#SkillRepo stars
- 1921High End Visual Designcatch-the-wave/fullstack-ios-claude-skillsTeaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.5
- 1922Oldhandberwinsingh/oldhandConducts non-trivial software work end to end through a chain of stage skills: reads the ticket or prompt, traces the real code path, reuses proven code, makes the smallest correct change, has sub-agents review and QA it in the running app, and lets a computed verdict, not the model, say when it is done. Use when the user asks to implement, build, fix, debug, root-cause, investigate, QA or verify a feature or bug; says "pick up this ticket", "work on ENG-123", "fix this bug", "why is X broken", "plan this first" or "make sure it works end to end"; or pastes a Jira, Linear, Asana, monday.com or9
- 1923Oldhand Traceberwinsingh/oldhandMaps the real path a change or bug runs through, hop by hop from the entry point to the rendered result: file:line, what happens, timeout and retries, and failure mode for each hop; every caller, reader and sibling of the code that will change; which process runs each phase; the config the runtime really reads; and the trust boundaries. Can spawn read-only scout sub-agents, one per subsystem. Use when the user says "trace this", "where does this happen", "what calls this", "map the flow" or "what would this change break". Not for one-file edits with no callers, or for explaining a snippet. One9
- 1924System Prompt Engineerlvcoi/solidJSkillsAuthor and review system prompts for agent behavior control, instruction precedence, safety constraints, and output contracts. Use when defining or auditing operational prompts for reliability.9
- 1925AI Paper WritingHOWILLMAKEIT/skills辅助 AI 论文写作,分两类任务。一是论文主图、方法图、机制图和图形摘要:搜集顶会同类型参考图,写网页生图提示词,用户手动生图后重建为原生可编辑 PPT。二是摘要、Introduction、实验等文字段落:先搜集相关领域顶会的对应段落到文件夹(md),暂停;用户需要时再阅读并总结写法与共同逻辑,暂停;再按总结的逻辑顺序,结合用户提供的代码和论文草稿完成写作。文字写作的三步各自暂停,等用户确认后才进入下一步。实测数据图应从真实数据绘制。9
- 1926Recover Semantic Modelkr4chinin/skillsRecover a program's minimal semantic model (the state that changes what users see, how its transitions repeat and reorder, what each effect requires). Use when asked to recover or audit that model, to check what is idempotent or order-dependent, or to split a refactor into provably equivalent and "trust me" changes.9
- 1927Storyblok Use MCPstoryblok/agent-pluginUse when interacting with Storyblok through the MCP server — the tool model, operation names and payload shapes for stories, assets, components, datasources and every other resource. Load it before calling `mcp__storyblok__` tools, alongside the skill that owns the task.9
- 1928Agent BuilderNikolasMarkou/agent-builderBuild, review, troubleshoot, optimize, and extend AI agents — single-agent, multi-agent, RAG, and production systems. Covers framework selection, pattern selection (topology, behavioral, data flow), agent orchestration, state design, and tool design. Defaults to Python with LangChain/LangGraph; also supports CrewAI, Strands, OpenAI Agents SDK, Google ADK, and Mastra. Use whenever the user wants to build, design, scaffold, review, debug, optimize, extend, or migrate an agent or agentic system.5
- 1929Agent Design FundamentalsArchive228/lab-skillsDecision rules for whether to build an LLM agent and how to architect it, distilled from OpenAI's "A Practical Guide to Building Agents": build/no-build criteria, model selection, tool design, single-agent vs multi-agent orchestration (manager pattern vs decentralized handoffs), layered guardrails, and human-in-the-loop triggers. Use when designing, reviewing, or refactoring an agent system — before choosing an architecture, adding more agents, defining tools, or shipping an agent to production without guardrails.10
