菜单
这个仓库中的 skills
SkillsMP 已收集 mj-deving/pai-skills 中的 107 个 Skill。打开任一 Skill 可查看来源和详情。
mj-deving/pai-skills已展示 40 / 107 个已收集 Skill。
Ethical people-finding using 15 parallel research agents (45 search threads) across public records, social media, reverse lookups. Public data only, no pretexting. USE WHEN find person, locate, reconnect, people search, skip trace, reverse lookup, social…
原文语言：英语
OSINT and people-finding — structured investigations, company intel, due diligence, and ethical people search. USE WHEN OSINT, due diligence, company intel, background check, find person, people search, public records, reverse lookup, social media search,…
原文语言：英语
Generate illustrations, technical diagrams, mermaid flowcharts, infographics, header images, thumbnails, comics, flyers, posters, and PAI pack icons using multiple rendering backends. USE WHEN art, header images, visualizations, mermaid, flowchart, technical…
原文语言：英语
Programmatic video creation with React via Remotion — compositions, animations, motion graphics, rendered to MP4. USE WHEN video, animation, motion graphics, video rendering, React video, intro video, YouTube video, TikTok video, video production, render…
原文语言：英语
Visual and video content — illustrations, diagrams, mermaid, infographics, header images, thumbnails, comics, and programmatic video via Remotion. USE WHEN art, diagrams, mermaid, infographics, video, animation, Remotion, thumbnails, comics, generate image,…
原文语言：英语
Project-only Telos context mapping for goals, constraints, stakeholders, decisions, dependencies, risks, and narrative reports. Use when analyzing a project, building a project context pack, mapping dependencies, writing an executive project brief, or…
原文语言：英语
Source-grounded research workflow for current facts, technical topics, market scans, literature reviews, and evidence-backed recommendations. Use when the user asks to research, investigate, compare sources, verify claims, summarize a topic from sources, or…
原文语言：英语
Scientific presentation generation — LaTeX Beamer decks and self-contained HTML slide decks using Scott Cunningham's Rhetoric of Decks framework. USE WHEN scientific presentation, beamer deck, academic slides, scientific slides, compile deck, latex…
原文语言：英语
Social media scraping, business data, e-commerce via Apify actors — with auto-update workflow for actor catalog. USE WHEN Twitter, Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon scraping, Apify, update Apify actors, social media scraping,…
原文语言：英语
X/Twitter CLI for reading, searching, and posting via browser cookies. USE WHEN read tweet, search X, search Twitter, post tweet, reply tweet, X timeline, Twitter mentions, trending topics, user tweets, bird.
原文语言：英语
4-tier progressive URL scraping and multi-page crawling — WebFetch, then Chrome-header curl, then Playwright browser, then Bright Data proxy. Auto-escalates when lower tiers fail. USE WHEN Bright Data, scrape URL, web scraping, site blocking me, can't access,…
原文语言：英语
Free open-source multi-page website crawler — self-hosted Python crawler that outputs LLM-ready Markdown with JS rendering. USE WHEN crawl website free, crawl site, crawl pages free, free crawler, open source crawler, crawl4ai, crawl without cost, self-hosted…
原文语言：英语
Discord guild archiving and search via discrawl CLI. USE WHEN Discord search, Discord history, Discord messages, Discord members, Discord channels, search Discord, Discord archive, Discord mentions, Discord server, Discord guild, discrawl.
原文语言：英语
Free zero-setup web scraping via Jina Reader API — converts any URL to clean Markdown with JS rendering, no API key needed. USE WHEN jina reader, free scrape, quick scrape, extract webpage free, scrape without key, simple scrape, lightweight scrape, get page…
原文语言：英语
Web scraping via progressive escalation — Jina Reader, Crawl4AI, Spider.cloud, Bright Data, Apify actors, bird CLI for X/Twitter, discrawl for Discord, Katana URL discovery. USE WHEN scraping, crawl, scrape URL, Twitter scraping, Apify, bot detection, jina…
原文语言：英语
Low-cost high-scale web scraping and crawling via Spider.cloud API — Rust-based, fast, ~$0.48/1K pages. USE WHEN spider cloud, scale scraping, bulk scrape, bulk crawl, high volume scraping, scrape at scale, affordable crawling, spider.cloud.
原文语言：英语
Aggregate and analyze annual security reports from major vendors — extract trends, compare threat landscapes year-over-year, produce synthesized threat intelligence summaries. Fetch, list, and update report sources. USE WHEN annual reports, security reports,…
原文语言：英语
Test LLM applications for prompt injection vulnerabilities — jailbreak attempts, system prompt extraction, context manipulation, guardrail bypass techniques, direct injection, indirect injection, multi-stage attacks, and reconnaissance. USE WHEN prompt…
原文语言：英语
Network reconnaissance — subdomain enumeration, port scanning, DNS/WHOIS/ASN lookups, endpoint discovery from JS, mass scanning, path discovery, CIDR/netblock analysis. Passive and active modes with corporate structure mapping and bounty program tracking. USE…
原文语言：英语
Security news from tldrsec, no.security, Krebs, Schneier, and other sources. USE WHEN security news, security updates, what's new in security, breaches, security research, sec updates, tldrsec, Krebs, Schneier.
