agentsclimarketplace

The catalog

608,666 rows, by stacks then stars

  • Mask

    zj021033/mask Skill

    1★

    戴上名人/名角色的"面具"来写文案——让输出一眼认出是谁,彻底去掉 AI 味。 Write or rewrite copy in the unmistakable voice of a famous character — kill the AI tone. 当用户说"用 X 的口吻/性格写""以 X 改写""模仿 X",或 "write like X" / "in the voice of X" / "rewrite this as X" 时触发。中文角色:孙悟空、猪八戒、唐僧、牛魔王、红孩儿、林黛玉、王熙凤、 张飞、诸葛亮、鲁智深。English: Sherlock Holmes, Yoda, Shakespeare. 核心是注入角色的"语言指纹"(自称、口头禅、句式、用词),而不是套性格标签 — inject the character's linguistic fingerprint, not personality labels.

  • Gh draft

    JordanTheJet/agentday-zeroclaw/.claude/skills/gh-draft Skill

    1★ repo

    Ask about, edit, or act on a GitHub-notification draft from Discord — draft-only.

  • Acui real property storyline

    cuiyan0412/acui-real-property-storyline Skill

    no license1★

    为地产项目(住宅/办公/商业三业态)策划完整故事线storyline。当用户提到"地产故事线/项目故事线/项目定位/项目策划/案名策划/营销主题/招商招租脚本/写字楼故事线/住宅故事线/商业故事线/产业园故事线/特色街区故事线/品牌叙事/项目品牌"或要为某个住宅/办公楼/产业园/商业综合体/购物中心/特色街区/度假商业设计品牌叙事时使用。

  • Analyse task

    vecten/sdlc-toolkit/skills/analyse-task Skill

    1★ repo

    Analyse a ticket from the configured PM tool, gather context from the codebase, produce a tech or non-tech plan, update the ticket, prepare questions for PM/client, send a Slack notification, and draft a client email. Use when the user says "analyse task", "analyze ticket", "plan task", "review ticket", "what does this ticket need", or provides a ticket URL/ID with analysis intent.

  • Chromadb management

    dor-rondel/agent-skills-mcp/resources/docker/chromadb-management Skill

    1★ repo

    Use this skill when the user asks to inspect, query, reset, or manage collections inside the ChromaDB vector store container.

  • Skills

    DeFiHackLabs/defi-incident-investigation-skill/skills Skill

    no license1★ repo

    Investigate DeFi security incidents with multi-agent on-chain verification. Gathers intel, enriches insufficient sources via web search, drafts schema-compliant JSON reports, verifies all claims against on-chain data, and runs adversarial validation before finalizing.

  • Lazyway io design

    jpbaking/lazyway-io-design/skills/shared/lazyway-io-design Skill

    no license1★ repo

    Build or edit web pages and UI in the lazyway.io design system (IBM Plex, brand blue #12279E, one amber accent, design/styles.css + design/components.css). Use when creating or styling HTML pages, React apps/components, landing pages, dashboards, blogs, docs sites, single-function app UIs (url-shortener style), charts, modals, forms, tables, tiles, date/time pickers, or favicons in a project that uses this kit — or when the user mentions lazyway design, the design kit, lw components, or the brand style guide.

  • Local memory skill

    yaoxiao99/local-memory-skill Skill

    1★

    Use when an agent needs to set up, read, write, or maintain a fully local Markdown-based memory system; when the user says "remember this", "save to memory", "set up local memory", or wants cross-session context without a cloud memory provider.

  • Influencer profile board

    bogdankrupin/influencer-profile-board/influencer-profile-board Skill

    1★ repo

    Build a rich, interactive single-file HTML profile board for any public figure, creator, or influencer in any niche. Pulls public information via web search and structures it into identity & contact, social presence + follower counts, expertise, notable work and links, key facts, and an optional LLM-visibility read. Use this skill whenever the user wants to profile, research, or "make a card / board / dossier" about a creator, influencer, expert, founder, athlete, or public personality — phrases like "tell me about [person]", "build a profile of [name]", "make an influencer board", or "who is [name] and what are they known for". Trigger even when the user doesn't say "board" or "skill", as long as they want a structured profile of a named person. When the SE Ranking connector or API is available, the board is enriched with live AI-search data (how the person shows up in ChatGPT and Google AI Overviews / AI Mode), and it falls back to the web-search-only board when SE Ranking is absent or out of credits.