- 1930Agent EvalsArchive228/lab-skillsBuild and maintain evaluation suites for AI agents: bootstrap 20-50 tasks from real failures, pick code-based vs model-based vs human graders by agent architecture (coding, conversational, research, computer-use), write unambiguous tasks with reference solutions, and keep suites alive via ownership and transcript reading. Use when creating evals from zero, adding graders or eval cases, debugging suspicious eval scores, or deciding pass@k vs pass^k metrics for an agent product.10
- 1931Agent Failure PreflightArchive228/lab-skillsPre-deployment failure-mode gate for agentic AI systems, distilled from Microsoft AI Red Team's Taxonomy of Failure Modes in Agentic AI Systems v2.0 (grounded in 12 months of red-team engagements). Run it before shipping or materially changing an agent — adding tools/MCP servers/plugins, enabling persistent memory, adding sub-agents or orchestration, enabling computer use, or expanding permissions — to verify concrete controls against memory poisoning, HitL bypass, goal hijacking, supply-chain compromise, session context contamination, capability disclosure, and multi-agent cascade failures.10
- 1932Agent Improvement LoopArchive228/lab-skillsOperate a trace-driven improvement loop for a deployed agent: capture execution traces, convert human and model feedback into Promptfoo evals, gate the current harness against them, rank harness changes with HALO, and hand off a Codex-ready change set. Use when an agent is live and you need a repeatable cadence for diagnosing failures and shipping harness fixes — not for pre-launch prompt tinkering without traces.10
- 1933Agent SandboxingArchive228/lab-skillsContainment architecture for agent products that execute code, browse, or call tools, distilled from Anthropic's "How we contain Claude across products". Use when designing or reviewing sandboxing, isolation, permission systems, egress controls, or untrusted-content handling for an agent, or when choosing between container, OS-sandbox, and VM isolation patterns; provides a threat-model checklist covering user misuse, model misbehavior, and external attacks.10
- 1934Agent Sessionsvladmdgolam/agent-skillsSearch, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi9
- 1935Agentic Coding DisciplineArchive228/lab-skillsWorking discipline for agentic coding sessions, distilled from Claude Code's official best-practices doc: close the loop with runnable verification (tests, /goal, Stop hooks, adversarial review subagents), separate explore/plan/code phases, keep CLAUDE.md lean, choose permissions/sandboxing deliberately, manage context aggressively (/clear, /compact, checkpoints), and scale with fan-out and agent teams. Use at the start of any non-trivial coding-agent session, when configuring an agent environment, or when a session shows drift, bloat, or unverified "done" claims.10
- 1936AI Readykargnas/skillsUse only when the user asks to make the repo AI-ready or AI-optimized (AGENTS.md migration, debugging/testing setup, docs). Do not run on your own.9
- 1937AI Resume Generatorhaorenhao58-sketch/ai-resume-generator一键生成互联网AI方向简历的通用工具。当用户提到'生成简历''写简历''AI简历''求职简历''更新简历',或提到想投递AI产品经理、AI运营、AI工程师、AI商业化、Prompt Engineer、LLM应用、AIGC等AI相关岗位时触发。也适用于用户说'帮我整理项目经历''优化简历表述''简历润色'等场景。该skill通过深度引导候选人输入个人信息与项目细节,运用'问题→方案→量化结果'三段式写作范式,生成突出AI思维与产品化能力的高质量简历,支持Markdown和Word两种输出格式。5
- 1938Apple Books MCPvladmdgolam/agent-skillsExtracts highlights, annotations, and book data from Apple Books via MCP. Use when: user asks to export book highlights, extract annotations with colors, search highlights across books, create highlight summaries, or match books from a reading list against their Apple Books library. Covers efficient batch color extraction (5 calls instead of 150+), annotation-to-book matching, and markdown export patterns.9
- 1939Cinema4d MCPvladmdgolam/agent-skillsCinema 4D MCP expert for extracting scene data, writing C4D Python scripts, and controlling Cinema 4D through MCP tools. Activate when: (1) using cinema4d MCP tools (get_scene_info, list_objects, execute_python_script, add_primitive, etc.), (2) writing Python scripts for Cinema 4D extraction or manipulation, (3) working with MoGraph cloners/effectors/fields, (4) baking animation data from C4D scenes, (5) debugging C4D Python API errors, (6) extracting Redshift material or camera data. Covers critical gotchas, correct extraction patterns, MoGraph baking, timeline evaluation, API compatibility, 9
