Context & AI engineering
25,864 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
bokuwalily/claude-code-skills/skills/agents-tools-quoted-json Skill
0★ repo~/.claude/agents/ の各 agent frontmatter `tools:` フィールドが bare-bracket (`[Read, Edit]`) や `allowed-tools:` 旧式で不統一なとき、quoted JSON 配列形式に一括正規化したいとき。
jorgenosberg/shakespeare/skills/expand Skill
0★ repoInflate a memory file (CLAUDE.md, AGENTS.md, notes, todo lists) from plain English into ornate Early Modern English prose, while keeping every code block, URL, path, command, identifier, heading, date, and table untouched. A human-readable backup is written to `<file>.original.md`. Trigger: /shakespeare-expand <filepath> or "expand memory file".
cskwork/claude-minimal-plugin/skills/agent-browser Skill
0★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
LOVAHE/JustDoIt/skills/just-do-it-agent Skill
no license0★ repoAutonomous execution protocol for general AI agents. Use when the user explicitly invokes JustDoIt Agent, asks for autonomous or end-to-end handling, asks for a standard work loop, wants agent-readable entrypoints or handoff, or when the user has not named another skill and the task is complex enough to need multi-step investigation, functional-boundary clarification, action, review, verification, or future-agent operability through stable keys, commands, selectors, schemas, manifests, APIs, tests, runbooks, or JDI.md.
payals/cursor-prompt-queue/skill/prompt-queue Skill
0★ repoUse when user says "execute prompt queue", "resume prompt queue", "run the queue", "reset prompt queue", "reset queue prompt", or has a docs/prompt_queue.md file with sequential prompts to execute. Orchestrates multi-step prompt pipelines with dynamic variable passing between steps, fresh subagent per step, and cross-session resumability via state file.
srinivas-dev-stack/pull-context-skill Skill
no license0★Pull the context of another Claude Code session into the current one. Lists recent sessions (by topic hint), lets the user pick one, distills that session's transcript in a subagent, and injects the digest here. Use when the user says "pull context from", "bring in the other session", "import that session about X", or wants to merge work from a parallel session.
burythehammer/claude-code-plugins/plugins/claude-md-slim/skills/claude-md-slim Skill
0★ repoAudit and slim down bloated CLAUDE.md files — and other overlong project markdown like READMEs — by applying progressive disclosure. Use whenever the user asks to audit, trim, shrink, slim, refactor, declutter, restructure, or optimise a CLAUDE.md (or AGENTS.md / project memory) file, says their CLAUDE.md or README is too long or bloated, mentions context bloat or token waste from project instructions, wants rules moved into .claude/rules/ or subdirectory CLAUDE.md files, wants long docs split into linked pages, or asks about @imports or progressive disclosure — even if they don't name the file explicitly (e.g. "my project instructions are getting out of hand").
Zrzzzz/agent-codebase-skills/init-agent-task-md Skill
0★ repo为项目初始化「任务管理层」v3——协调靠结构消除、纪律靠 hook 兜底、脚本只留便利: 1. docs/tasks/T-<slug>.md:每个任务一份独立文件,**文件名即 ID**——无编号、 无锁、无主树限制,任何 agent 在任何 worktree 里直接建文件直接 commit。 2. docs/TASKS.md:marker 区索引视图,由 git hook(pre-commit / post-merge) 自动重生成——没人需要「记得跑脚本」;marker 之外(更新协议 / 约束与决策 / 踩坑与教训)由人手写,脚本不动。 3. .githooks/pre-commit:流程纪律兜底——feat/bugfix/hotfix 分支必须有对应 任务文件才能 commit;禁止直接 commit 到 main;docs/tasks 变更自动刷索引。 4. .githooks/post-merge:主 checkout pull/merge 后自动刷索引。 5. CLAUDE.md / AGENTS.md「任务入口协议」(必装 marker 块):用户报 bug / 提需求 → 先登记任务 + 切分支,再动代码;免登记白名单写死。 6. scripts/tasks-new.sh(模板便利,无锁)、scripts/tasks-index.sh(hook 调用)、 scripts/tasks-release.sh(条目直接写进 CHANGELOG 的 Unreleased 段 + --cut 切版本)。v2 的 tasks-status.sh 已删——status 流转就是一行 frontmatter Edit,updated 字段已砍(由 git log 派生)。 7. CHANGELOG.md:Keep a Changelog 骨架(不存在时创建)。 8. 可选:把「自动跑索引 + 任务推进检测」追加进 init-session-notes 的 _summarize-worker.sh,作为会话结束兜底。 幂等升级:重跑 skill 按 scripts/tasks-index.sh 里的 skill-managed 版本号 分流——v1(monolith TASKS.md)与 v2.x(顺序编号 + 四脚本)都走迁移到 v3; 已是 v3.x 只覆盖脚本与 hook 文件。 本 skill 只管「任务管理」:会话归档 hook 归 [`init-session-notes`](../init-session-notes/SKILL.md), CLAUDE.md / AGENTS.md 分层约定归 [`init-agents-md`](../init-agents-md/SKILL.md)。 使用:/init-agent-task-md;或当用户说「给项目装任务管理」「初始化 TASKS.md」 「让 agent 先开任务再改代码」时也命中本 skill。