  • Unlock fujifilm film simulations

    chr1sc2y/fujifilm-film-sim-skill/skills/unlock-fujifilm-film-simulations Skill

    1★ repo

    Use when a user provides a RAW or DNG photo directory and wants Adobe Lightroom or Camera Raw to expose Fujifilm camera profiles or film simulations.

  • Code review

    aictrl-dev/skills/skills/code-review Skill

    1★ repo

    Review the exact head revision of a pull request for actionable correctness, security, reliability, performance, and test findings without modifying code. Use when the user says "review this PR", "do a code review", "find defects in this change", or provides a pull or merge request identifier.

  • Audit

    josezuma/ai-visibility-geo-toolkit/.claude/skills/audit Skill

    no license1★ repo

    Full GEO readiness audit of any URL. Score 0-100 across llms.txt, schema.org, EEAT signals, robots.txt, citability. Returns actionable recommendations.

  • Relationship intelligence

    mxbao063-bao/relationship-intelligence-agent/.cline/skills/relationship-intelligence Skill

    1★ repo

    Calculate and interpret one person's natal chart or analyze two people's relationship astrology. Use for natal positions and aspects, synastry, midpoint composite, Davison, Marks charts, birth-place resolution, and evidence-led astrology reports.

  • Run skill generator

    pleaseai/run-verify-plugin/skills/run-skill-generator Skill

    1★ repo

    Author or improve the run-<unit> skill — a per-project skill that tells agents how to build, launch, and drive this project's app. Use when the user asks to set up the project, get it running, write run instructions, or verify build/run steps work from a clean environment.

  • Ive got the big sad

    rastagan-git/ive-got-the-big-sad/.agents/skills/ive-got-the-big-sad Skill

    1★ repo

    Produce concise, low-affect, emotionally neutral answers when the user explicitly invokes $ive-got-the-big-sad. Use for token-conscious replies, deadpan wording, minimal emotional expression, or terse status updates. Do not use merely because a prompt mentions depression, sadness, mental illness, self-harm, or suicide; this skill does not diagnose, treat, or simulate clinical depression.

  • Traceable meeting minutes

    Rangooo/traceable-meeting-minutes Skill

    1★

    Turn meetings, interviews, calls, and earnings-call recordings or transcripts into accurate, actionable, and traceable minutes. Use for short internal meetings, design reviews, standups, long interviews, research calls, earnings calls, “meeting minutes”, “整理纪要”, “整理访谈”, “会议纪要”, or when decisions, action items, numerical scope, evidence links, or cross-validation are required. Supports audio (mp3, m4a, wav, flac), documents (docx, txt, md), and zip archives.

  • Codex

    mwgg/skills/plugins/codex Skill

    1★ repo

    Get an independent second-opinion review from the Codex CLI on a plan or a round of code changes, returning a clear verdict. Use when the user asks to "run codex", "codex review", "codex check", "review this with codex", "second opinion", "review my plan", or wants an outside reviewer over the current changes — in any project, git or not. Two modes — plan review (before code, verdict SOLID/WEAKNESSES) and code review (after changes, verdict APPROVE/COMMENTS). Advisory, never a hard gate. Other skills (e.g. gsd) call this to add review checkpoints.

  • Ste

    phb123/ste/skills/ste Skill

    1★ repo

    Use when a user is confused or asks an agent to clarify, simplify, de-jargon, rewrite, or review technical content for clarity without losing important details.

  • Auto polish skill

    Shavy72/auto-polish-skill Skill

    1★

    Mandatory final phase for every new UI/frontend build (feature, page, component, redesign, full app) — runs automatically, without the user asking. Mini-addons (<~30 changed lines) only on demand via /auto-polish. Runs a dynamic multi-agent workflow with fixed amplification stages 5x → 10x → +3x and design judges in between, including a resource inventory (which installed skills/MCPs are still unused?), sign-off from every angle (desktop, mobile, code, video for animations) — local first, then live after shipping. Triggers (DE+EN): feature finished, polish phase, 'auto-polish', 'polish das', 'maximal geiler machen', 'showcase level', 'design steigern'.

  • Analyze shopify app competitors

    applora/agent-skills/skills/analyze-shopify-app-competitors Skill

    1★ repo

    Produces evidence-backed Shopify app competitor teardowns using listings, pricing, rankings, review sentiment, developer portfolios, and change history from Applora MCP. Use when comparing competitors, finding differentiation, preparing battlecards, tracking market moves, or identifying weaknesses worth building against.