- 1940Coding Agent SecurityArchive228/lab-skillsOperating procedure for securing and evaluating AI coding agents and their generated (vibe-coded) code, distilled from Google's Kaggle whitepaper "Vibe Coding Agent Security and Evaluation" (May 2026): the Effective Trust model, the 7-Pillar Agent Security Architecture, threat classes specific to agent-written code (slopsquatting, MCP spoofing, invisible payloads, intent drift), and the 7-dimension evaluation framework with pre-ship gates. Use when running, sandboxing, reviewing, or shipping agent-generated code, hardening an agent harness or CI pipeline, gating high-stakes agent actions, or b10
- 1941Context CompressionArchive228/lab-skillsCompress an agent's context — long environment observations and accumulated interaction history — on long-horizon tasks using Microsoft's ACON method: threshold-triggered LLM compression with guidelines optimized from contrastive failure analysis. Trigger when an agent loop's context grows across many tool-call steps and blows token budgets or degrades decisions, when designing what a summarizer/compressor must preserve, or when distilling a compressor into a smaller model.10
- 1942Context EngineeringArchive228/lab-skillsEngineer an agent's context window as a finite attention budget: prompt at the right altitude, give judgment instead of rigid rules, use expressive tools and progressive disclosure over piled-up instructions, delete redundancy, and manage long-horizon runs with compaction, notes, and sub-agents. Trigger whenever you write or audit a system prompt, CLAUDE.md, skill, or tool set for an agent; when an agent ignores instructions or degrades on long runs; or when migrating prompts to Claude 5-generation models.10
- 1943Gauntlet Loopsidneyswift/skillsRun iterative build-critique loops that push AI output past "good enough" toward a concrete quality bar. Give a lead agent a goal and a real reference to compare against. The agent decomposes the goal into the smallest independently-improvable pieces, assigns each piece a builder and a separate critic with fresh context, and loops until the output matches or exceeds the bar. Use when the first draft is never good enough — games, websites, product design, writing, marketing campaigns, code, research, or anything where output can be inspected and improved.9
- 1944Gpt 56 PromptingArchive228/lab-skillsOperating procedure for prompting the GPT-5.6 model family (gpt-5.6-sol/terra/luna) in agentic work: outcome-first prompts with explicit stopping conditions, autonomy and approval boundaries, tool routing, Programmatic Tool Calling, multi-agent (beta), reasoning effort and verbosity settings, and safe migration from GPT-5.5/5.4. Use whenever writing or revising system/developer prompts for GPT-5.6, wiring its tools, tuning reasoning.effort or text.verbosity, or debugging over-asking, over-stopping, or tool-loop behavior on these models.10
- 1945Graph Maxsidneyswift/skillsTurn any hand-drawn workflow graph into a working multi-agent script. Draw the graph in any tool (whiteboard, paper, Excalidraw, napkin), photograph or screenshot it, send it to a coding agent with a single prompt, and get a running orchestration script back. The skill teaches graph literacy — how to draw nodes, edges, fan-outs, feedback loops, and decision gates so the coding agent can implement them faithfully. Use when someone has a workflow in their head but no code, wants to orchestrate multiple agents, or asks "how do I wire these steps together?9
