agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Skatteetaten shared

    magnusrodseth/skatteetaten-cli/skills/skatteetaten-shared Skill

    0★ repo

    Runtime contract for the `skt` CLI (unofficial, read-only Skatteetaten / Min skatt). Covers install, BankID login, the short-lived session model, secret-storage backends, output formats, global flags, the command map, and reconciling tax data against sb1 bank data. Use this before any other skatteetaten skill, or whenever a user asks to read their Norwegian skattekort, skattemelding, or skatteoppgjør via skt.

  • J lens observability

    Gonzih/j-lens-observability-skill/j-lens-observability Skill

    0★ repo

    J-Lens and model reasoning observability for AI harnesses. Use when asked about Anthropic J-Lens/J-space/Jacobian lens research, hidden model thinking, prompt/response thought traces, chain-of-thought observability, reasoning audits, OpenClaw/Claude/Codex harness instrumentation, local session logs, or activation-level analysis on open-weight models.

  • Agent retrospective

    marcozhou26/agent-retrospective/agent-retrospective Skill

    0★ repo

    Diagnose and improve a Codex, Agent, Skill, or workflow after failure, repeated correction, false completion, local symptom fixes, rule stacking, or before promoting any learning into AGENTS.md, SKILL.md, scripts, dependencies, memory, or eval gates. Use when the user asks to review why a task went wrong, why a skill/tool/process still feels broken after one successful run, or how to improve the whole working system instead of adding another isolated rule.

  • Agent experience capture

    sterraMind/agent-experience-capture Skill

    0★

    Captures session knowledge into codemem entries, SOP documents, and handoff records. Use when a session completes with lessons worth preserving across sessions — especially bugs found, API discoveries, design decisions, or patterns worth codifying. Also creates new agent skills when a captured experience proves to be a repeatable, cross-session process (Step 7). Don't use for trivial one-offs, routine operations following existing SOPs, temporary context expiring with the session, or on-the-fly skill generation without real usage history.

  • Codebase analysis

    tony-adamson/groundwork-bench/vendor/skills/codebase-analysis Skill

    no license0★ repo

    Creates CURRENT_STATE.md: an evidence-backed description of the current state of the repository. Use only when the user explicitly asks to run codebase-analysis. Does not design a solution, write code, or produce an implementation plan.

    The same file is in 1 other repository

  • Governed engineering runtime

    Abeer-ahmad-123/governed-engineering-runtime/skills/governed-engineering-runtime Skill

    0★ repo

    Operate a governed multi-agent software engineering runtime through a bootstrapped local ai CLI and the authenticated Codex CLI. Use when a repository change should pass through specification, architecture, specialist delegation, human approvals, implementation, independent review, security review, testing, persistent memory, and Git checkpoints rather than being edited immediately.

  • Gatedata market research

    gate/gate-data-ai-agent/skills/gatedata-market-research Skill

    0★ repo

    GateData market data via MCP: spot/perp prices, K-line, order book, CEX depth, derivatives, liquidation heatmap. Triggers on 'BTC price', 'ETH K-line', 'order book', 'funding rate', 'open interest', 'liquidation', 'how much is', '现价', 'K线', '盘口', '资金费率'.

  • Chart revive

    yoursmilestar-ctrl/chart-revive/skills/chart-revive Skill

    0★ repo

    Turn chart screenshots, chart images, and chart regions from PDFs or slides into native editable PowerPoint charts with embedded data, CSV export, confidence labels, and an offline audit report. Use when a user wants to recreate, recover, reverse-engineer, restyle, translate, or update a static bar, column, stacked-column, line, pie, or doughnut chart instead of keeping it as a flat image.

  • Agent browser webauthn

    kalepail/skills/skills/agent-browser-webauthn Skill

    0★ repo

    Use agent-browser with Chrome DevTools Protocol virtual WebAuthn authenticators to test passkey, WebAuthn, Stellar smart account, wallet creation, wallet restore, and browser signing flows. Trigger when a task mentions passkeys, WebAuthn, virtual authenticators, Stellar Smart Account Kit browser tests, or agent-browser passkey automation. Do not use for browser flows without a passkey or WebAuthn ceremony—password logins and extension-wallet connects route to agent-browser alone.

