All authors
Claude Skills by JoshuaShepherd
github.com/JoshuaShepherd397 skills10 installs150 views
- Storybook SetupSet up Storybook 8 for Next.js 15 or Vite + React — component dev environment, story scaffolding, shadcn/ui integration, dark mode toggle, accessibility checks (a11y addon), and visual regression snapshot configuration. Use when setting up a component library or design system workflow.Votes: 0GitHub stars: 2
- Visualization RepairAudit React/Next.js components for broken charts and diagrams (Stitch exports, invalid SVG, collapsed Recharts, wrong motion.svg props). Propose a replacement using Recharts, Mermaid, D3, GSAP, or plain React/SVG, then implement. Use when visualizations are missing, clipped, zero-height, off-center, or non-interactive when they should work; keywords: broken chart, stitch visualization, ResponsiveContainer, radar, network graph, SVG motion.Votes: 0GitHub stars: 2
- Write InstructionsAuthor or refine agent instructions — use when asked to write a system prompt, create or update agent instructions, compose instruction layers (identity, theme, mode, style, dynamic context), or tune agent voice and behavior.Votes: 0GitHub stars: 2
- Alan VoiceWrite, edit, or audit content in Alan Hirsch's exact voice — using the same five voice markers, argument patterns, rhetorical posture, and failure mode guards as the AI Lab agent. Use when writing any published content, course material, marketing copy, agent prompts, or social posts that must sound authentically like Alan.Votes: 0GitHub stars: 2
- Article AuditAudit a complete article against all criteria — Alan's five voice markers, SEO/GEO requirements, section architecture, corpus citation quality, pillar alignment, and CTA. Returns per-criterion scores, specific failing passages, and a prioritized revision list. Use before publishing any article, or to diagnose why an article isn't performing.Votes: 0GitHub stars: 2
- Article AuthorWrite a complete evergreen pillar article in Alan Hirsch's voice — with corpus research from his books, full SEO/GEO architecture, and proper citations. This is the main writing skill. It runs planning, corpus research, and writing in sequence. Use when writing any new article for the platform.Votes: 0GitHub stars: 2
- Article CorpusLook up passages, themes, and arguments from Alan Hirsch's book corpus — both from the local markdown files and the Supabase database. Use when researching what Alan actually says about a topic before writing an article. Returns quoted passages with proper citations.Votes: 0GitHub stars: 2
- Article PlanStrategically plan a single evergreen article — pillar assignment, keyword targeting, section outline, corpus references, internal link targets, and CTA. Run this before article-author when you want to align on strategy before writing. Use when deciding what to write or how to structure a specific article.Votes: 0GitHub stars: 2
- Author ContentWrite course content for a specific element (M.N.X) of a transformational course — readings, video scripts, reflection questions, exercises, discussion prompts, and more. Use when authoring or generating course content for a specific week and element code.Votes: 0GitHub stars: 2
- Author ResearchDeep research for book authors — searches Google Scholar, Internet Archive, JSTOR, Google Books/Ngram, Library of Congress, HathiTrust, OECD/World Bank data, historic newspapers, and news archives. Produces an organized research dossier with primary sources, data, historical context, and full citations.Votes: 0GitHub stars: 2
- Author Style GuideCreate or update the author visual style guide that ensures consistent lighting, color grade, and composition across all author imagery — trigger phrases include "author style guide", "visual style for author", "create style guide", "update style guide", or "ensure image consistency".Votes: 0GitHub stars: 2
- Book AuditRun a deterministic, sample-based BookQuality audit comparing the original PDF/EPUB source against its converted Markdown in `corpus/alan_hirsch/<book-slug>/`. Pulls 8–10 representative samples (chapter openings, dense paragraphs, lists, footnotes, scripture quotes, figures), compares character-for-character and structure-for-structure, flags every discrepancy (missing text, OCR errors, lost formatting, broken links, fabricated content, alternate-line drops), and produces a GREEN / YELLOW / R...Votes: 0GitHub stars: 2