原文语言：英语
Proactive secure coding — vulnerability patterns, bypass techniques, defense-in-depth for TypeScript and Cloudflare Workers. USE WHEN secure code, code security, vulnerability prevention, secure coding review, defense in depth, XSS prevention, SQL injection…
原文语言：英语
Security assessment — network recon, web app testing, prompt injection testing, security news, and vulnerability scanning. USE WHEN recon, port scan, subdomain, DNS, WHOIS, pentest, threat model, OWASP, prompt injection, LLM security, security news, trivy,…
原文语言：英语
Full web app security assessment — app understanding, threat modeling, OWASP testing, ffuf fuzzing, Playwright automation, AI-assisted vuln analysis. Coordinates with Recon and PromptInjection skills. USE WHEN web assessment, pentest, security testing,…
原文语言：英语
Declarative API testing and HTTP probing — Hurl for multi-step API workflows with assertions, httpx for concurrent endpoint discovery. USE WHEN API testing, HTTP test, endpoint testing, Hurl, httpx, REST API, API validation, request chaining, batch URL, probe…
原文语言：英语
Test-driven development — RED/GREEN/REFACTOR cycle, Prove-It Pattern for bugs, test pyramid, coverage strategy. USE WHEN writing tests, TDD, test strategy, prove-it pattern, test pyramid, bug fix testing, test coverage, test-first, write tests, add tests,…
原文语言：英语
Divergent ideation via Verbalized Sampling + extended thinking (1.6-2.1x diversity). USE WHEN be creative, deep thinking, brainstorm, divergent ideas, creative solutions, maximum creativity, tree of thoughts, idea generation, idea refine, refine idea, how…
原文语言：英语
Strategic context management for AI agents — 5-level hierarchy, starvation/flooding diagnosis, brain dump structuring, confusion surfacing. USE WHEN context management, context strategy, too much context, too little context, context window, context budget,…
原文语言：英语
Multi-agent debate with visible transcripts where agents respond to each other. USE WHEN council, debate, perspectives, weigh options, deliberate, multiple viewpoints. Unlike RedTeam (adversarial), Council is collaborative-adversarial.
原文语言：英语
Decompose to axioms, challenge inherited assumptions, reconstruct from verified truths. USE WHEN first principles, fundamental, root cause, decompose, challenge assumptions, rebuild from scratch.
原文语言：英语
2-8 scientific lens passes to surface hidden requirements single-pass analysis misses. USE WHEN iterative depth, deep exploration, multi-angle analysis, multiple perspectives, examine from angles, surface hidden requirements.
原文语言：英语
Synthesize multi-agent outputs into a single templated execution spec. Consumes any combination of Thinking sub-skill and Research outputs. USE WHEN synthesize plan, plan synthesis, merge findings, execution spec, combine analysis, synthesize outputs, make a…
原文语言：英语
32 adversarial agents to destroy weak arguments and find fatal flaws — parallel analysis and adversarial validation. USE WHEN red team, attack idea, counterarguments, critique, stress test, poke holes, devil's advocate, find weaknesses, break this, parallel…
原文语言：英语
Hypothesis-test-analyze cycles for systematic problem-solving — the meta-skill governing all others. Includes define goal, generate hypotheses, design experiment, measure results, analyze results, iterate, full cycle, quick diagnosis, and structured…
原文语言：英语
Multi-mode analytical and creative thinking — first principles, iterative depth, brainstorming, council debates, red teaming, world threat modeling, scientific hypothesis testing, plan synthesis, and context engineering. USE WHEN first principles, decompose,…
原文语言：英语
Stress-test ideas, strategies, and investments across 11 time horizons (6mo-50yr). Update and view world models. USE WHEN threat model, world model, test idea, test strategy, future analysis, test investment, test against future, stress test idea, time…
原文语言：英语
Systematic debugging and error recovery — 6-step triage, Stop-the-Line Rule, non-reproducible bug playbook, competing hypotheses. USE WHEN debugging, fix bug, error recovery, troubleshooting, reproduce bug, find root cause, stack trace, error message, test…
原文语言：英语
Incident management from detection through postmortem. USE WHEN incident, outage, SEV1, SEV2, production down, postmortem, blameless review, incident response, war room, incident update, status page, root cause analysis, 5 whys, incident timeline, on-call.
原文语言：英语
Debugging and incident management — 6-step triage, Stop-the-Line, competing hypotheses for dev-time bugs plus incident detection, response, and blameless postmortems for production issues. USE WHEN debugging, fix bug, error recovery, troubleshooting,…
原文语言：英语
AI-powered audio/video editing — transcription, intelligent cut detection, automated editing with crossfades, and optional cloud polish. USE WHEN clean audio, edit audio, remove filler words, clean podcast, remove ums, fix audio, cut dead air, polish audio,…
原文语言：英语
Attach to a real existing browser session instead of launching a separate Linux or WSL browser. Use when the user wants their current logged-in browser, real Brave on Windows from WSL, existing browser session, native messaging, CDP attach, remote debugging…
原文语言：英语