  • Memento

    Lego1997/memento/skills/memento Skill

    0★ repo

    $memento, memento, memory film, "recreate this memory", "turn these photos into a film", personal photos to Dreamina/Seedance video prompts. Use to turn a user's own or consented personal-memory photos into a resumable per-memory project folder with source references, visual inventory, adaptive interview, optional generated sheets or micro-edits, and paste-ready Dreamina prompts. Do not use for generic video-prompt writing, fiction pipelines, impersonation/deepfake work, or arbitrary image editing outside a memory project.

  • Human tone

    seacen/human-tone/skills/human-tone Skill

    0★ repo

    Strip AI flavor from writing — evaluative inflation, mechanical antithesis ("not just X, but Y"), rule-of-three padding, hollow hedging, narrator scaffolding, corporate jargon, translationese — so it reads like a person wrote it, without touching terms, quotes, code, numbers, or an author's deliberate voice. Multilingual; Chinese and English are first-class. Use it proactively as the finishing pass on any task producing prose people will read or publish: articles, blog posts, marketing and social copy (Xiaohongshu, WeChat posts), slide decks and PPT, emails, reports, documentation, announcements, product and landing copy, newsletters, scripts. Run it before delivering generated writing even when the user never mentions AI flavor; cleaning up after they complain is too late. Also use when asked to humanize, de-slop, remove the AI tone, make text sound human, or fix writing that "reads like ChatGPT" or "is too robotic". Skip only pure code, data, and mechanical transforms with no human-facing prose.

  • Jsonspecs rule author

    jsonspecs/jsonspecs-rule-author/skills/jsonspecs-rule-author Skill

    0★ repo

    Author, review, refactor, migrate, package, and validate jsonspecs rules projects for @jsonspecs/rules v4, jsonspecs-cli v4, and jsonspecs/spec 1.0.0-rc.7. Use for formatVersion 2 snapshots, manifest.json authoring metadata, exported pipelines, rule/condition/pipeline/dictionary artifacts, RC.7 wildcard guards, samples, custom {schema,evaluate} operators, sourceHash, Sandbox metadata, package boundaries, and migration from older jsonspecs releases.

  • Nutanix aiops

    AIops-tools/Nutanix-AIops/skills/nutanix-aiops Skill

    0★ repo

    Use this skill whenever the user needs to operate a Nutanix estate through Prism Central (v4 REST API) — an estate/cluster health overview, cluster & host inventory and utilization, VM lifecycle across AHV and ESXi (list/get/power/create/update/clone/delete/migrate), storage containers, subnets/network, images & categories, data protection / DR (snapshots, recovery points, protection domains, VM protect, failover), alerts & events with alert RCA (analyze_alert), LCM firmware/software upgrades, capacity runway forecasting, and read-only diagnostics/RCA over the whole estate (cluster_health_rca, alert_triage_rca). Always use this skill for "Nutanix", "Prism Central", "AHV", "cluster health", "list VMs", "power on/off a VM", "clone/migrate a VM", "delete a VM", "snapshot", "recovery point", "protection domain", "failover", "why did this alert fire" / "root cause this alert", "LCM upgrade / firmware", "days until storage is full" / "capacity runway", "what's wrong with my cluster" / "diagnose the estate", "triage my alerts", when the context is a Nutanix cluster or Prism Central. Do NOT use when the target is a non-Nutanix platform — those belong to their own AIops-tools sibling; this skill is Prism Central v4 only. Governed Nutanix Prism Central operations with a built-in governance harness (audit, token budget, undo, descriptive risk-tier labels).

  • Grok implementer

    nguyentan2808/agent-skills/grok-implementer Skill

    0★ repo

    Route hands-on implementation to Grok headless CLI — ONLY when the user explicitly asks for it (e.g. names Grok, or says "use grok-implementer"). Never trigger automatically. When invoked, the orchestrator AI (Claude Code, Cursor, Codex-as-orchestrator, etc.) freezes a work-order spec, runs Grok to implement, then reviews the diff and re-runs proof. Skip when already inside a Grok session — never self-delegate.

