菜单
这个仓库中的 skills
SkillsMP 已收集 tinh2/skills-hub-registry 中的 536 个 Skill。打开任一 Skill 可查看来源和详情。
tinh2/skills-hub-registry已展示 40 / 536 个已收集 Skill。
Detect content cannibalization on a site — multiple URLs ranking (or impressing) for the same query, splitting click-through, diluting authority, and confusing Google about which URL is canonical for the intent. Pulls GSC query × page data, identifies…
原文语言：英语
Pull and analyze Google Search Console data via the GSC API. Produces: weekly query × page performance with WoW/MoM/YoY deltas, top movers report (winners + losers ranked by absolute click change), click-loss attribution (lost rank? lost impressions? lost…
原文语言：英语
Build the internal link graph for a site, run PageRank-style authority distribution, detect orphan pages, and recommend new internal links via embedding-based semantic similarity (not keyword matching). Crawls the site (sitemap-driven, respects robots),…
原文语言：英语
The full open SEO suite for 2026 — a single orchestrator that composes 10+ specialized sub-skills into a daily, weekly, and on-demand workflow that owns the SEO + GEO surface for a site. Built as a direct, open, code-first answer to Visibly AI's "6 agents +…
原文语言：英语
Sets up and optimizes parallel task workflows for Cursor Composer 2.5. Decomposes multi-step work into concurrent sub-tasks with acceptance criteria, installs complementary skills, and verifies that the parallel output is correct and coherent before…
原文语言：英语
Monitor federal grant opportunities across Grants.gov (Simpler.grants.gov is the modern UX), SAM.gov assistance listings (the post-CFDA replacement that preserves CFDA program numbers), and direct agency portals — NIH RePORTER + NIH Guide, NSF Funding, DOE…
原文语言：英语
Extract a structured abstract from a commercial lease PDF — tenant/landlord identification, premises description + RSF/USF, lease term + commencement/expiration, renewal options (count, notice windows, fair-market rent reset), base rent schedule + escalations…
原文语言：英语
Map a cloud system against NIST SP 800-53 Rev. 5 + FedRAMP baselines to produce the documentation an authorization needs — System Security Plan (SSP), Control Implementation Summary (CIS), Plan of Action and Milestones (POA&M), Continuous Monitoring (ConMon)…
原文语言：英语
Analyze a residential rental property as an investment — 1-4 unit single-family / duplex / triplex / quadplex, condo, townhome. Computes: gross rent multiplier (GRM), cap rate (by property class, 4-12% range in 2026), cash-on-cash return (target 8-12%), DSCR,…
原文语言：英语
Run a full Section 508 + WCAG 2.2 Level AA accessibility audit on a federal / .gov / public-sector website or ICT product. Section 508 incorporates WCAG 2.0 AA as the binding federal standard, but most modern federal procurements now test against WCAG 2.2 AA…
原文语言：英语
Manage the full Freedom of Information Act (FOIA) and state public records request lifecycle — intake form generation, agency-specific portal routing (FOIA.gov, FBI eFOIA, USCIS, FOIAonline successor portals), statutory clock tracking (20 working days federal…
原文语言：英语
Audio file → full publishing kit pipeline. From a single .mp3 or .wav per episode, generates Whisper-large-v3 transcript with word-level timestamps, automatic chapter detection (audio scene change + topic shift), two show-notes lengths (scannable summary +…
原文语言：英语
Monitor SAM.gov federal contract opportunities (and follow-on awards) by NAICS, PSC, agency, set-aside, and keyword — produces a daily pipeline report with pursue/no-pursue scoring, capture-management cadence, RFI / Sources-Sought pre-RFP signal tracking…
原文语言：英语
Generate a multi-channel abandoned cart recovery sequence — SMS at 15 min (98% open rate, 25-40% conversion) followed by email cadence at 1hr / 24hr / 72hr, plus optional push and retargeting touchpoints. Cart-value-segmented (under $50 / $50-$150 / over…
原文语言：英语
Generate a complete structured interview kit for a role — 3-5 role-specific competencies, one behavioral (STAR-format) question per competency, 1-5 scoring rubric with explicit behavioral anchors at each level, per-panel scorecards, interviewer debrief…
原文语言：英语
Generate a bias-free, ATS-optimized, skills-based job description for 2026. Runs a banned-word filter on gender-coded ("rockstar/ninja/guru/aggressive/dominate"), age-coded ("digital native/young/recent grad"), and ability-coded ("walk the floor") language;…
原文语言：英语
Generate a production-grade Vehicle Routing Problem (VRP) solver using Google OR-Tools — supports CVRP (capacity), VRPTW (time windows), VRPPD (pickup + delivery), multi-depot, multi-trip, heterogeneous fleet, driver hours-of-service (HOS) compliance, and…
原文语言：英语
Multi-carrier shipping rate comparison and label-generation pipeline — real-time quotes from USPS, UPS, FedEx, DHL via direct carrier APIs OR aggregators (Shippo / EasyPost / ShipStation / Pirate Ship). Handles 2026 rate landscape: FedEx/UPS/DHL each +5.9%…
原文语言：英语
Generate an institutional-grade commercial real estate underwriting model — input schema (T-12 income, T-3 trailing, rent roll, debt terms, exit assumptions), calc engine (Cap Rate, NOI, Cash-on-Cash, IRR, DSCR, Debt Yield, ROI, Equity Multiple, levered &…
原文语言：英语
