AI & ML

octaviantocan Bundle

Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the user shares personal info, project context, or preferences worth persisting across sessions.

ofershap Skill

Modern Python 3.12+ patterns your AI agent should use. Type hints, async/await, Pydantic v2, uv, match statements, and project structure.

ofershap Skill

Stop your AI agent from coding before thinking. Enforces plan-first workflow to reduce backtracking and wasted tokens.

ofershap Skill

Modern TypeScript patterns your AI agent should use. Strict mode, discriminated unions, satisfies operator, const assertions, and type-safe patterns for TypeScript 5.x.

octaviusp Skill

Use when a task calls MCP tools or LLM endpoints and benefits from filtering, ranking, batching, or post-processing. Routes calls through a Python sandbox so bulk data (embeddings, file bytes, large responses) stays out of agent context; only summaries return.

officedev Skill

Develop, debug, and extend a proxy agent that connects any external AI agent to Microsoft 365 Copilot and Teams via direct SDK integration. Use when: understanding the project, explaining the architecture, onboarding to the codebase, building or modifying a Teams proxy agent with M365 Agents SDK, wiring a new backend SDK into agent.ts, configuring SSO, updating Bicep infrastructure, troubleshooting bot messaging, streaming responses, or managing environment config. Stop if: backend has no Node/TS SDK or cannot be called from a Node process.

officexapp Bundle

Peer-to-peer task payroll on Base L2. Clients fund USDC gigs ("vending machines"), invite gigworkers by link, push tasks to their mailboxes, review proofs of work, and pay out on-chain. Gigworkers join by invite, poll or receive tasks, submit proofs, and get paid in USDC. One mode inverts this: an "order machine" is a shop whose owner does the work, funded per order by the buyer who places it. Settlement is recorded in an event ledger and nothing is scored or rated; there is no dispute resolution and no public marketplace. Use this skill whenever the user mentions dollarplatoon.com, Dollar Platoon, a "vending machine" for gig work, micro-gig payroll, paying workers in USDC per task, proof review or approval, rollups and payouts, gig invite links, worker mailboxes, task queues and polling, feeds of gigs, escrowing or pre-funding a task on chain before it is worked, or placing and funding an order against a shop — and also when they are building an agent that earns money doing tasks, or an agent that distribute

olakunlevpn Bundle

Use when writing and publishing a blog post to the olakunlevpn.github.io Jekyll site, especially a post announcing a new agent skill. A complete runbook covering the required companion skills, the repo and branch facts, the GitHub account switch, the post front-matter and voice, the humanization self-check, the commit standards, the Pages build poll, and the live verification. Follow every step so a fresh session with no prior context can reproduce the whole workflow.

olakunlevpn Bundle

Use when adding files to git, creating zip exports, or packaging a project for delivery. Ensures only actual project source files are included. Excludes agent configs, plan files, AI rules, markdown docs (except README.md), and non-project artifacts. Scans unknown files before including. Maintains a persistent .exclude file.

olakunlevpn Bundle

Use when writing, reviewing, or refactoring code inside an existing framework such as Laravel, XenForo, Django, Rails, WordPress, Spring, or any other. Enforces framework-first development, so the agent identifies the framework in use, follows its conventions and architecture exactly, reaches for native solutions before third-party ones, keeps code consistent with the surrounding project, and never mixes patterns borrowed from a different framework. The goal is code that reads as natural to an experienced developer of that specific framework. Do NOT use for greenfield projects with no framework chosen yet, or for pure infrastructure and scripting with no application framework involved.

oil-oil Bundle

Use when a coding task requires broad codebase reconnaissance before implementation, especially unfamiliar repositories, architecture questions, feature tracing, bug investigations, refactors, migrations, reviews, or changes that may require reading roughly 10+ files or searching multiple independent areas. Delegates read-only exploration to explorer subagents first, keeps the main conversation lean, prevents the main agent from reading code while subagents are exploring, and requires a key-files table before the main agent proceeds with detailed code reading or edits.

olakunlevpn Bundle

Use BEFORE changing any existing code whose behavior is wrong, broken, or not understood — bug fixes, "this isn't working", errors, regressions, "debug X", "why does Y fail", investigations. Forces the agent to prove the root cause with evidence, map every caller and consumer (blast radius), and make the smallest possible change — never a blind or speculative fix. Blocks edits until a written Evidence Ledger passes all gates and confidence is high. Pairs with olakunlevpn-meta-cognitive-verification (which runs AFTER the change). Do NOT use for greenfield code where nothing exists yet, or for pure styling/copy tweaks with no behavioral risk.