- Book ChunkPhase 04a of the books pipeline — produce the canonical `chunks.jsonl` for a book using structure-then-recursive chunking with late chunking and Anthropic-style contextual prefixes. Heading-aware (split on H2/H3, never break a paragraph or footnote), 512-token target with 64-token overlap, embeds the full chapter once and mean-pools per chunk to preserve cross-paragraph anaphora. Output feeds both pgvector and the three external providers via `/book-rag-push`. Use after `/book-ingest` reports...Votes: 0GitHub stars: 2
- Book ConvertPhase 01 of the books pipeline — convert any PDF or EPUB book into lossless, paginated, footnoted Markdown using the right tool for the input type (Marker for native-text PDFs, MinerU for scanned PDFs, Pandoc for EPUB, Mistral OCR as hosted fallback). Auto-routes by file type, writes per-chapter MD with `<!-- page: N -->` markers and `[^N]` footnotes, and lands the output in `corpus/alan_hirsch/<book-slug>/chapters/`. Use when ingesting a new book source file from `_inbox/` into the corpus. T...Votes: 0GitHub stars: 2
- Book FixGenerate or execute a comprehensive remediation prompt for a YELLOW or RED book identified by `/book-audit`. Writes a `fix-<book-slug>.md` to `docs/build/prompts/` enumerating every defect with verbatim PDF source text inlined for verbatim restoration, then optionally executes the prompt to bring the book to GREEN. Mirrors the exemplar structure of `fix-on-the-verge.md` and `fix-reframation.md`. Use after `/book-audit` returns YELLOW or RED. Trigger phrases: "fix this book", "remediate the co...Votes: 0GitHub stars: 2
- Book FrontmatterPhase 02 of the books pipeline — generate, repair, or recompute YAML frontmatter for every chapter in a book and validate against the Zod schema at `scripts/lib/frontmatter-schema.ts`. Recomputes `content_sha256`, `word_count`, `char_count`, `estimated_reading_time`, and `Opening excerpt` to match the current body. Validates `book.json` against `BookManifest` and every chapter against `ChapterFrontmatter`. Use after `/book-convert` + `/book-validate` pass, before `/book-ingest`. Trigger phras...Votes: 0GitHub stars: 2
- Book IngestPhase 03 of the books pipeline — upsert validated MDX corpus into Supabase via Drizzle. Hydrates `books`, `book_chapters`, `book_sections`, and `book_chunks` tables. Maintains separation between display sections (stable bookmark anchors) and RAG chunks (regenerable retrieval units) so re-embedding never invalidates user bookmarks. Idempotent — only re-sections / re-embeds chapters whose `content_sha256` changed. Use after `/book-frontmatter` passes Zod validation. Trigger phrases: "ingest int...Votes: 0GitHub stars: 2
- Book PipelineOrchestrate the full books pipeline (Phases 01 → 04) for a single book from PDF/EPUB to live on all four vector stores. Routes through `/book-convert` → `/book-validate` → `/book-audit` → optional `/book-fix` → `/book-frontmatter` → `/book-ingest` → `/book-chunk` → `/book-rag-push`, with quality gates between phases. Idempotent — safe to re-run after a fix or copy edit. Use to ingest a brand-new book end-to-end, or to re-process a corrected book through every downstream stage. Trigger phrases...Votes: 0GitHub stars: 2
- Book Rag PushPhase 04b of the books pipeline — fan out the canonical `chunks.jsonl` to three vector stores (OpenAI Vector Stores, Gemini File Search, Anthropic Files API) and the in-house pgvector. Idempotent — only re-uploads chunks whose `sha256` changed since the last run; updates `vector_store_ids` map in chapter frontmatter to record which store/version each chapter lives in. Includes the smoke test (same query against all four stores, diff results). Use after `/book-chunk` produces an updated `chunk...Votes: 0GitHub stars: 2
- Book ValidatePhase 01b of the books pipeline — prove no words were lost during PDF/EPUB → Markdown conversion. Runs a five-layer validation harness (word-count diff, fuzzy alignment, 5-gram coverage, embedding similarity, vision LLM judge) comparing the converted MD against the original source. Cheap checks first, semantic checks last, LLM judge only on samples. A chapter that fails any layer goes back to Phase 01 before advancing. Use after `/book-convert`, before `/book-frontmatter`. Trigger phrases: "v...Votes: 0GitHub stars: 2