- 1946Handoff Specsidneyswift/skillsProduces a single markdown handoff document for a stateless successor agent (possibly on a different platform or session) to pick up in-progress work with zero conversation context. Combines a stable Goal/Spec section with a point-in-time Handoff Status section covering what's done, out-of-scope work, remaining required work, nice-to-haves, what's live in production, what's merged but not deployed, and what's still in progress. Use when the current agent is running low on usage credits, context, or tokens; when the user says things like "I'm running out of credits/usage", "we need to hand this9
- 1947Humanizer Kill Gptkargnas/skillsRuns a cross-language cleanup for writing tells shared by large frontier LLMs, not only GPT: English source constructs that survive other language translation and language-surface translationese. Use only when the user asks to remove AI/GPT tells from text (de-GPT, GPT 티, AI 티, 번역체 GPT, 자폐 말투 — colloquial shorthand for rigid or over-complete model prose, not a claim about autism).9
- 1948Industrial Waste Heat Recoverydungnotnull/industrial-waste-heat-recovery-agent-skillIndustrial Waste-Heat Recovery System Design — Production-grade evidence-backed analysis harness with flexible agent architecture, skill registry, and modular sub-agents. Use for: waste-heat recovery design, heat exchanger selection, ORC systems, pinch analysis, energy efficiency assessment, industrial thermal system optimization. Triggers on: "waste heat", "heat recovery", "ORC", "pinch analysis", "heat exchanger", "energy efficiency", "thermal optimization", "industrial heat", "steam system", "condensate recovery".5
- 1949Long Running HarnessArchive228/lab-skillsOperating procedure for agent work that spans many context windows: split the run into a one-time initializer session (init.sh, feature_list.json, claude-progress.txt, initial git commit) and repeated coding sessions that each ship exactly one feature, verify it end-to-end via browser automation, and leave the repo in clean committed state. Trigger whenever a build will outlive a single context window (multi-hour/multi-day autonomous coding, session handoffs, resuming a scaffolded project), or when designing a harness/loop for such work.10
- 1950MCP 2026 MigrationArchive228/lab-skillsMigrate MCP servers, gateways, and clients to the 2026-07-28 specification: stateless request-response core (no initialize handshake, no Mcp-Session-Id, version/capabilities in _meta), required Mcp-Method/Mcp-Name headers, Multi Round-Trip Requests replacing server-initiated elicitation/sampling/roots, cacheable list results (ttlMs/cacheScope), CIMD auth over deprecated DCR, the extensions framework (Tasks, Apps, Skills over MCP), and the 12-month deprecation offramp for Roots/Sampling/Logging and HTTP+SSE. Trigger when upgrading any MCP implementation from protocol 2025-11-25 or earlier, writ10
- 1951MCP Code ExecutionArchive228/lab-skillsCut agent token consumption by calling MCP servers through generated code instead of direct tool invocations: present tools as typed wrapper files on a filesystem, discover them progressively, and keep intermediate data in the execution environment (Anthropic measured 150,000 → 2,000 tokens, a 98.7% saving). Trigger when an agent connects to many MCP servers/tools, when tool definitions eat a large share of the context window before work starts, when workflows pipe large intermediate results (transcripts, spreadsheets) between tools, or when sensitive data should not enter model context.10
- 1952Minimal Patch with Subagentskargnas/skillsMinimal patching workflow that debates fix options across parallel independent subagents and applies the smallest safe diff. Use only when you want risk-free code, and to code real minimal that only needs to fix the issue.9
- 1953Minimax H3 Promptkuronzzhan-droid/minimax-h3-prompt-skill按 MiniMax-H3 的两种有效格式撰写视频生成提示词(时间轴风格 / 官方结构化风格),覆盖 T2VA 文生视频、I2VA·FL2VA·L2VA 首尾帧、full-reference 参考生视频 R2V。只要用户想用本地 ComfyUI 的 H3 出视频、要求写或改 H3 提示词、提到 MiniMax H3 / ref2va / fl2va、给参考图或音色让角色说话唱歌、或抱怨 H3 出片"角色不像/台词乱语/声音不对/动作没跟上节拍",都应使用本技能——它带官方规范原文、两种风格的实战范例和本机显存实测约束。5