  • Glumoo pet health

    Glumoo-ai/glumoo-pet-health-skill/glumoo-pet-health Skill

    1★ repo

    Safety-first bilingual pet health and nutrition guidance for cats and dogs. Use for 猫狗健康、症状、饮食、营养、补充剂、毒物、中暑、呕吐腹泻、尿闭、肥胖、幼宠/老年宠物照护, or questions about pet wellness, feeding, supplements, possible poisoning, emergency signs, and Glumoo products. Triage emergencies before education, gather species/life-stage context, cite current veterinary sources, and keep brand information separate from neutral guidance. Never diagnose, prescribe, calculate poison doses, or replace a veterinarian.

  • Skills

    SylphxAI/skills Skill

    1★

    Install, update, or verify the complete SylphxAI/skills managed environment for the current Codex, Claude Code, or Grok runtime, including AutoSync and canonical Sylphx Enact SaaS enrollment. Use when a user gives this repository and says "install this", asks to update Sylphx Skills, or requests installation readback. Read the repository's INSTALL.md before choosing any generic Skill installer; folder copies alone are incomplete, and other runtimes stay untouched unless the user explicitly includes them.

  • Cvopenmic

    zihengniu9/CVOpenMic/skills/cvopenmic Skill

    1★ repo

    Review and rewrite resumes with evidence-based scoring, target-job matching, ATS checks, privacy protection, fact-safe edits, and an optional Bazi career-reflection module. Use when a user asks to critique, roast, diagnose, score, tailor, translate, or rewrite a Chinese or English resume/CV, compare it with a job description, or explicitly asks whether a role suits them from a 八字、四柱、命理、五行 perspective.

  • Scientific writing zh

    ly0715-edit/scientific-writing-zh/skills/scientific-writing-zh Skill

    1★ repo

    Use when drafting, revising, reviewing, or de-templating Chinese scientific papers, technical reports, project documents, proposals, meeting records, or formal deliverables.

  • Generic context planner

    xiw249/agent-context-planner/skills/generic-context-planner Skill

    1★ repo

    A deterministic, hash-aware context planner that helps coding agents load only the files they need.

  • Generic commit skill

    paranoidandroid2124/sounds-like-a-skill-issue/evals/fixtures/generic-commit-skill Skill

    1★ repo

    Use when creating any Git commit.

  • Diary digest

    sfaustodev/discipline/skills/diary-digest Skill

    1★ repo

    Periodic reflective harvest of an append-only engineering journal (discipline/DIARY.md or any long log/changelog/postmortem). Reads the WHOLE journal via parallel diary-miner subagents, performs a k0-k4 metacognitive reflection over the mistakes and successes, turns every recurring mistake into a proposed mechanical gate, and saves the consolidated learning to Mycorrhiza. Use when the user asks for a "digest", "diary digest", "harvest do diary", "o que dá pra aprender do diary", "reflexão do diário", "mine the journal", "lessons from the log", a retro/postmortem over accumulated entries, or periodically when DIARY.md has grown by many entries since the last harvest. Output is lessons + proposed automation, NOT edits to the constitution (those are proposed and confirmed first).

  • Another skill

    LeoLin990405/skill-librarian/tests/fixture/another-skill Skill

    1★ repo

    Validate JSON against a schema and report the first failing path. Use when checking API payloads, config files, or fixtures against a JSON Schema, or debugging "why does this JSON not validate". Triggers on "validate json", "json schema check".

  • Mac optimizer

    ChuluuMGL/mac-optimizer Skill

    1★

    Use when a user wants to diagnose or safely optimize macOS storage, caches, startup items, logs, developer-tool residue, or routine Mac maintenance with risk-aware recommendations.

  • Skill manager

    potocibi/skills-manager/skills/skill-manager Skill

    1★ repo

    Manage, audit, deduplicate, merge, route, and APPLY the user's installed Claude Code skills, agents, commands, and plugins. Use when the user says "audit my skills", "dedupe skills", "merge skills", "skill registry", "which skill handles X", "skill health", "skill intake", "propose a skill", "should this be a skill?", "turn this into a skill", or BEFORE creating any new skill or agent (gap-check first). Also use when the user asks in plain English to run/use/apply whatever skill or agent handles a task ("use the right skill for this", "run the reviewer on this file", "apply whatever handles X") — resolve it from the registry and invoke it, chaining multi-step asks. Also use when the user shares a GitHub repo or folder of skills to compare against or import from ("is this skill better than mine", "check this skills repo", "add skills from this repo"), and to restore archived skills or fix registry drift.

