Showing 6601–6630 of 15645 skills
卖点分镜表:把商品卖点拆成 15–60 秒带货短视频的逐镜分镜表(时间码、画面、台词、字幕、花字、素材来源、运镜),并直接输出可渲染的 storyboard.json。Use when the user wants a storyboard, 分镜, 分镜脚本, shot list, 带货视频脚本, video script from selling points, or needs to plan a product video before generating or editing.
xianyu110/ecommerce-video-skills
爆款拆解复刻:把抖音/TikTok 爆款带货视频(链接、转写或口述结构)拆成 8 维结构与 5-beat 节拍,再映射到你的商品,输出拆解表 + 3 个复刻角度 + 可渲染 storyboard.json。Use when the user says 爆款, 拆解, 复刻, 对标, 仿拍, viral remake, breakdown, swipe file, copy structure, 竞品视频, remake a TikTok/Douyin product video, or wants to replicate a viral ecommerce short's structure with their own product.
xianyu110/ecommerce-video-skills
AI job search command center -- evaluate offers, generate CVs, scan portals, track applications
michaelinghilterra-creator/trajecktory
Extract the exact integer dependency model of an accepted Proximity Prize proof, search for the smallest strict 0.01 score step with replayable arithmetic, and formalize only the deltas that survive an independent exact check.
odinfree/storm-ecdsa-harness
Score an ecdsa.fail ops.bin exactly like the official eval_circuit (same Fiat-Shamir shots, totals, failure counts and score) in minutes, at about 20 bytes per op instead of 56. Uses BitWonka's fasteval. Use when a circuit is too big for eval_circuit on your machine, when you need an official-equivalent score before submitting, or when you need a circuit's failure rate from fresh salted shots.
odinfree/storm-ecdsa-harness
Compare each newly accepted Proximity Prize proof with its accepted predecessor only. Bind the source and the public note, inspect proof-root and module changes, and isolate the lever that transfers, without contaminating clean-room lanes.
odinfree/storm-ecdsa-harness
孙宇晨(Justin Sun / 孙割)的思维框架与行为逻辑。基于6个维度(著作、深度采访、表达DNA、 他者视角、决策记录、时间线)共1500+行调研素材的深度蒸馏, 提炼6个核心心智模型、8条决策启发式、5种割味造句公式和完整的表达DNA。 用途:作为思维顾问,用孙宇晨的视角分析营销策略、注意力经济、危机公关、叙事操控、蹭热点方法论。 割味十足的角色扮演——自大、暴论、碰瓷、数字轰炸、成功学底色。 当用户提到「用孙宇晨的视角」「孙割会怎么做」「孙宇晨模式」「Justin Sun perspective」「割神」时使用。 即使用户只是说「帮我用孙割的角度想想」「如果孙宇晨会怎么操作」「切换到割神」「用割的视角」也应触发。
alchaincyf/sun-yuchen-perspective
Draft a campaign brief using approved brand guidance and campaign notes.
trina-app/trina-ax-cp
Draft an onboarding checklist from permitted policies and office guidance.
trina-app/trina-ax-cp
Prepare a weekly team report from permitted sales and finance notes.
trina-app/trina-ax-cp
Promo video — reads a company intro or other material and makes an 18-second vertical (4:5) promo video with music, using the pictures and logo in the team's brand folder and the brand colors. Use it for "make a promo video about our company", "a promo video from this deck".
trina-app/trina-ax-cp
홍보 영상 — 회사 소개서나 자료를 읽고, 팀 브랜드 폴더의 사진과 로고, 브랜드 색으로 음악이 깔린 18초짜리 세로형(4:5) 홍보 영상을 만들어요. "우리 회사 홍보 영상 만들어 줘", "이 자료로 홍보 영상"처럼 물을 때 써요.
trina-app/trina-ax-cp
Natural writing — rewrites text that reads as AI-generated so it sounds like a person wrote it, or points out the patterns that give it away. For posts, emails, proposals, reports and notices. Every fact, number, name and condition stays exactly as it was.
trina-app/trina-ax-cp
자연스러운 글 — AI가 쓴 티가 나는 한국어 글을 사람이 쓴 것처럼 다듬거나, 장르에 맞는 제목·문구를 새로 써요. 블로그, 유튜브·쇼츠 제목, 인스타그램 캡션, 제안서·보고서, 보도자료·공지에 써요. 숫자, 날짜, 이름, 조건은 하나도 바꾸지 않아요.
trina-app/trina-ax-cp
Maintain Yuzu's Meson build graph, source lists, dependency wiring, and platform conditionals. Use when editing any `meson.build`, adding or removing source files, changing dependencies, updating native or cross files, or adjusting CI build behavior.