Generative Engine Optimization (GEO) / Answer Engine Optimization (AEO) — make a site citable by ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews. Generates llms.txt and llms-full.txt, fills schema.org coverage gaps (Organization, Person/Author,…
原文语言：英语
Generate a production-grade Industrial IoT protocol bridge — OPC UA ↔ MQTT Sparkplug B, Modbus → MQTT, or direct PLC (Rockwell/Siemens/Beckhoff) → cloud (AWS IoT Core / Azure IoT Hub / GCP IoT / self-hosted HiveMQ). Output is real code with TLS / X.509 mutual…
原文语言：英语
Generate MLS-compliant property listing copy in five length variants (tagline, MLS-short ≤250 char, MLS-long ≤4000 char, marketing description ~600-800 words, social caption) PLUS schema.org RealEstateListing JSON-LD for SEO/AEO syndication. Auto-runs HUD…
原文语言：英语
Generate a production-grade OEE (Overall Equipment Effectiveness) measurement pipeline for a manufacturing line — data ingestion from MQTT/OPC-UA/Modbus/CSV, A×P×Q calculation engine, Six Big Losses categorizer, MTBF/MTTR/TEEP metrics, Grafana or Streamlit…
原文语言：英语
Comprehensive 2026 SEO audit covering classic technical SEO (crawl, render, index, Core Web Vitals with INP), on-page (titles, meta, headings, internal linking), content (topical authority, entity density), and the new mandatory layer — Generative Engine…
原文语言：英语
Generate a 2026-grade content brief for a target query — combines classic SERP analysis with AI Overview / Perplexity / ChatGPT citation analysis, entity recommendations (target ≥15 recognized entities), topical authority gap map, intent-mapped heading…
原文语言：英语
Workflow orchestrator. Decomposes a task into ordered steps, finds or installs the right skill for each step, runs the chain, and offers to save it as a reusable skill.
原文语言：英语
Dispatch independent feature work in parallel git worktrees. Spawns one agent per feature, each in its own isolated worktree, then merges sequentially. Use when 3+ independent features need shipping and would otherwise run serially. Triggers: parallel…
原文语言：英语
Build distinctive, production-grade interfaces with Ralph Wiggum velocity. Ships working code — web or mobile — with modern CSS, fluid typography, purposeful motion, and zero generic AI aesthetics. Use when: 'build UI', 'design this', 'create interface',…
原文语言：英语
Fast autonomous build loop -- 4 iterations max. Ship it, quick build, fast implementation, just build it, ship fast.
原文语言：英语
Implements a story, spec, or ticket from any format (text, image, structured doc) using the repository's existing conventions. Writes tests, commits, and creates a PR. Trigger phrases: implement story, implement spec, implement ticket, code this feature,…
原文语言：英语
Complete autonomous design overhaul — tears down dated patterns and rebuilds with modern CSS, proper tokens, purposeful motion, and production-grade quality. The nuclear option for ugly interfaces.
原文语言：英语
Automated app improvement cycles. Assesses each app's health, prioritizes by staleness and debt, consumes recall/metrics/evolve findings from cron, then runs targeted fix pipelines per app. Fully autonomous — runs unattended via cron or manually. Triggers:…
原文语言：英语
Architect-level story review with component reuse, domain consistency, data privacy, service architecture, and infrastructure checks. Design review before coding or implementation validation after.
原文语言：英语
Sets up and manages Windsurf Spaces for multi-agent workflows — discovers project context, creates properly-scoped Space configs, seeds shared context for agent sessions, and generates structured Devin handoff specs so cloud execution starts with complete,…
原文语言：英语
Runtime sweep that catches mobile-layout bugs: content clipped off the edge of a phone screen, touch targets smaller than 44×44px, text inside a button or input that overflows its visible width, and modals that extend past the viewport. Loads the running web…
原文语言：英语
Statically scan a CSS / single-file HTML / multi-file frontend project for references to undefined CSS custom properties — the silent class of bug where `color: var(--ink-2)` is written but `--ink-2` is never declared in any `:root { ... }` block, and the…
原文语言：英语
Methodically walks a running app — every public route, every interactive control, every state (empty/loading/error/auth/un-auth) — to find real bugs, then root-causes, fixes, adds a regression test, and verifies each one before moving to the next. Use when:…
原文语言：英语
Polishes UI primitives one at a time using 2026 research-backed patterns — adds loading/icon states to buttons, replaces inline skeletons with primitives, adds secondary actions to errors, ensures 48px touch targets and visible focus indicators, applies a…
原文语言：英语
Audits GitHub Copilot AI Credit usage patterns before the June 2026 flex-billing transition. Pulls usage data from the GitHub API, identifies high-credit-cost workflows (agentic sessions, cloud review, heavy chat), recommends the right plan tier (Pro / Pro+ /…
原文语言：英语
Rewrites existing landing pages, blog posts, and documentation so AI search engines (Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini) cite them. Applies the 2026 AEO pattern: 40-80 word direct answer at top, 4-intent classification (definitional /…
原文语言：英语