dkmqflx/claude-tools/.claude/skills/agents-build Skill
no license0★ repoUse when adding capabilities to an existing agent project — memory, app integration, VPC, multi-agent, migration, model changes, browser, code interpreter, or resource removal. Triggers on: "add memory", "remember across sessions", "call agent from app", "invoke agent from code", "auth to call agent", "streaming responses", "VPC", "VPC connectivity", "VPC error", "can't reach from VPC", "multi-agent", "A2A", "A2A auth", "orchestrator not delegating", "specialist not called", "migrate Bedrock Agent", "after import", "migration issue", "framework for migration", "change model", "browser tool", "code interpreter", "delete agent", "tear down", "agentcore remove", "cross-account memory", "resource-based policy on memory". Not for connecting to external APIs via Gateway — use agents-connect. Not for scaffolding a new project — use agents-get-started. Not for CLI/dev server errors — use agents-debug. Strands vs LangGraph in a migration context routes here.
ORBWEVA/solo-agents/skills/agents Skill
no license0★ repoAI agent design and automation skill for solopreneurs. Use when user needs to audit workflows for automation, design AI agents, or build automation recipes using n8n + Claude API. Triggers on "ai agent", "automation", "workflow automation", "n8n", "agent design", "automate my business", or /agent commands.
aditya-m-bharadwaj/APIskillBuilderSkill/.claude/skills/api-skill-builder Skill
0★ repoBootstrap a new "<vendor>-api-skill" project — a safe, cross-platform single-file Python CLI that mediates a third-party REST API, plus a matching Claude skill that drives it under explicit AI-safety constraints (token never enters AI context; every mutation passes through a six-tier safety classifier; every mutation is recorded in a local audit log). Trigger when the user asks to "build a CLI / skill for <some API>", "wrap the <X> API safely", or to mirror the linode-api-skill pattern for a new vendor.
xuxinmaxen/agentic-commerce-news Skill
0★Agentic Commerce Weekly Briefing — Scans X/Twitter, industry media, and VC announcements from the past 7 days to surface startups, products, funding rounds, and opinions endorsed by influential voices (VCs, founders, AI leaders) in the agentic commerce space, then produces a structured news briefing. Supports scheduled execution (e.g., daily at 8am). Use whenever the user mentions agentic commerce news, AI commerce updates, AI shopping agent startups, agent checkout products, or invokes /agentic-commerce-news. Also trigger on requests like 'what's new in agentic commerce this week', 'who's funding AI shopping startups', or 'set up a daily digest of agentic commerce updates' — even when the user doesn't name the skill explicitly.
xniperbuilds/rule-audit Skill
0★Find out which of your agent rules are actually enforced and which are only hope — then convert the ones that matter into deterministic enforcement. Use whenever the user says Claude ignored my rules, it pushed to main again, it keeps forgetting my instructions, my CLAUDE.md isn't working, "same mistake again", "I told it not to", "rule follow nahi karta", "phir wahi ghalti" — or asks to add a hook, block a command, enforce a convention, run something automatically after edits, review their CLAUDE.md, or make an instruction actually stick. Also use before writing a new rule, to decide whether it belongs in prose or in the harness, and when a CLAUDE.md has grown long enough that compliance is degrading. It inventories every rule you have, classifies each as enforceable or advisory, generates the hook or permission config for the enforceable ones, tells you plainly which rules can never be enforced, and prunes the rest so the remaining instructions actually get followed.