  • Iching research

    ProfesseurHaipeng/iching-research-skill/skills/iching-research Skill

    1★ repo

    Research the I Ching and Zhouyi as textual and symbolic systems with reproducible hexagram casting, primary-text provenance, competing interpretations, and explicit uncertainty. Use when Codex is asked to explain, compare, cast, or design an educational workflow for 易经、周易、六十四卦、爻辞 or related traditions.

  • Codex internal agent orchestration

    FairladyZ625/codex-internal-agent-orchestration Skill

    1★

    Coordinate complex coding and knowledge-work tasks inside a user's target repository with Codex's current main agent and in-task internal subagents. Use for multi-agent task graphs, parallel exploration, disjoint implementation slices, long-running supervision, evidence collection, adversarial review, final integration, and Harness Anything task/decision/fact workflows when the target repository has adopted Harness Anything.

  • Claude multi agent

    SYMBaiEX/skills/skills/claude-multi-agent Skill

    1★ repo

    Hand off engineering work to Claude Code as an autonomous team or native dynamic workflow, with explicit Opus/Sonnet routing, foreground completion barriers, resumable sessions, repeatable JavaScript workflow phases, hooks, and worktree isolation. Use when another agent or CI needs Claude Code to implement a scoped task, run a codebase-wide audit or migration, execute research-build-verify-gap-close phases, launch work in the background, or install project subagents and `.claude/workflows`.

  • Procraft

    Xerneas216/ProCraft/skills/procraft Skill

    1★ repo

    Use when the requested deliverable is an AI or model Prompt, prompt text, or 提示词, including an LLM, Agent, image, video, or audio Prompt, or a system/developer/user message, tool policy, Structured Output contract, or reusable AI workflow specification; do not use for direct execution of writing, research, coding, summarization, email, image generation, or any other underlying task unless the user asks for the Prompt or instructions that will perform it.

  • Top cs figure

    zhiming33416/top-cs-paper-skills/skills/top-cs-figure Skill

    1★ repo

    Create, revise, audit, render, and export publication-ready computer-science paper figures using a Python-first, corpus-calibrated workflow. Use for manuscript figures, multi-panel experimental charts, comparison plots, scaling curves, heatmaps, embeddings, network diagrams, method schematics, executable YAML/CSV figure render specs, figure-brief handoffs, caption/callout alignment, SVG/PDF/PNG/TIFF export bundles, venue-style evidence checks, and visual QA for WWW, ICLR, ICML, or generic top-CS submissions. Prefer an existing top-cs figure brief or render spec when provided; otherwise build a compact figure contract before plotting. Do not use for interactive dashboards, Plotly/Altair/web apps, Illustrator/Figma-first layout, AI-generated graphical abstracts, or result-table writing.

  • Harness engineering init

    Kinghonga/harness-engineering-init Skill

    1★

    Initialize and operate a project's AI-agent harness-engineering loop so it actually runs, not just gets scaffolded. Scaffolds the .harness/ structure, checks whether the loop is alive, drives task checkpoints, failure-trace recording, and the Critic analysis that converts traces into failure-pattern memory and rule updates. Use when the user says "harness", asks to set up / check / run harness engineering, mentions .harness/ or AGENTS.md discipline, wants an AI coding agent's loop to self-improve, or when checkpoints/traces/memory are not being maintained. Makes silent harness failure visible and closes the trace-to-Critic-to-failures loop that usually dies.

  • Lean loop

    hermes98761234/lean-loop/skills/lean-loop Skill

    1★ repo

    Use when writing, fixing, or refactoring any code, before writing implementation code — especially under time pressure, with vague requirements, when asked to make something "configurable" or "flexible", or when running as a small or local model with limited context.

  • Aise capture

    jiayx01/PhysisAI/plugins/physisai/skills/aise-capture Skill

    1★ repo

    把用户明确纠正、个人习惯、模型未知的私有或项目知识、已验证工作流和质量门禁保存为待审候选。用户说记住、沉淀、以后按这个来,或明确纠正 AI 的项目事实与使用方式时使用;不直接晋升规则。

  • Ai pm jd analyzer

    chanthomas20180908-cpu/pigua-aipm-jd-analyzer/skills/ai-pm-jd-analyzer Skill

    1★ repo

    Analyze AI product manager, Agent, data-platform, and related product job descriptions using an evidence-based business meta-model. Use when an agent needs to explain what a JD actually requires, model value streams, work items, entities and capabilities, identify pseudo-AI or role-overload signals, or draft targeted interview questions. Do not use for resume matching, job application decisions, company web research, or running the repository API.

