content-strategy
Develop and execute a content strategy that maps content to audience needs, funnel stages, and business goals through editorial planning and performance analysis. Use when the user requests content strategy or provides relevant inputs for this workflow.
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/content-strategy && cp -r /tmp/content-strategy/marketing-and-seo/content-strategy ~/.claude/skills/content-strategySKILL.md
# Content Strategy This skill enables an AI agent to build a comprehensive content strategy from the ground up or audit and improve an existing one. The agent defines content pillars aligned to business objectives, maps content types to funnel stages (TOFU/MOFU/BOFU), creates editorial calendars, and establishes a measurement framework. The output is a repeatable system for producing, distributing, and optimizing content that drives traffic, engagement, and conversions. ## Workflow 1. **Audit existing content and define goals.** Inventory all current content assets — blog posts, landing pages, case studies, videos, whitepapers — with their publication dates, traffic, and conversion metrics. Identify top performers, underperformers, and content gaps. Align the strategy to 2–3 measurable goals such as "increase organic traffic 40% in 6 months" or "generate 200 MQLs per month from content." 2. **Research the target audience and build personas.** Define 2–4 buyer personas with demographics, job roles, pain points, content consumption habits, and preferred channels. Map each persona to their buyer journey stages: awareness (problem recognition), consideration (evaluating solutions), and decision (selecting a vendor). This determines what content types each persona needs at each stage. 3. **Establish content pillars and topic clusters.** Define 3–5 content pillars — broad themes that align with the product's value proposition and audience needs. Under each pillar, plan a cluster of 8–15 supporting pieces that link back to a comprehensive pillar page. This structure builds topical authority for SEO and creates a logical content architecture. 4. **Build the editorial calendar.** Plan content production on a rolling 3-month horizon. For each piece, specify the topic, target keyword, content format (blog, video, infographic, podcast), funnel stage, assigned persona, distribution channels, author, and publish date. Balance content across pillars and funnel stages — roughly 60% TOFU, 30% MOFU, and 10% BOFU. 5. **Define distribution and repurposing workflows.** For each content piece, plan the distribution path: organic social posts, email newsletter inclusion, syndication partners, and paid promotion budget. Design repurposing chains — for example, a long-form blog post becomes a LinkedIn carousel, a Twitter/X thread, an email snippet, and a short video. This multiplies reach without multiplying production effort. 6. **Set up measurement and iteration cadence.** Define KPIs for each funnel stage: TOFU (traffic, impressions, social shares), MOFU (email signups, content downloads, time on page), BOFU (demo requests, free trial starts, SQLs). Review content performance biweekly, retire or update underperforming content quarterly, and refresh the editorial calendar monthly. ## Usage Provide the agent with your business type, target audience, existing content (if any), and goals. The agent will return a complete content strategy with pillars, editorial calendar, and distribution plan. **Prompt:** `Create a content strategy for a B2B cybersecurity startup targeting IT directors at mid-market companies. Goal: generate 150 leads/month from content within 6 months.` ## Examples ### Example 1: Three-Month Editorial Calendar **Request:** Create a Q2 content calendar for a SaaS HR platform targeting startup founders. | Week | Topic | Format | Funnel | Pillar | Channel | Keyword | |------|-------|--------|--------|--------|---------|---------| | W1 Apr | How to Write Your First Employee Handbook | Blog (2,000 words) | TOFU | HR Compliance | Organic + LinkedIn | employee handbook template | | W2 Apr | Employee Handbook Checklist (PDF) | Downloadable guide | MOFU | HR Compliance | Email + Gated landing page | — | | W3 Apr | 5 Onboarding Mistakes That Increase Turnover | Blog (1,500 words) | TOFU | Employee Onboarding | Organic + Twitter/X | onboarding mistakes | | W4 Apr | Video: Setting Up PTO Policies in HRBot | Tutorial video (8 min) | BOFU | Product Demos | YouTube + Email | — | | W1 May | Remote Hiring: Compliance in 5 States | Blog (2,500 words) | TOFU | Remote Work | Organic + LinkedIn | remote hiring compliance | | W2 May | Startup Compensation Benchmarks 2025 | Data report + infographic | MOFU | Compensation | Gated + Social | startup salary benchmarks | | W3 May | How We Helped Acme Scale from 10 to 100 Employees | Case study | BOFU | Product Demos | Email + Sales enablement | — | | W4 May | Ask an HR Expert: Live Q&A Webinar | Webinar | MOFU | HR Compliance | Email + LinkedIn Events | — | | W1 Jun | Performance Review Templates That Actually Work | Blog + templates | TOFU | Performance Mgmt | Organic + Pinterest | performance review template | | W2 Jun | MOFU Email Nurture Sequence (5-part) | Email series | MOFU | Cross-pillar | Email automation | — | | W3 Jun | Comparison: HRBot vs BambooHR vs Gusto | Comparison page | BOFU | Product Demos | Organic + Paid search | hrbot vs bamboohr | | W4 Jun | Q2 Content Performance Review | Internal report | — | — | Internal | — | ### Example 2: Content Audit with Recommendations **Request:** Audit the existing blog for `startuphub.io` (42 posts published over 18 months). **Audit Findings:** | Category | Count | Avg Monthly Traffic | Action | |----------|-------|-------------------|--------| | High performers (>1,000 visits/mo) | 6 | 2,400 | Update with fresh data, add CTAs, interlink with MOFU content | | Moderate performers (200–1,000 visits/mo) | 14 | 480 | Optimize titles/meta descriptions, add internal links, refresh examples | | Low performers (<200 visits/mo) | 18 | 65 | Consolidate 8 thin posts into 4 comprehensive guides; redirect old URLs | | Outdated content (>12 months, no updates) | 12 | 110 | Update statistics and screenshots, re-publish with current date | | No-traffic content (<10 visits/mo) | 4 | 6 | Evaluate for removal or complete rewrite; 301 redirect to related content | **Top Recommendations:** 1. **Consolidate thin content
Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.
Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.
Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.
Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.
Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.
Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.
Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.
Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.