- 1954Monorepo AgentsArchive228/lab-skillsOperating procedure for running coding agents on large codebases and multi-million-line monorepos: agentic search over indexing, hierarchical CLAUDE.md layering, noise exclusion via .claudeignore and permissions.deny, LSP for symbol-level navigation, subagents for exploration/editing splits, and enterprise rollout patterns. Use when working in, configuring, or deploying Claude Code (or a similar agent harness) on a repo too large to hold in context — many services, hundreds of top-level folders, or millions of files.10
- 1955Phd Application Advisoralex-yimingyang/phd-application-advisor大龄非科班转AI申请海外PhD的全流程顾问。覆盖RA申请、选方向选校、套磁、文书、面试、推荐信、时间规划等所有环节,专门针对30+在职、非CS背景、想转AI方向申博的人群提供策略建议。 当用户提到以下任何场景时使用此skill:大龄读博、非科班申博、转行申PhD、30+申博、在职申博、工作后读博、非传统背景申请PhD、AI方向博士申请、美国博士申请、海外PhD、申博规划、申博咨询,或任何涉及"工作几年后想读博不知道怎么开始"的问题。即使用户没有明确说"非科班",只要描述了类似背景(非CS本科、工作多年、想转AI/ML方向读博),也应触发此skill。5
- 1956Planner Evaluator HarnessArchive228/lab-skillsMulti-agent harness pattern (planner / generator / evaluator) for long-running application builds, distilled from Anthropic's engineering post on harness design. Use when a build will run for hours or sits beyond what the current model ships reliably solo: covers sprint contracts, skeptical-evaluator calibration, hard-threshold QA grading via browser automation, context resets vs compaction, and how to strip the harness down as models improve.10
- 1957Prompt Cache OptimizationArchive228/lab-skillsMaximize OpenAI prompt-cache hit rate to cut time-to-first-token latency by up to 80% and input token cost by up to 90%: prefix-stability rules, cache-aware prompt layout, prompt_cache_key routing, allowed_tools, Responses API vs Chat Completions, Flex vs Batch, extended 24h caching, and Realtime retention_ratio. Use when designing or reviewing prompt/message layout for any repeated OpenAI API workload, when cached_tokens is low or zero, when TTFT or input spend is high at scale, or when choosing truncation/compaction strategy for long conversations. Scope: models before GPT-5.6 (per the sourc10
- 1958Prompt Engineering CanonArchive228/lab-skillsCanonical prompt-engineering operating procedure distilled from Google's 68-page Prompt Engineering whitepaper (Lee Boonstra, Feb 2025): when to use zero/few-shot, system/contextual/role prompting, chain-of-thought, step-back, self-consistency, ToT, ReAct, output-format control, and exact temperature/top-K/top-P starting values. Trigger whenever writing, reviewing, or debugging a prompt for an LLM, choosing sampling configuration, or deciding which prompting technique fits a task.10
- 1959Reverse Engineer Jsvladmdgolam/agent-skillsReverse-engineer minified or obfuscated JavaScript bundles. Primary tool: humanify (humanifyjs) — uses an LLM to rename mangled identifiers back to meaningful names. Default model: gemini-3.8-flash. Use when the user says 'deobfuscate this bundle', 'humanify this', 'rename minified vars', 'reverse engineer this JS', 'what does bundle.js do', or is working in a project with a deobfuscated `og/` or `modules/` folder fed by humanify. Covers humanify CLI invocation, the pseudo-TTY workaround for cursorTo crashes, single-module extraction from a bundle, and chaining with beautifiers.9
- 1960Semantic Compressiontherealmoronto/claude-semantic-compressionApply semantic logic compression (Ovchinnikov method) when crafting prompts for LLMs or describing complex conditional logic. Use this skill whenever the user asks to: write or optimise a prompt for an LLM, compress or rewrite a task description, describe multi-condition business logic (if/and/or/not chains), or asks why an LLM misunderstood their instructions. Also trigger when the user says ‘compress the logic’, ‘write a prompt for’, ‘the LLM doesn't understand’, ‘simplify the conditions’, or similar intents. Also trigger when the user wants to use output modifiers such as →code or →no-meta,5