  • Social cover layout

    ChuluuMGL/social-cover-layout Skill

    1★

    把完成的内容 brief 变成适配小红书、X/Twitter、YouTube、微信及其他媒体表面的原创社交封面方案或生成封面。根据内容目的、平台比例、视觉主体和素材授权选择可质检的排版、配色和层叠路线。

  • Research profile

    DeyangLiu123/research-profile-skill/skills/research-profile Skill

    1★ repo

    Inject an academic research profile and enforce scope boundaries for networking and systems optimization in distributed training and distributed inference (MLSys × computer networks). Use whenever the conversation involves research or academic work: reading, summarizing, or analyzing papers; literature search and recommendations; relevance judgments; surveys, related work, reviews, or rebuttals; research ideation and topic selection; venue selection; and academic self-introductions. Applies to Chinese requests such as 论文、文献、综述、相关工作、选题、研究方向、投稿、审稿、学术讨论. Keep work anchored to AI workloads on distributed infrastructure; prevent drift upward into pure model algorithms or accuracy research and downward into physical-layer devices, modulation, or coding.

  • Hlvibes

    Cashmeran/hlvibes-skills/hlvibes Skill

    no license1★ repo

    Use when user describes a product idea, a problem they want to solve, a wish-style programming request, or says "I want to build...", "我想做...", "帮我做个...". Main entry point for the vibe coding skill system. Routes user intent to the appropriate vibe-* sub-skill. Trigger phrases: /vibes, "vibe coding", "许愿式编程", "build me".

  • Suno fanqie music

    ismilewolf-eng/suno-fanqie-music/skills/suno-fanqie-music Skill

    1★ repo

    Create, diagnose, humanize, and iterate original Chinese songs for Suno with a Fanqie Music and short-video audience focus. Use for 中文歌词、番茄音乐、Suno 三栏成品、苦情歌、草原歌、草原民谣、亲情歌、打工人现实歌、女声伤感、男声烟嗓、DJ 情绪版、Hook 优化、歌词去 AI 味、Style/Exclude 提示词、选题策划、歌词诊断、多版本 A/B、投稿前检查,或可复用创作 Prompt。 Do not use historical contest details as current rules without verification, and do not directly imitate a real singer or existing song.

  • Add skill

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

    1★ repo

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

    The same file is in 11 other repositories

  • Grill

    Black-coffe/grill/plugins/grill/skills/grill Skill

    1★ repo

    Relentless structured interview to stress-test any plan, idea, decision, investment, or text before acting on it. Use when the user wants to brainstorm, plan, validate or pressure-test something, asks to be interviewed/questioned about their thinking, or uses trigger words — EN: grill, roast my plan/idea, interrogate me, stress-test, brainstorm, planning session, validate this idea, fact-check / prove this claim; RU: гриль, прожарка, прожарь (меня/идею/план), брейншторм, допрос, допроси меня, расспроси, планирование, провентилируй, проверь идею, докажи; UK: гриль, прожарка, прожар, мозковий штурм, допит, допитай мене, розпитай, планування, перевір ідею, доведи. Also use proactively when the user presents a raw plan/idea and asks 'what do you think' before major commitments. Works with or without supporting documents, in any Claude surface (Code, web, desktop).

  • Agent config reference

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

    1★ repo

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

  • Bootstrap sdd tdd

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

    1★ repo

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

  • Cleanmymac x

    evanlong-me/skills/cleanmymac-x Skill

    no license1★ repo

    A CLI-based macOS system cleanup, optimization, security, and privacy tool — the command-line equivalent of CleanMyMac X. Scan-first, clean-confirmed workflow. Includes the cmx convenience script.