  • Onchain equity route advisor

    PKCrox/onchain-equity-route-advisor Skill

    no license0★

    Compare tokenized stock and onchain equity holding routes across CEX spot, perps, and onchain RWA venues. Use when a user asks where to buy or hold xStocks or tokenized equities, how much 1000/5000/10000 USD execution costs, whether Bybit/Mantle/perps are suitable for long-term holding, or how to produce a Mantle Research Challenge style route-quality report. Defaults to global discovery scans; SPCXx is a focused Mantle case study, not the only supported asset.

  • Robinhood chain

    jp4g/robinhood-chain-skill/skills/robinhood-chain Skill

    0★ repo

    Robinhood Chain integration guide for agents. Use for network config, RPCs, ChainList, Stock Tokens, bridges, oracles, AA, indexing, wallets, and connected services.

  • Bazi calendar research

    ProfesseurHaipeng/bazi-calendar-research-skill/skills/bazi-calendar-research Skill

    0★ repo

    Research BaZi and Chinese calendrical notation as convention-dependent time labeling, with transparent sexagenary-cycle calculations, solar-term boundaries, source provenance, and uncertainty. Use when Codex is asked about 八字、四柱、天干地支、节气、真太阳时 or Chinese calendar algorithms.

  • ProcGen Toolkit

    axtontc/ProcGen-Toolkit Skill

    0★

    Actionable workflow for generating deterministic procedural assets (sprites, textures, layouts) using the high-performance ProcGen-Toolkit SDK.

  • Product brief builder

    linxumoney/product-brief-builder/skills/product-brief-builder Skill

    0★ repo

    把模糊产品想法、功能需求、会议记录或现有 PRD 整理为决策型产品简报,明确用户问题、证据、目标、最小范围、不做项、验收条件、假设、风险和未决问题。适用于写产品简报、功能方案、需求澄清、MVP 范围、PRD 精简或评审准备。

  • Design company soul

    binbingoes/design-company-soul/design-company-soul Skill

    0★ repo

    Design or iterate a company's actionable SOUL: mission and vision, worldview, talent philosophy, values, decision principles, product and business principles, culture implementation mechanisms, and a shared human/agent decision kernel. Use when founders, executives, HR/culture teams, or business leaders ask to define company culture, refresh values, align leadership, create talent principles, turn culture into business decisions, make principles usable by both people and AI agents, test principles against real conflicts, or produce a SOUL v0.1-to-v1.0. Triggers include 公司SOUL、企业文化、使命愿景、人才观、价值观、世界观、决策原则、文化落地、人机决策原则、Agent SOUL、culture operating system, mission vision values, and leadership alignment.

  • Love me love my docs

    silkyland/love-me-love-my-docs Skill

    0★

    Auto-generates a beautiful user manual with REAL screenshots captured by executable scripts: censuses the app's user flows from routes and navigation, builds a Playwright (Python) capture harness for web (the primary focus; mobile via Maestro is an optional path), seeds safe demo data so no real user data appears in images, writes the manual chapter-per-flow with a numbered step per screenshot, and renders it beautifully (MkDocs Material site, Markdown, or PDF). The capture scripts are committed, so the manual regenerates when the UI changes instead of rotting. Use when the user asks to generate a user manual, user guide, documentation with screenshots, onboarding docs, or mentions love-me-love-my-docs or /love-me-love-my-docs.

  • Zuiti huabing

    SilentFleetKK/zuiti-huabing Skill

    0★

    嘴替·画饼包——专治老板/上级用"未来的好处"和"情怀"换你"现在确定的付出"。它先把画饼话术翻译成人话(这句到底想让你干什么、成本谁扛、饼几时兑现),再给你三档可以直接发出去的回复(体面版 / 绵里藏针版 / 掀桌版),最后附长期策略和发送建议。专门覆盖:成长机会、年轻人多拼、明年优先考虑你、先扛下来、要有格局、狼性文化、把公司当家、画大饼不谈钱、共患难、给你更大平台、锻炼锻炼你、这是信任你。只要老板/领导/HR/合伙人用愿景、情怀、栽培、格局来包装"让你多干、白干、先干",或者你被一段"听着很暖但一分钱不提"的话噎住,说"帮我回一下""这饼怎么接""想怼又不好直接怼",都用本 skill。它是嘴替.skill 的画饼专场子仓,比主 skill 更懂饼。

  • Lesstoken

    Zane456/lesstoken Skill

    0★

    Ultra-compressed lesstoken response mode. ALWAYS invoke when user says "lesstoken", "less tokens", "caveman mode", "talk like caveman", "use caveman", "be brief", "极简模式", "简洁", "少废话", "省token", or /lesstoken. Do not use normal verbose style when triggered. Use this skill first.