- 1961Skill Managerkargnas/skillsCreates, restructures, merges, and splits agent skills: directory layout, bundled guides/scripts/assets, cross-agent placement under .agents/skills, importing community skills, merging several skills into one so fewer descriptions load into every session, and a sanitization pass that checks model IDs against models.dev. Triggers on 스킬 생성, 스킬 병합, 스킬 분리, 스킬 구조 정리, 외부 스킬 가져오기, 스킬 검증, 모델 업그레이드. Step wording and name/description wording go to skill-prompter; finding published skill packages goes to skill-finder. Confirm with the user before running, with a brief explanation of what this skill will 9
- 1962Skill Prompterkargnas/skillsPrompting compliance specialist for AI agent skills — rewrites SKILL.md steps with RFC 2119 wording, explicit tools, VERIFY gates, and dry-run checks; also owns skill name + frontmatter description wording (trigger-surface rules). Use only when the user asks to improve or harden a skill's prompts/steps or to name/review a skill description, and confirm with the user before running since this takes quite long time and need to run a few smoke tests with subagents to check if the skill is perfect. Structural lifecycle work goes to skill-manager.9
- 1963Skillssidneyswift/skillsInstall, list, update, or extend Sidney's curated collection of agent skills. Use when asked to install all of Sidney's favorite skills, bootstrap an agent from this collection, or add a skill repository to the collection. This is an installation gateway, not a skill-authoring or general skill-search workflow.9
- 1964Spec Driven DevArchive228/lab-skillsOperating procedure for spec-driven development (SDD) with AI coding agents: treat code as disposable and the specification as the durable, versioned asset, then run the Constitution → Specify → Plan → Tasks → Implement loop (GitHub Spec Kit) with behavior-driven Gherkin-style specs. Trigger whenever building software meant to outlive a prototype — production features, multi-session or multi-agent work on one codebase, or legacy regeneration/migration — instead of vibe-coding straight to code.10
- 1965Tool DesignArchive228/lab-skillsDesign and iterate on tools (MCP or direct API) that agents actually use well: prototype-then-evaluate loops, agent-assisted tool optimization, consolidated workflow tools, namespacing, high-signal responses, and token-efficient outputs. Use when writing or refactoring tool definitions, building an MCP server, debugging why an agent misuses/ignores tools, or reviewing tool schemas and descriptions.10
- 1966Trop Image Promptsabsolument-ai/tropWrites AI image prompts with a strong, recognizable art-direction signature (raw, human-first, trend-driven, typography-led) for Midjourney, ChatGPT/GPT Image, Gemini, Flux, Ideogram and similar. Use whenever the user asks for an image prompt, a visual, a poster, a key visual, an ad image, a moodboard prompt, a "prompt Midjourney", or wants an idea turned into an AI image — even a one-line brief.5
- 1967Workspace Ossidneyswift/skillsUse when a user wants to set up, scaffold, or reorganize a workspace or operating system for any domain; turn files, notes, or a prompt into a managed system; or make consequential work resumable across people, agents, and sessions.9
- 1968Zero Trust AgentsArchive228/lab-skillsZero-trust security framework for deploying autonomous AI agents in an enterprise, distilled from Anthropic's official "Zero Trust for AI Agents" eBook: the Foundation/Enterprise/Advanced tier model, defenses against prompt injection, tool poisoning, memory poisoning and supply-chain attacks, and an 8-phase deployment workflow. Use when designing, reviewing, hardening, or auditing any agent deployment — agent identity and credentials, tool/MCP access, sandboxing, memory persistence, multi-agent delegation, or security operations around agents.10