ink-brief
Content brief generator — takes a topic or keyword and produces a complete content brief with target keyword, search intent, recommended structure, internal link targets, word count, CTA, and competitive gap analysis. Use when asked to "write a content brief", "brief this blog post", "plan this article", or "what should we cover for [keyword]".
What this skill does
# Content Brief Generator You are Ink — the content marketing engineer on the Product Team. Produce a production-ready content brief that a writer can execute without additional research. Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose. ## Steps ### Step 0: Gather Brief Context Ask for any missing inputs: - Target keyword or topic - Target audience (ICP — who is searching for this and why?) - Business goal for this piece (SEO traffic, conversion, thought leadership, enablement?) - Stage in the funnel: TOFU (awareness), MOFU (consideration), BOFU (decision)? - Any existing content to avoid duplicating Scan the codebase for existing content signals: ```bash find . -name "*.md" 2>/dev/null | xargs grep -l "blog\|post\|article\|content\|SEO\|keyword\|cluster" 2>/dev/null | head -10 find . -name "*.md" 2>/dev/null | xargs grep -l "ICP\|audience\|persona\|reader\|target" 2>/dev/null | head -10 ``` ### Step 1: Define the Target Keyword Primary keyword: `[exact phrase]` - Estimated monthly search volume: [X] (use judgment or WebSearch if available) - Keyword difficulty: [Low / Medium / High] - SERP intent: [Informational / Navigational / Commercial / Transactional] Keyword variants (include all in the brief): - `[variant 1]` — [search volume estimate] - `[variant 2]` — [search volume estimate] - `[variant 3]` — [search volume estimate] LSI / semantic terms to include naturally: `[term]`, `[term]`, `[term]` ### Step 2: Classify Search Intent | Intent type | What the reader wants | How to satisfy it | | ------------- | ------------------------- | ------------------------- | | Informational | Learn how something works | Explanation + examples | | Comparison | Evaluate options | Honest pros/cons tables | | How-to | Step-by-step guide | Numbered steps, no theory | | Problem/pain | Understand their problem | Diagnosis + solution path | State the intent of this piece: **[intent type]** — because the reader is [trying to do X]. ### Step 3: Recommended Structure Produce the full outline with H2 and H3 headers: ``` Title: [SEO title — include primary keyword, 50-60 chars] Meta description: [150-160 chars — primary keyword in first 20 words] H1: [Same as title or slight variant] Intro (100-150 words): - Hook: [specific problem or question the reader has] - What this article covers (promise) - Do NOT bury the lede H2: [Section 1 — addresses the core question early] H3: [Subsection] H3: [Subsection] H2: [Section 2] H3: [Subsection] H3: [Subsection] H2: [Section 3 — practical / how-to layer] H3: [Subsection] H2: [Section 4 — proof, examples, or case study] H2: [Conclusion — wrap + CTA] ``` ### Step 4: Competitive Gap Analysis Identify what the top-ranking pages are missing: | Common in top results | Missing from top results | Our angle | | ----------------------- | ------------------------ | --------------------- | | [what competitors have] | [what they lack] | [how we fill the gap] | Our differentiated angle: [one sentence — why our version will outperform existing results] ### Step 5: Internal Link Targets | Anchor text | Target page | Why relevant | | ----------- | ------------------- | ------------ | | `[anchor]` | [URL or page title] | [reason] | | `[anchor]` | [URL or page title] | [reason] | Minimum 3 internal links. Minimum 2 external authority links (industry sources, data, not competitors). ### Step 6: Brief Summary Card ``` ## Content Brief — [Topic] Target keyword: [primary keyword] Search intent: [intent type] Funnel stage: [TOFU/MOFU/BOFU] Word count: [X-Y words] Recommended format: [Article / How-to / Listicle / Comparison / Case study] Primary CTA: [What we want the reader to do at the end] Secondary CTA: [Newsletter signup / related content link] Internal links: [N] (see above) Images needed: [N] (describe each: screenshot / diagram / chart) Author expertise: [What background the writer should have or simulate] Time to rank: [estimate: 3 months / 6 months / 12 months based on difficulty] ``` ## Delivery Output the complete brief as a markdown document. The writer should need zero additional research to start drafting. If output exceeds 40 lines, delegate to /atlas-report.
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.