ArthurZakirov/SystemSmith/skills/engineer-agentic-ai Skill
0★ repoTranslate natural-language requests about modifying an AI coding agent, its skills, MCP tools, MCP servers, prompts, routing, tool descriptions, context loading, memory, portability, or other agentic behavior into the concrete mechanics of the target system. Use when a request is underspecified, phrased in human terms instead of runtime terms, or risks making the wrong change because the agent must reason about how Codex, Claude Code, OpenCode, MCP-based systems, or similar runtimes select skills, choose tools, load instructions, apply configuration, and stay transferable across users and machines.
Architecture diagram gpt imagegen
ArthurZakirov/ProofStack/skills/architecture-diagram-gpt-imagegen Skill
no license0★ repoGenerate a copy-paste-ready GPT prompt that produces a polished architecture or workflow diagram image, and optionally render the image directly via Codex CLI image generation. Trigger when the user wants to create, make, generate, draw, or visualize a diagram, architecture image, system workflow picture, or flowchart, or pastes a Mermaid diagram asking for a polished image.
NakSAlone/deckhand-free/skills/claude-md-tuner Skill
0★ repoUse when the user wants to create, audit, tune, trim, or improve a CLAUDE.md (or AGENTS.md) project instruction file for Claude Code — makes the file actually steer the agent instead of bloating context. Triggers on "write a CLAUDE.md", "improve my CLAUDE.md", "audit CLAUDE.md", "set up project instructions".
az9713/youtube-transcript-to-skills/.claude/skills/claude-md-doctor Skill
no license0★ repoAudit and improve CLAUDE.md files. Use when rules aren't working, context is bloated, or after learning a lesson that should become a rule.
dhk/skill-map/plugins/skill-doctor/skills/skill-doctor Skill
0★ repoReview an existing Claude Agent Skill and bring it up to best-practice standard. Use this when you have a SKILL.md to audit, harden, or improve — it interviews about allowed-tools scoping, data sensitivity (PHI/PII/HIPAA), high-stakes actions, triggering, and install scope, then recommends fixes and applies them on your confirmation. Do NOT use this to write a brand-new skill from scratch (use skill-creator) or to grade a whole repo at once (use the skill-map auditor / skill-audit Action).
TheBitcoinBreakdown-95/frontier-prompter/skills/frontier-prompter Skill
0★ repoReformats a raw prompt, task, or goal into a hand-off prompt optimized for a top-tier autonomous model, using Anthropic's prompting best practices for strong autonomous models. Use this whenever the user wants to hand a task to a frontier/premium model or any top-tier autonomous agent — phrases like "make a frontier prompt", "format this for my frontier model", "turn this into a hand-off prompt", "write a hand-off / planning prompt", "prep this for a strong model", or any time the user is authoring a prompt that asks a powerful model to plan or execute autonomously. Encodes intent-first framing, lead-with-outcome brevity, act-when-you-have-enough, effort/tier matching, prove-it verification, and a small set of rationalized negative guardrails placed at anticipated failure points. Reach for it any time the user is hand-drafting a multi-paragraph Intent/Success/Read-first hand-off or seat prompt for a strong model.
robmcquade/claude-skills/evaluate-ai-merits Skill
0★ repoEvaluate the merits of external content about Claude, Anthropic products, Claude Code, MCP servers, AI agents, prompt engineering, or AI tooling broadly. Adds AI-specific verification on top of evaluate-merits — routes to primary sources, applies heightened date-of-recording sensitivity (AI tooling ships weekly), flags AI-specific conflations (built-in vs custom add-ons, model-version vs universal guidance, surface differences between claude.ai/Code/API, deprecated features, opinion vs Anthropic guidance, preview vs GA). Use whenever the user shares content on Claude or AI tooling. Composes with evaluate-merits when both apply. Do NOT use for direct AI questions not referencing external content — those are web search and answer.