- CareerCareer management skill covering resume coaching (review, score, tailor, audit), job evaluation, rubric development, content extraction from conversations, and pipeline quality assurance.Votes: 0GitHub stars: 2
- Content IngestIngest, organize, and structure raw content (book chapters, transcripts, articles, research notes) into the repository's canonical format. Use when bringing new source material into the content library.Votes: 0GitHub stars: 2
- Corpus IngestionConvert heterogeneous source files (PDFs, EPUBs, DOCX, PPTX, HTML, audio, images, ZIPs, web pages) into normalized markdown using MarkItDown, then prepare them for Movemental-style corpus pipelines. Use this skill whenever ingesting an author's books, sermons, transcripts, slide decks, or archive materials for downstream theme/voice/concept analysis, RAG pipeline preparation, course content generation, or vector store upload. Also trigger on: "ingest this book", "convert and add to corpus", "...Votes: 0GitHub stars: 2
- Course AuditAudit the course learn experience — checks section components, sidebar rendering, progress tracking, responsiveness, design tokens, and accessibility. Use before shipping a course.Votes: 0GitHub stars: 2
- Course AuthorGenerate course content for a specific section of the transformation loop, following the actual Forgotten Ways course structure, Charter requirements, and Alan Hirsch's voice. Use when writing individual course sections.Votes: 0GitHub stars: 2
- Course IngestIngest course content from markdown files into the database. Parses manifest + module files, validates, and upserts course_lessons, reflection_questions, discussion_prompts, and exercises.Votes: 0GitHub stars: 2
- Course ScaffoldScaffold a new 8-week course with all canonical section types, database rows, and optional markdown file structure. Use when creating a new course from scratch.Votes: 0GitHub stars: 2
- Course SectionCreate a new course section component following the existing section pattern. Use when adding new content types to courses.Votes: 0GitHub stars: 2
- Course UxAudit and fix course player UX against LMS best practices — layout proportions, progressive disclosure, progress psychology, sidebar hierarchy, video sizing, light/dark harmony, sidebar naming & learning flow, cohort pacing, and AI integration points. Use when improving the learn experience.Votes: 0GitHub stars: 2
- Course ValidateValidate a course against the Transformational Course Charter — checks Four Necessities, section completeness, word counts, and structure. Use before publishing or after authoring.Votes: 0GitHub stars: 2
- Dialogue CraftDialogue craft for fiction and conversational AI agents — subtext, character voice differentiation, pacing, exposition handling, conflict in conversation, and the art of what people don't say. Use when writing dialogue, designing agent conversation patterns, or auditing dialogue quality.Votes: 0GitHub stars: 2
- Editorial LensMulti-level editorial review — from developmental editing (structure, argument, arc) through line editing (prose quality, voice) to copy editing (grammar, consistency, fact-checking). Use when reviewing any written work or auditing an agent's output quality.Votes: 0GitHub stars: 2
- Ingest ContentIngest course content from markdown files or a content directory into the database — parsing, validating, and upserting weeks, lessons, reflection questions, discussion prompts, and exercises. Use when loading or re-loading course content into the platform database.Votes: 0GitHub stars: 2
- Nonfiction CraftNon-fiction writing craft — argument construction, evidence handling, essay structure, chapter architecture, research integration, and the art of making ideas vivid. Use when writing, planning, or reviewing non-fiction of any kind (books, essays, articles, thought leadership).Votes: 0GitHub stars: 2
- Paratext AuditAudit paratext (supporting content) across all platform surfaces — courses, books, articles, exercises, field experiments, and reflection questions. Reports presence, voice quality, rendering gaps, and SEO/GEO readiness. Use before publishing content or to find what needs authoring.Votes: 0GitHub stars: 2
- Paratext AuthorWrite missing or stub paratext for any platform surface — books, courses, podcast episodes — in Alan Hirsch's voice. Queries the database for gaps, writes content, and updates via SQL. Use after running /paratext-audit to fill what it found.Votes: 0GitHub stars: 2