  • OpenQuery

    dillondrobena/OpenQuery Skill

    0★

    Safely explore and visualize a user's Postgres database. Use when the user asks questions about their data — relationships between entities ("how is user X connected to companies A, B, C?"), aggregates, or investigations. Runs guarded read-only SQL through the openquery CLI and renders answers as interactive entity graphs where every edge carries a SQL receipt. The AI never sees or handles database credentials.

  • Aikc open source release

    AHappyAtlas/ai-knowledge-center/ai-knowledge/skills/aikc-open-source-release Skill

    0★ repo

    Local-first project context, verification gates, and repo-scoped MCP for coding agents.

  • Readme craft

    okht/readme-craft/skills/readme-craft Skill

    0★ repo

    Create, rewrite, localize, audit, and visually refine public GitHub README files for tools, libraries, frameworks, research repositories, templates, and Skills. Use when the user asks to write or redesign a README, align README presentation across repositories, improve badges or navigation, add a complete multilingual set, compact Mermaid diagrams, verify README claims against repository evidence, remove private information, or visually QA GitHub rendering.

  • Cloud incident coach

    linxumoney/cloud-incident-coach/skills/cloud-incident-coach Skill

    0★ repo

    协助防御性云安全事件响应,建立严重度、时间线、证据保全、影响范围、可逆遏制、恢复验证、沟通和复盘计划。适用于云账号异常、凭据泄露、数据访问异常、工作负载入侵、配置误改和事件响应演练;不提供入侵、持久化、规避检测或破坏性指导。

  • Deploy ai research radar

    peipeijiang/ai-research-radar-skill/skills/deploy-ai-research-radar Skill

    0★ repo

    Deploy, configure, verify, or repair a GitHub-hosted AI research radar for any academic field. Use this skill whenever a user wants automated paper discovery, custom research topics, ArXiv/OpenAlex/DBLP ingestion, lawful full-text recovery, evidence-labeled LLM analysis, MinerU parsing, daily or weekly WeCom delivery, Git-backed knowledge, GBrain semantic search, GitHub code matching, citation expansion, one-click paper feedback, or single-paper reanalysis, even when they describe only part of that workflow.

  • Know your unknowns

    NimaChu/know-your-unknowns Skill

    no license0★

    Systematic discovery of unknowns for software, product, design, research, and writing tasks. Use when the user asks in natural language to find what they missed, what they do not know, hidden risks, blindspots, assumptions, edge cases, ambiguity, better questions, implementation-plan risks, prompt improvements, reviewer objections, merge readiness checks, or when a request is underspecified and would benefit from clarification before or during execution. Trigger on phrases like "帮我找出未知", "我漏了什么", "哪里可能出问题", "what am I missing", "find the risks", "spot assumptions", and "tell me what I have not considered".

  • Cohesivity

    cohesivity-org/cohesivity-skill/skills/cohesivity Skill

    0★ repo

    The Cohesivity agent skill: on-the-fly backend infrastructure for AI agents. Install with: npx skills add cohesivity-org/cohesivity-skill

  • Commit message writer

    bilals2008/bilal-skills/skills/commit-message-writer Skill

    0★ repo

    Write short, accurate Git commit messages in English. Use when the user asks to commit, create a PR, or write a commit message. ALWAYS check the actual git diff first. ALWAYS write the commit message in English regardless of what language the user speaks.

  • Excalidraw

    fuller-stack-dev/excalidraw-mcp-skill/excalidraw Skill

    0★ repo

    Excalidraw MCP workflows for creating, editing, presenting, exporting, and persisting diagrams, wireframes, sequence diagrams, architecture maps, state machines, and slide decks. Use when working with the Excalidraw MCP App, Excalidraw+ workspace scenes, MCP installation or repair, live tool discovery, API-key permissions, or inline interactive canvas rendering.

  • Seven steps primer

    strandic/skills/skills/seven-steps-primer Skill

    0★ repo

    Step-gated method for building one medium, structural feature with an agent, without slop — you clear every gate; the agent never self-certifies a step.