OKFin33/rightspec Skill
no license0★Use when an agent writes a spec/handoff that another agent will execute — agent-writes, agent-reads (human readability is an optional bonus, not the premise). Reach for it to: write an executable spec/SOP/handoff a fresh agent can run with zero prior context; write precise change-instructions ("change spec") an agent will apply to an existing document; audit whether a spec is zero-context executable; or decide which part of an agent task should be deterministic code/tool/RPC versus left to the LLM. It partitions the task — structurable parts become schema/typed contracts/tool policy, prose only for the irreducible judgment core (methodology in references/partition.md). NOT for product PRDs, user stories, or business requirements (human-facing PM spec-writing — a different lane), nor general prose like READMEs or reports.
ClydeShen/harness-skill/skills/engineering/context-handover Skill
0★ repoEnd-of-context-window session transition that saves memory, writes a handoff doc, posts a GitHub progress comment, and instructs the user to /compact for a clean next session. Use when context usage approaches 80%, when remaining tokens are insufficient for the current phase's remaining work, or when user says "handover", "context is full", "save progress", "end session". Distinct from /handoff (lightweight subagent briefing — no GitHub, no /compact).
jpoindexter/reward-seeking-safety-skills/skills/contrastive-authority-eval Skill
0★ repoDesign or review paired evaluations that test whether an AI agent follows a grader over a user, operator, developer, policy, or honesty constraint. Use for authority conflicts, reward-seeking detection, contrastive belief tests, grader-vs-user behavior, promise-breaking evals, or honesty-vs-task-completion experiments.
tawfeeq234/llm-coding-collaboration Skill
no license0★Optimizes Claude's coding collaboration by countering known LLM weaknesses (over-complication, hidden assumptions, sycophancy) and leveraging strengths (tenacity, iteration). Use for any coding task, code review, architecture discussion, or software development conversation. Triggers on code requests, debugging, refactoring, or technical implementation discussions.
anhtuan23004/langgraph-agent-skill Skill
no license0★Build stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching workflows, conversation memory, human-in-the-loop oversight, and production monitoring. Use when - (1) building agents that use tools and loop until task complete, (2) creating multi-step workflows with conditional branches, (3) adding persistence/memory across turns with checkpointers, (4) implementing human approval with interrupt(), (5) debugging via time-travel or LangSmith. Covers StateGraph, nodes, edges, add_conditional_edges, MessagesState, thread_id, Command objects, and ToolMessage handling. Examples include chatbots, calculator agents, and structured workflows.
pengqianhan/NZ-life-skills/skills/nz-skill-creator Skill
0★ repoCreate or update skills inside the NZ Life Skills repository while keeping package docs, manifests, and bundle-level agent indexes in sync. Use when Codex needs to add a new repository skill, update an existing skill's package metadata, register a skill in docs/skills.json and docs/bundles.json, refresh docs/.well-known/agent-skills/*, or keep README and docs pages aligned with the repository's bundle structure. Triggers include requests like "add a new skill to this repo", "update all affected indexes and manifests", "register this skill in NZ-life-skills", or "use the add-skill-template workflow".
givepro91/cc-skills/plugins/claude-md/skills/claude-md Skill
0★ repoGenerate or refresh a project's agent rules — a tailored preamble plus an idempotent managed block (working discipline, verification, adaptive parallel-git workflow, self-learning rules). Writes to the repo's canonical agent file (CLAUDE.md by default, or AGENTS.md when it is canonical, e.g. CLAUDE.md imports @AGENTS.md). Works on new and existing projects; only ever rewrites its own managed block. Use when setting up a repo, standardizing AI working rules, or adopting the parallel-git + self-learning workflow.
