verifier, Dockerfile, and ten annotated attempt trajectories.
hifizz/skills/skills/chrome-web-store-review Skill
0★ repo对 Chrome 扩展(Manifest V3)在提交 Chrome Web Store 审核前做一次可重复的上线前自查,覆盖单一用途、权限逐项理由、远程代码/MV3 红线、数据使用声明、商店素材、商标合规,产出一份带 ✅/⚠️/❌/❓ 判定的 Markdown 自查报告。Use when the user wants to check whether a browser extension can pass Chrome Web Store / CWS review before submitting, or asks for a "扩展过审 / 提审自查 / CWS review / Web Store 审核" report.
dbtlr/atlas-skills/pre-release/adversarial-review Skill
0★ repoThe verification gate before a change is declared complete — MANDATORY before creating a PR (`gh pr create`) on any work branch, and on request ('run the review', 'adversarial review'). Runs the proportionality gate (or declares a skip), a deterministic suppression scan, delegates the review to the harness's native engine, then drives the resolution loop until every finding is fixed, dismissed with a stated reason, or deferred to a tracked task — recording the disposition trailer and presenting the table to a human. Primary agent / controller only.
unliftedq/agents/android-dev/skills/adaptive Skill
no license0★ repoInstructions to make or update an app's UI so that it adapts to different Android devices including phones, tablets, foldables, laptops, desktop, TV, Auto and XR. It includes how to handle different window sizes, pointing devices (such as mouse) and text entry devices (such as keyboard) using the Compose MediaQuery API. It also covers multi-pane layouts using Navigation3 Scenes, adaptive UI components (such as buttons) with varying target sizes, and adaptive layouts (including navigation areas - nav rails and nav bars) using the Compose Grid and FlexBox APIs.
kenantang/codex-and-claude-skills/collected-academic-research-skills/sources/AI-4-Phi__PhilLit/.claude/skills/literature-review Skill
no license0★ repoCoordinate comprehensive literature reviews on any research topic in philosophy. Manages 6-phase workflow including domain decomposition, literature search, and synthesis. Use proactively when user requests a literature review.
cskwork/storyboard-spec Skill
0★Side-by-side storyboard 화면설계서. Left = screen (wireframe to design up front, OR replica of a built/Figma UI) with numbered callouts; right = per-element table (action/data/exception); plus thumbnail board. Domain-agnostic.
cskwork/myfocus-skill Skill
0★Surface the highest-priority next task across recent coding-agent sessions (Claude Code, Codex, Gemini, +extensible). Domain-agnostic Claude Code skill.
xuluoforcainiao/tailored-resume-generator/tailored-resume-generator Skill
no license0★ repoAnalyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
zhanglianjie3766/ai-anchor-prompting/skills/ai-anchor-prompting Skill
0★ repoGuide complex human-AI collaboration with the AI Anchor Prompting method, also called AnchorFlow. Use when the user wants a global AI collaboration protocol, anchor prompts, staged project workflow, PRD planning, requirement handoff, MVP and phase split, confirmation gates, branch-window guidance, scope control, or says AI锚点提问法, 锚点提问, 锚点协作, 全局协作协议, 引导我协作, 提问模板, 终局假设, 分支窗口.
Mercer8964/audit-loop/platforms/claude-code/audit-loop-max Skill
0★ repoAccuracy-optimal variant of audit-loop. 3-5 parallel independent re-solves + 2-3 cross-method probes + optional Du-et-al debate rounds on disagreement. No spawn cap. Use ONLY when cost-of-being-wrong dominates audit cost — security-critical claims, irreversible deployment, claims with material financial/legal/safety consequence. For everyday work where 2 spawns suffice, use audit-loop instead. THIS IS A DELTA FILE — load ~/.claude/skills/audit-loop/SKILL.md alongside for the shared sections (why re-solve, triage gate, characterize step, equivalence semantics, multi-turn handling, mandatory rules 1-4, explicit limits, design fallback principles).
Hari31416/interactive-article-skill Skill
no license0★Create polished, single-page technical HTML articles that teach topics through fully functional interactive web components. Use this whenever the user asks for an HTML technical guide, explainer, tutorial, article, visual walkthrough, interactive documentation page, or any request to explain engineering topics via an interactive webpage. Apply this skill even if the user does not explicitly mention "HTML skill" but asks for a standalone educational web page.
peizh/refactor-legacy-code Skill
0★Apply legacy-code refactoring and maintenance workflows for large codebases where behavior must be preserved while changing risky, poorly tested, tightly coupled, or hard-to-understand code. Use when asked to refactor, modernize, stabilize, maintain, add features to, test, untangle, break dependencies in, or plan safe changes for legacy systems, large repositories, monster methods/classes, hard-to-test code, API-heavy code, library/global/static dependencies, or repeated cross-cutting changes.