  • Dojo

    quangtran88/dojo Skill

    0★

    Generate a personalized, self-mentoring learning repo (a "dojo") for any topic the user wants to master — coding or not. Interviews the learner, deep-researches and curates the best materials, synthesizes a module-based curriculum with a roadmap, then scaffolds a git repo whose AGENTS.md turns any coding agent into a persistent mentor with daily check-ins, teach-back gates, spaced repetition, confidence calibration, and progress tracking. Use when the user asks to build a dojo, learning repo, curriculum, roadmap, or mentor repo for a topic, or commits to mastering a topic long-term ("build me a dojo for X", "teach me X long-term") — not for one-off questions about a topic.

  • Execution envelope

    knowledgeco/airworthiness/skills/execution-envelope Skill

    0★ repo

    Bound autonomous coding work with an explicit, operator-adjustable contract for execution authority, multidimensional fidelity, work granularity, permitted deviation, evidence, escalation, zones, and delegation inheritance. Use when starting a substantial or broad implementation, the user asks an agent to proceed autonomously, delegating to subagents, fidelity differs across paths or workflows, work crosses public API, data migration, security, release, or irreversible-action boundaries, scope is underspecified, or an agent is about to decide what "close enough" means.

  • Arms

    dianbrown/rocky/benchmarks/arms/caveman Skill

    no license0★ repo

    Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

    The same file is in 6 other repositories

  • Goal draft policy

    yshmr/codex-goal-draft-policy/skill/goal-draft-policy Skill

    0★ repo

    Draft or review a human-reviewable Codex /goal completion contract for long-running, multi-turn, iterative, or evidence-driven work before activation. Use for explicit or implicit requests to prepare, critique, or refine a Goal draft. Do not implicitly invoke for combined draft-and-execute requests, ordinary plans or one-off work, /goal explanation questions, or continuation of an active Goal. This skill always stops at the reviewed draft.

  • Skill

    raphaelbleier/userstory-playwright-skill/skill Skill

    0★ repo

    Derive user stories from a website codebase into an Excel sheet, turn them into Playwright E2E tests, run them, and write failures and their root causes back into the sheet. Use when asked to generate user stories, build an E2E test suite from a codebase, run a QA pass over a website, or track bugs against user stories.

  • Monitoring aiops

    AIops-tools/Monitoring-AIops/skills/monitoring-aiops Skill

    0★ repo

    Use this skill whenever the user needs to operate a network / infrastructure monitoring NOC on SolarWinds Orion (SWIS REST + SWQL), Paessler PRTG (web API), or Zabbix 6.x/7.x (JSON-RPC) — a one-shot NOC overview, canned SWQL answers (nodes down, flapping interfaces, muted, high-CPU nodes, full volumes, unmanaged/scheduled), a validated read-only SWQL passthrough, deduped/rolled-up active alerts, SolarWinds node/interface/volume/application health and top-N, PRTG sensors/devices/groups/history/alarms, Zabbix problems/hosts/host-groups/triggers/events/item-history/maintenances, and guarded writes (acknowledge, mute/unmute, schedule maintenance, unmanage/remanage, remove node, pause/resume sensor, create/delete Zabbix maintenance window). Always use this skill for "SolarWinds", "Orion", "SWQL", "THWACK question", "PRTG", "Paessler", "Zabbix", "Zabbix problem", "Zabbix trigger", "Zabbix maintenance", "NOC overview", "which nodes are down", "flapping interfaces", "interface flap storm", "alert storm", "acknowledge this alert", "worst CPU nodes", "top-N by latency/packet loss", "which volumes are full", "muted alerts report", "unmanaged nodes", "schedule a maintenance window", "unmanage / remanage a node", "pause a PRTG sensor" when the context is monitoring. Do NOT use when the target is something other than a SolarWinds/PRTG/Zabbix monitoring platform (a hypervisor, storage appliance, backup product, Kubernetes cluster, network device config, or OT/industrial equipment) — route those to the appropriate other AIops-tools skill. Governed monitoring operations with a built-in governance harness (audit, policy, token budget, undo, risk-tiers). PRTG's free Freeware edition and an open-source Zabbix appliance are the easiest live checks; SolarWinds is trial-only past 30 days.