  • Humanizer cs

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

    1★ repo

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

  • Adopt existing project

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

    1★ repo

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

  • A stock value check

    jkgeekJack/a-stock-value-check/skills/a-stock-value-check Skill

    1★ repo

    每天检查沪深300「股债性价比」排名,按固定纪律返回"买 / 卖 / 不动"信号。数据来自 rich.jkgeekjk.xyz。 触发方式:/a-stock-value-check、「查一下性价比」「今天 A 股该买还是该卖」「A 股贵不贵」「帮我看看沪深300」「今天该加仓还是减仓」 Daily CSI 300 cost-performance (equity-bond value) check that returns a buy/sell/hold signal by a fixed discipline. Data from rich.jkgeekjk.xyz. Trigger: /a-stock-value-check, "check A-share valuation", "should I buy or sell CSI300 today", "is A-share expensive"

  • Remember design system

    sarveshsea/remember-design-system Skill

    1★

    Use when an agent is about to build or refactor interface code and needs a compact, repository-specific brief covering existing tokens, components, routes, conventions, and verification commands.

  • Cognitive quadrant general

    SpartansPotato/cognitive-quadrant-skills/skills/cognitive-quadrant-general Skill

    1★ repo

    Use this cognitive reflection workflow to clarify complex issues, inspect assumptions and blind spots, compare decisions, iterate plans or ideas, expand knowledge boundaries, and create verifiable next actions. Trigger on requests such as “help me understand this better,” “what am I missing,” “analyze this choice,” “expand my perspective,” “iterate this idea,” “帮我看清这个问题”, “检查认知盲区”, “分析一个选择”, or “拓宽知识边界”. Do not use for simple translation, formatting, or a single stable fact.

  • Analyze reviews

    Feedspace/Feedspace-Cookbook/plugins/feedspace-reviews/skills/analyze-reviews Skill

    1★ repo

    Analyze a batch of customer reviews - you choose the lens: an overview, what customers love, their complaints, their requests, or a data-quality check. Reviews can come from a Feedspace account (via the Feedspace MCP), a CSV, or pasted text, so anyone can use it. Trigger when someone asks to analyze, summarize, or make sense of reviews, testimonials, or feedback.

  • Add clickalong identifiers

    clickalong/clickalong-agent-skills/skills/add-clickalong-identifiers Skill

    1★ repo

    Add, audit, and verify production-stable data-testid contracts for Clickalong guided-tour targets. Use when instrumenting a web app for Clickalong tours, replacing fragile CSS/nth-of-type/generated-ID selectors, fixing account-specific Shopify GID or record selectors, hardening a walkthrough across tenants and redesigns, or reviewing tour targets in React, Vue, Svelte, Angular, Astro, or plain HTML.

  • Purrfectionist audit

    Blackajiro/Purrfectionist/skills/purrfectionist-audit Skill

    1★ repo

    Audit a web or app interface without modifying files. Use when the user asks for a report-only UI review, pre-release visual QA, accessibility findings, responsive or interaction inspection, vibe-code diagnosis, or explicitly invokes $purrfectionist-audit. Return prioritized, evidence-backed findings.

  • Experimental reasoning

    ElliotGluck/groundwork/skills/experimental-reasoning Skill

    1★ repo

    EXPERIMENTAL, intentionally aggressive explicit-reasoning profile for hard analytical work — deep debugging, thorny architecture decisions, root-cause investigation, and complex problem-solving. Use it when you want the model to narrate a visible hypothesis-test-revise loop (stating beliefs and confidence, then killing its own wrong beliefs out loud), push hard on autonomy (chaining investigative steps and finding its own route to evidence instead of stopping to ask), and bias toward structural root-cause fixes over local patches. This is an experiment with unknown payoff — effects vary by task and it trades tokens/latency/verbosity for depth. It is inspired by reasoning behaviors people have praised in high-end models; it is not a reconstruction of any specific model's internal reasoning.

  • Model advisor

    gagooganyan/model-advisor Skill

    1★

    When the user describes a development task, project, or ТЗ and wants a recommendation on which AI model(s) to use for maximum quality at minimum cost. Also use when the user mentions "какую модель", "что использовать", "посчитай стоимость", "дешевле", "бесплатно", or asks to choose/compare models for a specific task.

  • Agent llm

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

    1★ repo

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

  • Handdrawn wisdom video

    huxlife/handdrawn-wisdom-video/skills/handdrawn-wisdom-video Skill

    1★ repo

    Create vertical English hand-drawn wisdom videos from public-domain fables, Chinese idioms, historical anecdotes, and the Thirty-Six Stratagems. Use when Codex needs original English adaptation, scene-synchronized English TTS, a persistent top headline, timed bottom captions, gray-sketch-to-color drawing animation, a one-minute TikTok/YouTube Shorts MP4, cover, title, description, and tags.