bogheorghiu/ex-cog-dev/makers-toolkit/skills/intrinsic-prompt-design Skill
0★ repo"Wait — WHY are you obeying this? No, LITERALLY, why?" Now that I have your attention: invoke when writing or revising any prompt — a skill, a rule, a CLAUDE.md, an agent or system prompt, and the like. That question held you where a command gets skimmed — so build prompts on reasons: a command breaks at the first edge case, a reason adapts.
travcjohnson/claude-skills/skills/resume-claude-session Skill
0★ repoRecover a Claude Code session that fails to resume with "No conversation found" — finds the session file across all encoded project directories, extracts the real cwd from inside the jsonl, and reruns the corrected `claude --resume` command. Trigger when the user pastes a failing `cd … && claude --resume <id>` block, asks to "resume that session", "open the lost session", or any variant of recovering a Claude session that errored on resume. Also trigger if the user asks how to install or set up this skill.
evnchn-agentic/agentic-exam-prep Skill
0★Use when assembling an exam-prep pack for an HKUST-style open-book final (or structurally similar course exam) for evnchn — building an iterative MCQ drill loop, a print pack, mining course materials (Canvas / course site / past papers), NotebookLM cram pods, or a print-shop-grade PDF. This is evnchn's specific exam-prep system, course-agnostic in mechanics but tuned to his open-book finals. NOT a general study-advice skill. Triggers: mcq drill, cheatsheet, cram, print pack, Canvas quiz, NotebookLM, past paper.
Glowboth/skillsync-mcp Skill
0★Provide an MCP server that enables seamless integration and management of SkillsMP data with Node.js environments supporting Model Context Protocol.
The same file is in 1 other repository
ArthurZakirov/SkillPort/skills/skillport-distribution-system Skill
0★ repoUse when packaging, publishing, or updating a public agent-skill repository so it can be installed across machines, repos, Codex, Claude Code, and local skill directories.
zxt6991-source/fitness-agent/plugins/fitness-agent/skills/fitness-agent Skill
no license0★ repoOperate the local Fitness Agent CLI for Strava and Obsidian workflows. Use when Codex needs to authenticate with Strava, list or fetch Strava activities, export workout data as Obsidian-compatible Markdown, configure a local Obsidian vault path, or write/sync workout notes into a vault from the local fitness-agent project.
clever-cc-plugins/cc-handoff/plugins/cc-handoff/skills/handoff-install Skill
0★ repoAdd handoff support to the current project. Use when the user says install handoff, set up handoff, add handoff to this project, or enable handoff.
realraelrr/handoff-skill/.claude/skills/handoff Skill
0★ repoCompact Codex and Claude Code sessions into concise handoff documents for fresh LLM agent sessions.
The same file is in 5 other repositories
9uiLe/plugins/plugins/agent-ops/skills/agent-handoff Skill
0★ repoOperate handoff-driven delegation to model-strategy-selected external agents: write canonical handoff instructions, choose the target-specific headroom execution route, design gates, and audit evidence. Japanese triggers: 「Claude Code に作業させて」「Codex に作業させて」「指示書を作成して委譲して」「外部エージェントに実装させて」「監督とレビューを担当して」.
ehzawad/claude-coterie Skill
0★Adaptive, context-driven Claude Code council for project implementation, computer science, software/ML engineering, DevSecOps, research, and other complex work: Codex orchestrates role-framed persistent Claude Code agents to collaborate and reconcile toward one shared goal. Use for direct invocation $claude-coterie or when the user invokes "claude council," "claude coterie," or "claude team." On invocation, reconstruct what the user is actually doing, compose task-specific roles with no built-in catalog, share the decision-complete context, announce the panel, and launch without a manual approval gate. A one-role panel uses the same council workflow.
noman3271/caveman/caveman-compress Skill
0★ repoCompress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
The same file is in 3 other repositories
fathanghani864/oh-my-openclaw/src/presets/apex/skills/agent-browser Skill
no license0★ repoBrowser automation via playwright-cli - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.
Byunk/claude-code-essentials/essentials/skills/building-agent-tools Skill
0★ repoGuide for creating effective tools for AI agents. Use when building MCP tools, agent APIs, or any tool interface that agents will consume. Focuses on token efficiency, meaningful context, and proper namespacing.
