agent-meta
claudeSkill discovery, skill evolution, and context-window management
38 skills
Organizational role skills: demand generation
Plugin org-demand-generation from marketplace dxta-skills in DxTa/claude-code-skills. Commands read from the repo's manifest — 5 days ago.
ai-search-optimizationImprove how a company, product, or fact is retrieved and represented in AI-generated answers through self-contained pages, explicit facts, structured content, source attribution, and citation monitoring. Use when AI answers omit or misstate a brand, when creating retrieval-oriented content, or when
app-store-optimizationImprove an iOS App Store or Google Play listing's search visibility and install conversion through metadata, keyword coverage, screenshots, ratings, reviews, and controlled tests. Use when auditing a listing, preparing a launch, diagnosing low impressions or installs, or planning store experiments.
landing-page-cro-expertDiagnose and improve a landing page, homepage, or sales page by testing clarity, audience fit, proof, objections, page sequence, form friction, and the primary call to action. Use when a page underperforms, when given a URL or screenshot for critique, or before choosing conversion experiments.
lead-captureDesign ethical lead magnets, free tools, forms, popups, and gated content that exchange a useful next step for permission to follow up. Use when increasing qualified contacts, deciding what to gate, planning a calculator or assessment, or reducing form and overlay abandonment.
lifecycle-messagingDesign behavior-triggered email and SMS programs for onboarding, activation, nurture, retention, re-engagement, and transactional events. Use when creating or repairing sequences, choosing timing and segmentation, diagnosing opens, clicks, conversion, opt-outs, or deliverability.
listing-distributionPlan and maintain product presence in buyer-used directories, review sites, marketplaces, launch platforms, comparison pages, and alternative pages. Use when preparing a listing campaign, choosing worthwhile destinations, assembling reusable listing assets, or correcting stale public product informa
marketing-analyticsPlan, audit, and interpret marketing measurement through event schemas, consent-aware tracking, attribution, experiments, and decision-focused reporting. Use when instrumenting a site or funnel, reconciling analytics tools, evaluating channel performance, or deciding whether a campaign caused increm
paid-advertisingPlan, launch, measure, and optimize paid search, social, and display campaigns using verified conversion tracking, intent-based structure, creative testing, budget limits, and downstream customer quality. Use when setting up campaigns, diagnosing acquisition cost, reallocating spend, or deciding whe
programmatic-seoAssess and build search-targeted page sets from a validated query pattern, reliable dataset, useful template, and scalable internal linking. Use when considering location, comparison, integration, or use-case pages at scale, or when auditing thin, stale, orphaned programmatic pages.
seo-strategyAudit and prioritize organic search work across crawlability, indexation, intent, site architecture, internal links, structured data, performance, and authority. Use when pages do not rank, traffic falls, pages are deindexed, URLs or navigation need planning, or SEO fixes need sequencing by business
Skill discovery, skill evolution, and context-window management
38 skills
Argo CD and Argo Workflows GitOps operations for Kubernetes
38 skills
Megatron Bridge / TensorRT-LLM / PyTorch GPU performance tuning and profiling
38 skills
LLM evaluation (NEL, BYOB, MLflow) and model serving (vLLM, SGLang, TRT-LLM)
38 skills
NeMo / Megatron repo workflow: CI, dependency bumps, issues, conventions
38 skills
NVIDIA DeepStream, VSS deployment, real-time VLM, video search and analytics
38 skills
AGENTS.md as project instructions, by one option. Under claude-md-or-agents-md a project with no instruction files of its own gets its AGENTS.md files instead: a prompt.context hook asks $.fs.ancestors for every AGENTS.md and .claude/AGENTS.md from the filesystem root down to the working directory and hands them to the engine as project instruction files, which it renders, announces and withholds from agents exactly as it does CLAUDE.md, skipping any file the engine already loaded by import or link; a tool.call hook on Read attaches the ones under the project root as the engine attaches a nested CLAUDE.md. Under claude-md-and-agents-md every AGENTS.md is loaded beside CLAUDE.md. Under managed-only the project's and the person's instruction files are dropped and the organization's managed ones kept. Under claude-md the engine's walk stands alone. claude-md-or-agents-md is the default.
Work with your Box content directly from Claude Code — search files, organize folders, collaborate with your team, and use Box AI to answer questions, summarize documents, and extract data without leaving your workflow.
9 skills
Ready-to-run workflows for financial advisors in Claude Cowork, drawing live data from the tools their firm already uses through third-party connectors. The plugin holds no client data, and the advisor approves any write back to an external system. Claude gathers, organizes, summarizes, compares and presents information, while the advisor exercises judgment, makes the recommendation and gives the advice. For financial professional use only; not investment, legal, or tax advice.
8 skills · 6 agents · 36 MCP servers
Organic LinkedIn presence, end to end, with LinkedIn's own rules enforced in code. Orchestrator (context: fork) gates every request against User Agreement §8.2 — refusing automation, scraping, engagement pods, bulk DMs, fake identity and fabricated proof, each with a compliant substitute — then routes to profile / strategy / content / engagement / analytics. Headline and whole-profile scoring with fixes ranked by points per hour; positioning brief with a mandatory exclusion list; cadence priced against real hours with a 90-minute floor; newsletter eligibility + six-month sustainability gate; post linter blocking on engagement bait and screen-reader-hostile Unicode pseudo-bold; repurposing with a reuse ledger; capped commenting roster and template-refusing outreach; analytics that test patterns against a seeded permutation null and refuse to conclude below 10 posts. 17 stdlib tools, 15 references with per-claim confidence levels. No credentials, no API calls, nothing auto-sent. Answers discussion #934.
6 skills · 8 commands · 2 agents
Identify which organic growth path to pursue — new segments, geographies, channels, or products.
1 skill
HookRadar creative intelligence workflows for Codex, Claude, and MCP-capable agents: competitor ads, organic videos, AI creative analysis, reports, and free first-pass competitor research.
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.