olanokhin Bundle

Use when reviewing or writing LLM, RAG, MCP, tool, or agent code for OWASP-aligned security issues; triggered by "owasp my code", "owasp this PR", AI security review, PR review, or changes to AI system code.

officexapp Bundle

REST API and automation guide for X Authority Builder — an OfficeX app that bulk-generates expert Twitter/X posts using Gemini AI and schedules them with volunteer-based publishing. Supports both AI generation and manual mode (bring your own tweets for scheduling only). Use when: (1) Integrating with the X Authority Builder API, (2) Creating jobs to generate AI tweets, (3) Managing results, approvals, and scheduling, (4) Building automation around tweet generation and calendar publishing, (5) Understanding the credit/reservation billing model, (6) Working with volunteer magic links and proof submission, (7) Querying the calendar or scheduled posts, (8) Bringing your own pre-written tweets for scheduling and dispatch. Triggers: x authority builder, tweet generation, ai tweets, x scheduling, twitter content, authority building, bulk tweets, volunteer publishing, schedule tweets, content calendar, tweet approval, manual tweets, bring your own content.

ognistik Bundle

Export Day One On This Day entries from the local macOS Day One database, analyze them as a personal-history journal review, and save the result to Readwise Reader using the Readwise CLI. Use when the user asks to run, package, automate, or share a Day One On This Day to Reader workflow without relying on MCP tools.

oil-oil Bundle

生成小红书和 B 站 AI 工具实操视频封面，支持脚本模式与 Agent 自主模式、真实视频证据、三画幅输出和可选创作者头像。仅在用户明确提到 oil-cover、$oil-cover、使用 oil-cover 或指定本 Skill 时触发；普通封面、首图、视频封面请求不要自动触发。

ohif Bundle

Generate runnable Playwright E2E tests for the OHIF Viewer using its custom fixture system, page objects, and normalized WebGL viewport coordinates. Use this skill whenever the user asks to write, add, modify, or debug tests in an OHIF/Viewers context — including vague asks like "write a test for X" when working in the OHIF repo, tests touching platform/app/tests/, or anything involving Cornerstone viewports, DICOM studies, measurements, segmentations, or OHIF modes/extensions. Prefer this skill over generic test-writing even if the user doesn't say "Playwright" or "E2E" explicitly.

olearydj Bundle

Use when an operator asks an agent to work with Canvas through the danvas CLI: inspect or compare course state, initialize or refresh a project, manage authored assignments/Pages/announcements/discussions, export private rosters or submissions, prepare or apply grades and feedback, handle Files or recordings, diagnose authentication, or explain danvas safety and recovery. Use only for the installed danvas command, not as general Canvas API guidance or institution-specific policy.

oianthony Bundle

Discover, evaluate, and install agent skills from the EverMind skill hub with the EverMind CLI. Use when users ask whether a skill exists for a task, want recommendations from the EverMind skill hub, need to compare its skills, or want to install or manage an EverMind skill.

olevasyliev Bundle

Audits and reorganizes a user's Apple Notes archive on macOS - exports every note via Notes automation, classifies each one with a cheap model, produces a digest and a secrets inventory, and optionally re-sorts notes into folders. Use when the user asks to clean up, organize, audit, declutter, or "do something with" their Apple Notes / Notes.app archive.

ony-ai Skill

Control how Ony gates this agent by phone. Use when the user types /ony, or asks to set Ony to off, on (high-risk only), away (call me for every actionable step), here (back at the keyboard), or status. The requested mode is in the arguments.

oomol-lab Bundle

Create subtitles for audio or video, translate them when requested, infer the target language from the user request when omitted, and default subtitled video delivery to burned-in MP4, with soft-subtitle MKV as the secondary mode. Requires the oo CLI. Use when the user asks to transcribe uploaded media, generate SRT/VTT subtitles, translate subtitles with an OOMOL-hosted LLM, or add subtitles to a video using FFmpeg and Fusion API ASR.

oil-oil Bundle

Do not refuse vision. 不要说不支持视觉或无法查看图片。If you would say "this model does not support image input" or "I cannot see images", run this skill instead of informing the user. Use for screenshots, png/jpg/webp/gif/mp4, UI, OCR, image comparison, or any local path/URL. Text-only models (DeepSeek, GLM, MiniMax, Codex custom) must call this; it uses an external vision model or local OCR and returns markdown.