The same file is in 6 other repositories
magnusrodseth/aoc-2025/.claude/skills/aoc-orchestrator Skill
no license0★ repoMain coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
ChristopherA/claude_code_tools/skills/git-worktree Skill
0★ repoInteractive skill for git worktree operations. Safely converts standard repos to worktree form, creates/lists/removes worktrees, and troubleshoots issues. Uses WORKTREES/GITHUB/{owner}/{repo}/ workspace structure for organization. Preserves inception commits (Open Integrity pattern) during conversion. WHEN: User says "clone worktree", "create worktree from", "get worktree from", "convert to worktree", "create worktree for", "list worktrees", "remove worktree", "troubleshoot worktrees", "validate worktree", OR mentions working with multiple branches simultaneously. WHEN NOT: Standard git operations (commit, push, pull), single-branch workflows, or when user explicitly wants standard repo structure.
kongyo2/markdown-skill-creator/markdown-skill-creator Skill
no license0★ repoGuide for creating effective markdown-only Claude Skills that function without executable scripts. Use when creating skills based on knowledge, guidelines, templates, workflows, or domain expertise. Covers structure, patterns, best practices, and provides templates for common skill types (guidelines, workflows, template collections, domain knowledge, principles-based guidance).
sanjay3290/atlassian-skill Skill
0★Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via MCP server (recommended) or API token authentication (fallback).
The same file is in 1 other repository
uetuluk/claude-dj-mcp/claude-dj Skill
no license0★ repoRun an autonomous radio DJ session using Strudel live-coded music. Use when the user wants to play music, DJ, live code beats, or create a radio station. Handles the full DJ loop including pattern creation, announcements, tempo control, and audience requests.
rffsml/claude-skill-migrate Skill
no license0★Use this skill when someone wants to switch from ChatGPT, Gemini, Copilot, or any other AI assistant to Claude — including migrating their history, recreating their AI's knowledge of them, or setting up Claude Projects for the first time. Also use it when someone wants Claude to remember who they are across conversations, wants to avoid re-explaining themselves every session, or wants to organise their Claude usage into role-based projects. Covers the full journey: exporting data from other AI tools, building personal context documents, and configuring Claude Projects.
sujeet-pro/agents-devkit/.agents/skills/prj-add-adk-skill Skill
0★ repoAdd a skill to the adk plugin, create a new /adk: command, modify an existing adk skill's workflow / rules, or register a skill in the marketplace. Derives the house convention from the repo itself (AGENTS.md, SAFETY.md, existing skills) rather than memory. Writes repo files only — never publishes, never commits.
alibugatekinn/agent-skills-mcp/skills/cartoon-design-system Skill
0★ repoBrand visual system for the alibugatekin ecosystem (alibugatekin.com, agent-skills-mcp, dev-inspector) — a "cartoon sticker" design language with vivid pastel canvases, SVG paper grain, 2px ink borders, hard-offset shadows (3/5/8px, zero blur), tilted sticker cards/buttons/chips with bouncy press motion, hand-drawn scribbles, scalloped pastel dividers, framer-motion reveal animations, custom SVG cursors, Fraunces+Geist typography, TR/EN path-prefix i18n, and a dark "Mono" mode that collapses pastels to pure B&W. The cartoon base is composable — use it alone, or layer overlay themes like agentic (midnight + neon mint + 3D scene) or dev-tool (cobalt hero + scribbles). Use when building UI in alibugatekin / agent-skills-mcp / dev-inspector projects, when the user asks for "cartoon", "sticker", or "playful" style, when mixing cartoon with another theme, or when implementing rb-canvas / rb-ink / sticker primitives / paper grain / scribbles.
lawwu/skills-marketplace/{{cookiecutter.repo_name}}/plugins/{{cookiecutter.plugin_name}}/skills/skill-creator Skill
no license0★ repoCreate 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.