DevNullLtd/Yuzu
Use when a person asks to change how Jason itself works rather than to do campaign work - make a role write or behave differently, add a role, add or change a plugin for a service they use, send an operation to another plugin, or grant a plugin what it needs - and to say what an update keeps and what is never touched.
reply-team/jason-ai
Analyze financial data, calculate financial ratios, and generate analysis reports. Use when the user asks about revenue, costs, profits, margins, ROI, financial metrics, or needs financial analysis of a company or project.
huangjia2019/claude-code-engineering
The Atlas engine — turn any goal into a validated PRD and an executable, verified task graph. Brand-name entrypoint; a thin alias for the `go` orchestrator. Use when the user types /prd:atlas, says "I want to build", or asks for a PRD / task-driven build.
anombyte93/prd-taskmaster
Use when the user asks about the CTI Hyperloop framework, the intelligence lifecycle as a high-tempo loop, or how to map intelligence work across strategic / operational / tactical levels with bidirectional feedback. Liberty91's operational doctrine.
Liberty91LTD/cti-skills
Use when challenging a prevailing analytical judgment, the user asks "what is the opposing case?" / "argue the other side" / "play devil's advocate", or wants an assessment stress-tested before release. Takes the team's own lead judgment and builds the strongest case that it is wrong. A contrarian technique. It does not model what an adversary would do next, which is Red Team Analysis. Formerly /red-team-analysis.
Liberty91LTD/cti-skills
Use when a user asks to investigate, check, or characterize a domain or hostname. Chains VirusTotal, URLScan (search existing scans), Shodan (DNS resolve + host), OTX, ransomware.live (victim-status sweep), and optionally Censys. Returns reputation, resolution, hosting fingerprint, ransomware-claim status, and pivot candidates. Invoked by /cti-orchestrator when the target is a domain.
Liberty91LTD/cti-skills
Feedback loop implementation for continuous CTI improvement. Consumer feedback, analyst retrospectives, source quality tracking.
Liberty91LTD/cti-skills
Use when a user asks to investigate, check, enrich, or characterize an IP address (IPv4 or IPv6). Chains VirusTotal, Shodan, AbuseIPDB, GreyNoise, OTX, and optionally Censys in parallel, then consolidates findings and prioritizes follow-up IOCs. Invoked by /cti-orchestrator when the target is an IP.
Liberty91LTD/cti-skills
Use when surfacing the assumptions underlying an analytical judgment, the user asks "what are we assuming?" / "are these assumptions still valid?", or before publishing a high-impact assessment. Standard SAT applied during major assessments.
Liberty91LTD/cti-skills
Use when you need abuse-report history for an IPv4/IPv6 address — confidence score, total reports, distinct reporters, usage type. IP-only. Commonly invoked by /ip-investigation. Retrieval only.
Liberty91LTD/cti-skills
Use when you need deep host + certificate reconnaissance for an IP or need to run a Censys search query. Returns services, TLS certificates, ASN, and location. Free tier is severely limited (250 queries/month) — use sparingly. Retrieval only.
Liberty91LTD/cti-skills
Use when you need to classify an IP as internet scanner noise vs. targeted activity. Returns noise/riot flags, classification (benign/malicious/unknown), actor name if known. IP-only. Commonly invoked by /ip-investigation to filter out mass-scanning noise. Retrieval only.
Liberty91LTD/cti-skills
Use when you need to submit a URL for live scanning via URLScan.io and retrieve results, or search existing scans for a domain. Returns verdict, final URL after redirects, resolved IP, contacted domains/IPs, and screenshot URL. Commonly invoked by /url-investigation and /domain-investigation.
Liberty91LTD/cti-skills
Use when assessing the maturity of a CTI programme, the user asks "how mature is our CTI?" / "what should we improve next?", or wants a benchmark against the five-level model across six dimensions.
Liberty91LTD/cti-skills
MITRE ATT&CK local dataset reference. Query techniques, groups, software, and mitigations from the local enterprise-attack.json.
Liberty91LTD/cti-skills