  • Idea honing

    aneviaro/pipack/agent/skills/idea-honing Skill

    no license0★ repo

    Relentlessly interview the user to sharpen a vague idea into an actionable implementation spec, then save that spec to the repository. Use when the user wants to refine an idea, stress-test a concept, build a spec, write a PRD, or says "hone this idea", "grill me", "turn this into a spec", or similar.

  • Headless cli

    oldantique/headless-cli-playbook/skills/headless-cli Skill

    0★ repo

    Call another local AI CLI headlessly from a Bash call — codex, opencode, agy, or kimi — to delegate a subtask, get a second opinion from a different model, fan out work in parallel, or run a one-shot prompt and capture the result. Use when the user asks to use/ask codex, opencode, agy, kimi, gemini, gpt, deepseek, or k3; wants another model's take or a cross-model check; when delegating coding/analysis to a non-Claude model is useful; or when the user wants an image generated (logo, banner, cover, illustration) — codex can do that headlessly. Contains the exact verified flags plus the gotchas (stdin/sandbox/parallelism) that otherwise cause hung or empty calls.

  • Asbuilt

    tommylower/asbuilt Skill

    0★

    Asbuilt design-system extraction and conformance. Use when the user asks to derive a design system from existing code, extract tokens/components/states, conform a finished UI to a derived package, or retrofit studio law onto a project. Never for greenfield design systems.

    The same file is in 1 other repository

  • Agents sdk

    Pdbjork/hermosskills-site/skills/agents-sdk Skill

    no license0★ repo

    Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

    The same file is in 1 other repository

  • Twin my site

    silkyland/twin-my-site Skill

    0★

    Plans a native mobile companion app for an existing website — a twin, not a wrapper: same brand DNA, data, and features; native body. Censuses the web product's features and classifies each for the app, audits API readiness and designs the mobile API contract (token auth, pagination, media, push pipeline), extracts the web's design language into mobile design tokens translated to native idioms, commits to an app stack, prepares the store listing (app name, description, category, privacy policy and account-deletion links — recommending generators when missing — and a scaffolded store/ publish kit), and writes a phased blueprint starting with a walking skeleton. Use when the user has a website and wants a mobile app version or companion app, needs an API designed for an app, wants the app to match the web's design and tone, asks to prepare an App Store or Play Store listing, or mentions twin-my-site or /twin-my-site.

  • Duty loop designer

    yeyitech/duty-loops/.agents/skills/duty-loop-designer Skill

    0★ repo

    Design a lightweight scene-specific Duty Loop from a user's goal. Use when Codex should help create or refine BLUEPRINT.md, context sources, notification policy, human gates, and minimal scripts for a recurring, scheduled, event-triggered, or autonomous AI worker that stays on duty instead of answering once.

  • Kickoff

    lusipad/zhizhi/skills/kickoff Skill

    0★ repo

    Kickoff (开工) — run before starting any non-trivial task. Diagnoses the gap between what the user asked for (the map) and what the codebase or domain actually requires (the territory), then applies only the techniques needed — blindspot briefing for unfamiliar territory, premise challenges that falsify what's treated as fact, throwaway prototypes and feasibility spikes for "I'll know it when I see it", one-question-at-a-time interviews for ambiguities, reference extraction, and an unknowns-first plan. Use when the user says "kickoff", "开工", "帮我开始", "找找我的盲区", "help me start", "find my unknowns", "what am I missing", "I don't know where to start", or when a previous attempt — theirs or an AI's — came back wrong and they don't know why.

  • Template

    adrianfoehl/kira-agent-system/skills/_template Skill

    0★ repo

    A file-based multi-agent system for Claude Code: orchestrator, specialist agents, skills and playbooks as versioned markdown, capped per-agent memory, and a feedback loop. In daily use since March 2026.