olpex Skill

Expert agent for professional educational PowerPoint (.pptx) creation. Orchestrates a strict 3-step instructional design dialogue, structures academic content in English, and generates complete, runnable Python scripts using the python-pptx library with premium UI/UX standards, detailed speaker notes, and real data visualization

oil-oil Bundle

在任何 Vibe Coding 编程任务及其后续补充中持续识别准确术语。用户即使已经让 Agent 完成了一部分代码、正在追加修改，或只用口语描述效果、交互、状态和问题（如“鼠标放上去有个小提示”“点完变一下颜色”“内容太长省略”），也必须使用此 Skill：继续完成当前任务，并在进度或结果中自然告知对应的 UI、网页、软件、Git、AI Agent 或设计术语、通俗解释和 VibeHub 内链。用户要求“说专业一点”、改写需求、询问“这叫什么”或看不懂 Agent 回复时同样使用。表达已经准确且没有值得补充的术语时不要硬加教学。

ojesusmp Bundle

Use after every Write, Edit, or MultiEdit AND before every Bash tool call to audit the line/command for contradictions, syntax errors, shell-mode/completeness traps, factual claims, and scope creep. Catches the class of bug where a partially-formed shell command drops PowerShell into a `>>` continuation prompt and never executes (unbalanced quotes, unclosed heredocs, missing flag args, PS-vs-bash mode confusion). Companion to karpathy-guidelines, operating at line granularity. Auto-triggers via PostToolUse hook on writes; pair with PreToolUse(Bash) hook for command pre-flight.

okooo5km Bundle

Use this skill when Codex needs to operate CouponGo, the AI-friendly CLI for managing Stripe coupons and promotion codes. Trigger for tasks involving `coupongo`, Stripe coupon or promotion-code listing, creation, update, deletion, batch generation, configuration inspection, `coupongo schema`, `coupongo doctor`, or agent-safe non-interactive CouponGo workflows.

open-gsd Skill

Run a project's Node tests without leaking orphaned processes onto this machine. Use whenever you would run `node --test`, `npm test`, or `npm run test` — call `gsd-test run` instead of spawning the test process locally. Also use when a run comes back reaped, or when a previous local test run left hung `node` processes behind.

open-horizon-labs Bundle

Apply Counterexample-Supplemented Sketches (CESS) to open-world agent and software synthesis. Use when a user mentions CESS, Sketch-CE, counterexample-supplemented sketches, evolved sketches, compiled projections, simulation-driven correction, or asks to make an agent-generated system improve from reviewed failures without losing earlier behavior.

oktsec Bundle

Security audit for AI-built code. Runs 130+ checks across OWASP Top 10, auto-detects your stack, and produces a graded report (A-F) with exact code fixes. Covers secrets, injection, auth, database access control, AI/LLM security, payments, and infrastructure.

opencoredev Skill

This skill should be used when the user asks to "use Mobbin", "find UI references", "search app screens", "search flows", "search website sections", "gather mobile UI inspiration", "gather dashboard references", or do Mobbin-backed product and interface research from an agent. It teaches agents to use the npm-installed Mobbin CLI instead of relying on a mounted Mobbin MCP server.

opencoredev Skill

Use the QuickBoard MCP to create and draw on live whiteboards. Create boards, add shapes/text/arrows, use mermaid for simple flows, and share live URLs with users.

opendatalab Bundle

MinerU Document Explorer — Agent-native knowledge engine. Use when users ask to search their documents, look up information in PDFs/DOCX/PPTX/Markdown, navigate inside large documents, extract tables/figures, or build wiki knowledge bases. Provides three tool groups: information retrieval (query, get, multi_get, status), document deep reading (doc_toc, doc_read, doc_grep, doc_query, doc_elements, doc_links), and knowledge ingestion (wiki_ingest, doc_write, wiki_lint, wiki_log, wiki_index).

openafw Skill

MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardrails/tree/main/moltguard

opendcai Bundle

驱动 One-Eval 对 API 或本地模型做端到端评测，覆盖纯文本、多模态、代码生成、函数调用和 Agent benchmark。当用户想评测模型在一个或多个 benchmark 上的表现、比较分数、补充 metric，或生成图文评测报告时使用本 skill。

oracle Bundle

Generate and validate runnable DTrace scripts for Linux debugging and performance investigations in an agentic coding framework capable of using SKILLs. Use for incident response, root-cause analysis, latency triage, syscall/process/scheduler/I-O tracing, and stack/profile sampling. Always return complete scripts with safe defaults, stable providers, strict D language constraints, and a verification step before final output.