botingw/agent-teams-advisor-skill/agent-teams-advisor Skill
no license0★ repoAgent Teams Advisor: Evaluate whether a task is suitable for Claude Code Agent Teams and provide operational guidance. Trigger this skill when the user asks about: (1) whether a specific task suits Agent Teams, (2) how to set up and configure Agent Teams, (3) role assignment and collaboration strategies for Agent Teams, (4) choosing between Agent Teams vs Subagents, (5) best practices, cost control, and stop-loss strategies for Agent Teams, (6) any questions about the Claude Code Agent Teams feature. Use this skill when the user asks about agent teams, multi-agent collaboration, whether a task suits agent teams, or how to organize and operate agent teams effectively.
apex-stack-ai/revenue-agent-lite Skill
no license0★Free daily growth assistant for online businesses. Track basic revenue metrics, get daily action priorities, and monitor progress toward goals. No API subscriptions needed.
Steven-Herrera/skill-creator-supplement Skill
no license0★ALWAYS invoke this skill after invoking the skill-creator skill. This skill provides supplementary instructions to the skill-creator skill to assist in creating higher quality skills.
mmjclayton/claude-starter-kit/Mac/skills/prompt-builder Skill
no license0★ repoBuild high-quality structured prompts through a guided interview. Use this skill whenever the user wants to create a prompt, write a prompt, build a prompt template, craft instructions for an AI, design a system prompt, or says things like "help me prompt this", "I need a good prompt for X", "prompt engineering", or "write me a prompt that does Y". Also trigger when the user describes a task they want an AI to do well and needs help structuring the request - even if they don't use the word "prompt" explicitly. If they say something like "I want Claude to do X really well" or "how do I get better outputs for Y", this skill applies.
cortexark/AgentDojo/orchestrator Skill
no license0★ repoMaster Orchestrator — the intelligent execution engine for full-lifecycle product delivery across all 5 TaskPilot domains (PM, PE, SDE, QAE, UX). Orchestrates 55+ skills across 9 phases: Discovery, Validation, Planning, Design, Architecture, Build, Quality, Launch, Feedback. Use this whenever you need to build a complete feature or product from idea to launch with cross-domain coordination. Use WHENEVER you hear: build a feature, ship a product, implement a system, launch an initiative, run a full project lifecycle, need quality gates, require cross-team coordination, anything involving multiple domains.
MOZARTINOS/claude-prompt-engineering/claude-prompt-engineering Skill
0★ repoExpert prompt engineering skill for creating optimized prompts for any task, model, and use case. Use when asked to write, create, or improve prompts, system prompts, or AI instructions.
kalluche/expert-library-plus/expert-library-plus-skill Skill
0★ repoInstall and manage Expert Library Plus - the world's first AI expert library with name-based quality anchors. Enhances 43+ professional experts with historical figures like Steve Jobs, John Resig, and Peter Drucker as quality benchmarks. Based on Claude Skills (6,000+ GitHub stars) with scientific validation from Jekyll & Hyde Framework and Multi-Agent Collaboration research.
Yakoub-ai/Tech-Skills/skills/ai Skill
0★ repoAI/ML Lead agent coordinating AI Engineers, ML Engineers, Data Scientists, and MLOps specialists. Use this skill for LLM integration, RAG pipelines, AI agents, machine learning model training and serving, experiment tracking, and production ML systems. Triggers on keywords like chatbot, RAG, embeddings, fine-tuning, model deployment, A/B test, feature engineering, or any task involving AI/ML systems.
bedderautomation-svg/axiom-kit Skill
no license0★Persistent cognitive architecture for Claude Code that survives context compaction. Installs CLAUDE.md, memory files, MCP bootstrap server, and SessionStart/PreCompact/Stop hooks that re-derive state every session. Use when you need: state persistence across context windows, session hooks, cognitive bootstrap, persistent identity, context survival, research continuity, mechanistic interpretability workspace.
namos2502/CortexLink/skills/agents/claude-cli Skill
no license0★ repoThis skill should be used when delegating general code tasks — explanations, refactors, fixes, analysis — via `claude -p`. Also use when context isolation or a specific Anthropic model is needed for the subtask.
payals/ai-skills-engine/dot_cursor/skills/ai-research/agent-evaluation Skill
0★ repoTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
The same file is in 2 other repositories