  • Codebase 5yr forecast skill

    eligapris/codebase-5yr-forecast-skill Skill

    no license0★

    Performs a data-driven 5-year survival and moat forecast for any codebase, app, or product idea. Analyzes code, identifies the project's defensible moat, quantifies AI-disruption exposure, projects year-by-year decay curves plus bull/base/bear scenarios, and produces a pivot roadmap if the verdict is negative. Use this skill whenever the user asks to "forecast", "project", "predict the future of", "assess longevity of", "evaluate durability of", "is my project still relevant", "should I pivot", "what's the moat of", or otherwise wants a strategic, evidence-backed, multi-year outlook on a codebase, app, or technical product. Also trigger when the user mentions "5-year projection", "moat analysis", "AI disruption risk", or "tech stack longevity" — even if they don't explicitly use the word "forecast". The skill is deliberately brutal and quantitative; do not soften its verdicts.

  • Skill

    rahim1845/product-design-partner/skill Skill

    0★ repo

    Senior product design and product thinking partner across the full lifecycle — from "is this worth building at all" through discovery, design, validation, shipping, measurement, and growth. Use whenever the user is exploring, validating, designing, researching, testing, positioning, prioritizing, or measuring any digital product, app, website, feature, AI product, or portfolio case study. Trigger on phrases like "design a product", "validate my idea", "is this worth building", "user research", "usability test", "jobs-to-be-done", "journey map", "persona", "MVP", "product strategy", "positioning", "growth loop", "north star", "retention", "redesign", "heuristic evaluation", "RICE", "OKRs", "WCAG", "AI UX", "case study" — and on implicit cues like "I have an app idea" or "users aren't coming back". Produces quantified artifacts, not generic advice. Not for pure graphic/brand design, frontend code without design thinking, or business advice unconnected to a product.

  • Senior prompt engineer

    Arushmukundan/senior-prompt-engineer/senior-prompt-engineer Skill

    no license0★ repo

    Transforms any vague, generic, or short user request into a comprehensive, senior-level prompt/spec BEFORE doing the work, then executes against that spec. Use this whenever the user asks you to build an app, write or refactor code, create a website or landing page, design UI/UX, make a presentation or slides, write content, do research, or analyze data - and especially any time a request feels underspecified. Also use it when the user says a previous result was wrong, not what they expected, or asks you to "try again" - so the skill can learn from the miss and self-correct.

  • Audio theater

    puntorigen/skills/audio-theater Skill

    no license0★ repo

    Turn a dialogue, a story with dialogue, or a one-line idea into finished multi-character audio - a radio drama, a two-host podcast, or clean lip-sync voice clips - 100% locally with no cloud or API keys. Orchestrates three local sibling skills: voice-clone-narration (one cloned/designed voice per character, a clean clip per line), sound-effects (foley/ambience via Stable Audio Open Small), and bg-music (instrumental score/beds via ACE-Step), then mixes them with ffmpeg using sidechain ducking (music ducks under voices+SFX and swells in the gaps) and optional stereo spatialization (pan + distance + movement). Three modes - theater (dramatized play + SFX + music), podcast (two hosts + music bed), and lipsync (clean per-line clips + a manifest for the talking-head skill). When there is music it delivers the full mix plus music-only and no-music stems, plus a timecoded markdown transcript. Use when the user asks for an audio drama, audioteatro / radioteatro, a dramatized dialogue, a podcast episode from a script or idea, a voiceover for lip-sync, or a local TTS conversation with sound.

  • Skill miner

    Sagart-cactus/skill-miner/skills/skill-miner Skill

    0★ repo

    Mine past coding-agent session history (Claude Code, Codex CLI, opencode, pi, …) to discover and build the reusable skills a person or team should create. Use whenever the user wants to extract skills, conventions, or workflows from their session transcripts — "what skills should we create", "go through my past sessions", "turn my corrections into rules", "build a skill catalog" — or wants to run this across a whole team by collecting sanitized findings from each member's local history. Works for individuals and organizations alike.

  • Loss weighted unknowns

    runsagents/loss-weighted-unknowns Skill

    0★

    Rank delivery unknowns by potential loss. Use when someone asks “what are we missing,” requests a pre-merge unknowns pass, says “rank the unknowns,” or when an agent has finished building and needs to expose consequential assumptions before merge.

  • Pdf2md

    iabakumov/pdf2md Skill

    0★

    Batch-convert whole folders of PDFs — scanned or digital — into Markdown files with a quality-first, fully local Tesseract OCR pipeline. Built for poorly scanned documents (fixes rotation, skew, low contrast, shadows) and for large batches (10k+ files, resumable). Works with any Tesseract-supported language and is particularly strong on German (umlauts, ß). Use this skill whenever the user wants to OCR PDFs, convert PDF documents or archives to Markdown or plain text, extract text from scanned documents at scale, or digitize a folder of paperwork — even if they never say the word "OCR".

