blog-post
Create a blog post via guided prompts with git context auto-populated. Use when writing a quick update, retrospective, tutorial, deep dive, or devlog entry.
What this skill does
# /blog:post Create a blog post about your work with minimal friction. Gathers context automatically and provides structured templates to reduce blank-page anxiety. ## When to Use This Skill | Use this skill when... | Use alternative when... | |------------------------|--------------------------| | Capturing work quickly into a blog post | Need detailed documentation -> Project wiki/docs | | Want templates to reduce blank-page anxiety | Writing a technical tutorial -> `/blog:post tutorial` | | Need git context auto-populated | Creating portfolio summary -> Different workflow | ## Context - Blog directory: !`find . -maxdepth 1 -type d \( -name blog -o -name posts -o -name _posts \) -print -quit` - Git remotes: !`git remote -v` - Recent commits: !`git rev-list --count --since="7 days ago" HEAD` - Current branch: !`git branch --show-current` ## Parameters Parse `$ARGUMENTS` for: - `type`: Post type (quick-update, project-update, retrospective, tutorial, deep-dive) - If not provided, ask user to select - `--project <name>`: Specify project name (default: detected from git) - `--title <title>`: Specify post title (default: ask user) - `--edit`: Open in editor after creation (default: show filepath) ## Execution Execute this blog post creation workflow: ### Step 1: Gather context Detect project name and recent git history: 1. Use `git log` to get recent commits 2. Extract project name from git remote or directory 3. If blog directory doesn't exist, ask where to save posts ### Step 2: Determine post type If type argument not provided, ask user to select from five options: - Quick Update (5-15 min) - Project Update (20-45 min) - Retrospective (45-90 min) - Tutorial (1-3 hours) - Deep Dive (2-5 hours) ### Step 3: Ask targeted questions based on post type For each type, ask 1-2 focused questions: - Quick Update: "What did you just do?" - Project Update: "Main accomplishment?" and "What was interesting?" - Retrospective: "What period/project?" and "One thing to remember?" - Tutorial: "What are you teaching?" and "Why document this?" - Deep Dive: "What topic?" and "Key insight to share?" ### Step 4: Generate post file 1. Determine where to save (blog directory, ~/blog/, or custom path) 2. Generate filename: `YYYY-MM-DD-<slugified-title>.md` 3. Create file with frontmatter: - `date`: Today - `project`: Detected or specified - `type`: Selected type - `status`: draft 4. Pre-fill content sections with placeholders and git context as comments ### Step 5: Offer writing assistance Ask what user would like to do: - "Help me write it" → Walk through each section interactively - "I'll write it myself" → Show filepath - "Add more context" → Pull more git history and files for reference ### Step 6: Finalize post 1. Present review checklist (title, content, tags, next steps) 2. Ask: "Is this post ready to publish?" (draft or published) 3. Output summary with file path and quick actions ## Agentic Optimizations | Context | Command | |---------|---------| | Get project name | `git remote get-url origin 2>/dev/null \| sed 's/.*\///' \| sed 's/\.git$//'` | | Recent commits | `git log --since="7 days ago" --format="%h %s" 2>/dev/null \| head -10` | | Find blog directory | `ls -d blog/ posts/ content/blog/ content/posts/ _posts/ 2>/dev/null \| head -1` | | Current date | `date +%Y-%m-%d` | | Get today's commits | `git log --since="1 day ago" --format="- %s" 2>/dev/null` | ## Quick Reference | Post Type | Time | Use Case | |-----------|------|----------| | Quick Update | 5-15 min | Small wins, log entries | | Project Update | 20-45 min | Milestone, feature complete | | Retrospective | 45-90 min | Reflection on period/project | | Tutorial | 1-3 hours | Teach how to do something | | Deep Dive | 2-5 hours | Explain complex concepts |
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.