alexbw/vectorize-figure/skills/vectorize-figure Skill
0★ repoReconstruct raster images of scientific figures into editable, configurable HTML plus a semantic JSON specification. Use when the user asks to recreate a figure from a PNG/JPEG/screenshot, wants a no-source-image HTML reconstruction, or needs chart panels converted into editable axes, marks, annotations, legends, styles, and data recipes.
cskwork/skill-ab-eval Skill
0★Prove whether a SKILL.md actually changes agent behavior (with/without) and which CLI harness does a task best — agent-native subagents or CLI. agentskills.io-compatible. Site: https://cskwork.github.io/skill-ab-eval/
theomonfort/skills/skills/agentfinder Skill
no license0★ repoDiscover installable MCP servers, tools, skills, and agents for a task by searching an ARD Agent Finder. Use whenever the user wants to find or install a tool, MCP server, skill, agent, or integration for something they are trying to do — email, calendars, databases, payments, cloud platforms, CI/CD, messaging, monitoring, file storage, and similar services.
The same file is in 1 other repository
kira-0521/agent-skills/railway-openclaw-troubleshoot/claude-code Skill
0★ repoRailway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。
brandonbryant12/copilot-goal/skills/goal Skill
0★ repoStart, track, resume, and complete durable project goals in GitHub Copilot while minimizing AI-credit and legacy premium-request usage.
CodedVibesX/byoc-preflight/plugins/byoc-preflight/skills/preflight Skill
0★ repoGate a regulated deployment before it ships. Run a BYOC readiness gate on a service installation before promoting or deploying it into a regulated environment (HIPAA, PCI, FedRAMP, SOC 2, or a customer-owned cloud). Gathers evidence from the Ryvn CLI, evaluates data egress, secrets and standing access, observe-without-access, rollback safety, promotion discipline, audit, and compliance preconditions, then blocks the task approval and the promotion until the gate is clean or its findings are explicitly acknowledged. Use this skill whenever the user mentions deploying, promoting, or releasing into a regulated, healthcare, HIPAA, BYOC, on-prem, or customer environment, a readiness gate, a compliance check, a go/no-go, a service installation, or a promotion pipeline, even if they don't say "byoc-preflight" explicitly.
bluefeet/skills/commit-organizer Skill
no license0★ repoOrganizes committed Git branch history into focused, reviewable linear commits. Use when the user asks to clean up, split, squash, reorder, reconstruct, or make committed branch or range history reviewable before a PR. Do not use for ordinary commit creation, commit-message drafting, generic Git advice, or standalone conflict recovery.
RolandOne/codex-image-generation/skills/image-generation Skill
0★ repoGenerate or edit raster images (photos, illustrations, mockups, sprites, transparent cutouts) by delegating to Codex's built-in imagegen skill. Use when the user asks to "generate an image", "create an image", "make a picture", "render", "draw me", "produce a mockup/sprite/asset", "headshot", "logo", "thumbnail", "banner", "hero image", or any other bitmap-asset request. Do not use for SVG/vector edits, icon-system extensions, or HTML/CSS/canvas drawings.
pingwurth/code-to-uml/skills/code-to-uml Skill
0★ repoUse when generating, updating, repairing, validating, or reviewing Code-To-UML .ctu/HTML source-analysis reports for a project, module, file, class, function, existing report, or validator/rendering failure.
Business architecture foundations
krishanjogia-collab/plektis/sdk/skills/business-architecture-foundations Skill
no license0★ repoFoundational domain intelligence for business architecture practice. Covers capability mapping, value streams, the Business Motivation Model, and PPIT dimensional analysis. Load when working on capability assessments, operating model design, strategy-to-execution traceability, or any engagement where business architecture concepts are the analytical backbone.
egesabanci/agent-collab Skill
0★Coordinate multiple AI coding agents working on the same repository with git worktree isolation, task ownership, structured handoffs, review, testing, merge readiness, conflict handling, and human escalation. Use when an AI agent, agent runtime, automation workflow, or human coordinator needs to orchestrate parallel or sequential agents on one codebase, split work across architect/implementer/reviewer/tester/documentation/integration roles, create .agent coordination files, prevent agents from overwriting each other, or safely prepare multi-agent repository changes for merge.
mastercodeai/skillopt-methodology-skill Skill
no license0★Systematic methodology for optimizing agent skills using SkillOpt approach. Use when iterating on SKILL.md files, validating skill improvements, or applying deep-learning-style optimization to text-based agent skills. Includes 8 optimizer prompts, validation gates, and bounded edit controls. Triggers on: optimize skill, improve skill, iterate skill, skill validation, skill optimization, skillopt, bounded edits, rejected edits buffer.
Levix0501/next-agent-rails/.agents/skills/find-skills Skill
0★ repoHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
The same file is in 21 other repositories
MarchRory/liushi_agent_settings/.agents/skills/code-review Skill
no license0★ repoUse when code, configuration, documentation, policies, or public interfaces changed and the result needs risk-focused review before delivery.
MYMDO/AGENTSKILL Skill
0★Complete guide to minimal universal configuration files compatible with all major AI coding agents.