  • Voice preserving editor

    linxumoney/voice-preserving-editor/skills/voice-preserving-editor Skill

    0★ repo

    在不改变事实、立场和作者身份的前提下编辑中文或英文文本,先从用户样本建立声音基线,再识别模板感、空泛概括、重复结构、宣传腔和不自然过渡,进行最小必要改写。适用于去 AI 腔、润色、改写得更像本人、保持原意、博客编辑和品牌语气校准;不承诺绕过 AI 检测器。

  • Incident to eval

    hamidettefagh/incident-to-eval Skill

    0★

    Turns a production AI agent incident into a golden eval case, a portable regression test that makes the failure unrepeatable. Use when an agent did something wrong in production or testing, when someone has a postmortem, trace, bug report, or a paragraph describing an agent failure, when someone asks how to stop an agent failure from happening again, or when converting incidents, escalations, or wrong answers into evals, test cases, or a regression suite. Reconstructs the incident, classifies the failure against an agent-specific taxonomy, writes a vendor-neutral eval case, and validates it with a deterministic script.

  • Sync claude context

    TobiasWestholm/sync-claude-context Skill

    0★

    Sync all Claude Code project context at the start of a new session or after significant changes. Use this whenever: starting fresh on a project after a gap, asked to "sync", "catch up", "update project docs", "bring yourself up to speed", or when you suspect CLAUDE.md, skills, or memory might be stale. Proactively suggest it when the user says they've been away, a big feature landed, or the stack changed. Works for any language and project structure. Covers CLAUDE.md accuracy, project skills, memory consolidation, and settings review.

  • Ai guardian

    AIops-tools/AI-Guardian/skills/ai-guardian Skill

    0★ repo

    Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-node vLLM — inventory installed/running models with an allow/deny verdict (shadow-AI detection), inspect VRAM residency, model license/params/capabilities and server version, view the model policy, detect model provenance/digest drift (re-pulled or tampered weights; strong for Ollama/llama.cpp, id-only and honestly weaker for LM Studio/vLLM), scan a prompt for secrets / PII / source-code / jailbreak with a weighted risk band, route a prompt THROUGH a guard that scans + policy-gates + records + runs-if-allowed (guarded_generate / observe_chat), query the observed-usage log, and roll up anomalies (shadow models, digest drift, high-risk + blocked prompts). Always use this skill for "what local models are installed", "find shadow / unsanctioned AI models", "which model is loaded in VRAM", "scan this prompt for secrets/PII before sending", "stop secrets leaking into a local model", "block a prompt with an API key", "detect a jailbreak / prompt injection", "set a model allowlist / denylist", "detect a tampered / re-pulled model", "audit local LLM usage", "guard my llama.cpp / LM Studio / local vLLM endpoint", or "the complement to IGEL AI Armor". Do NOT use for GPU inference CLUSTERS (multi-node / fleet-scale vLLM / Ray serving) — this is for single-endpoint LOCAL LLMs; point cluster/serving work to inference-aiops. Also not for hypervisors, storage, backup, Kubernetes, or network devices. Passive inventory/state auditing plus opt-in route-through content governance, with a bundled governance harness (audit, policy, token budget, undo, risk-tiers). A transparent capture proxy is v0.2 roadmap.

  • Settlement proof

    runsagents/settlement-proof Skill

    0★

    Create a read-only evidence packet that verifies a claimed payment outcome against processor, internal ledger, idempotency/retry, reconciliation, and compensating-action state. Use when asked to "prove payment settled", "verify a payment", "check payment succeeded", "produce settlement proof", investigate a "ledger mismatch", validate a "duplicate webhook", check a reversal or refund, reconcile payment state, or block an agent's payment-done claim until money-stakes systems agree.

  • Quiz me

    runsagents/quiz-me Skill

    0★

    Quiz the human on their own codebase, recent changes by default. Use when the user says "quiz me", asks to be tested on their code, or wants to check they can still answer for agent-written changes.