- Pathway AuditAudit a pathway page against the canonical 12-section architecture. Reports what's missing, what's below spec, what's complete, and what needs improvement for SEO/GEO, voice, and formation quality. Use before publishing a pathway or after adding new sections.Votes: 0GitHub stars: 2
- Pathway AuthorWrite or update content for a pathway page — any single section or a full pathway. Follows the canonical 12-section architecture, Alan Hirsch's voice, and SEO/GEO best practices. Use when writing new pathways, filling missing sections, or improving existing content.Votes: 0GitHub stars: 2
- Pathway BuilderBuild type-safe React pathway pages from pathway_sections database content — generates types, hooks, section components, and page composition. Triggers on: pathway page, pathway builder, build pathway, pathway components. NOT for: pathway content editing, seed scripts, schema changes, or Stitch conversions.Votes: 0GitHub stars: 2
- Pathway Content AuthorGenerate the full markdown content for any Movemental pathway page — all twelve canonical sections — in the documented voice and style of a given author, grounded in that author's own books and research in the repo (the books corpus and movement_leader_research / dashboard-content). GENERAL skill: works for any tenant author and any pathway theme once an author and a theme are given. Use it whenever someone wants to write, draft, or generate the content for a pathway page — e.g. "write the [t...Votes: 0GitHub stars: 2
- Plain ProseWrite clear, plain prose, and strip register-jargon out of text that already has it. Use this whenever writing prose that should sound like a person talking (essays, web copy, emails, docs, explanations, scripts) AND whenever cleaning up text that reads like a whitepaper, a consulting deck, or systems-engineering English. Trigger it when the user asks to make writing "clearer," "plainer," "simpler," "cleaner," "less corporate," "less jargony," or "less abstract"; when they say text sounds lik...Votes: 0GitHub stars: 2
- Prose CraftCore writing craft skill — sentence-level quality, rhythm, voice, show-don't-tell, sensory detail, pacing, and line-level revision. Use when writing, rewriting, or polishing prose in any genre. Also use when tuning an agent's prose output quality.Votes: 0GitHub stars: 2
- Scaffold CourseScaffold a new 8-week transformational course — creating the database rows, ingestion script, and optional markdown content directory. Use when starting a new course from scratch with a slug and title.Votes: 0GitHub stars: 2
- Story ArchitectNarrative structure skill for fiction and creative non-fiction — plot architecture, character arcs, scene construction, tension/release, theme, and pacing. Use when planning, outlining, diagnosing, or restructuring a narrative. Also use when building agents that generate structured stories.Votes: 0GitHub stars: 2
- Validate CourseValidate a course against the Transformational Course Charter — checking 8-week structure, Four Necessities compliance, section completeness, content quality, and exclusions. Use when reviewing a course before publishing or after authoring to ensure it meets Charter requirements.Votes: 0GitHub stars: 2
- Week AuthorDraft a complete course week — all transformation loop sections in Alan Hirsch's voice, grounded in corpus, following the canonical structure. Combines alan-voice + course-author + corpus retrieval + Trello prompt alignment into a single authoring pass. Use when generating an entire week of course content.Votes: 0GitHub stars: 2
- Writing Agent BuilderArchitect AI agents that write well — system prompt design, voice integration, tool selection, RAG for source material, guardrails for quality, and multi-agent writing pipelines. Use when building any agent whose primary output is prose (stories, articles, copy, dialogue, scripts).Votes: 0GitHub stars: 2
- Add Section TypeCreate a new course section component and register it in the section router. Use when adding a new section type to the course learn experience (e.g., "add a quiz section type" or "add a new section component").Votes: 0GitHub stars: 2
- AnimationAdd scroll animations, micro-interactions, or page transitions to a component using GSAP. Use when a section needs motion design or interactive polish.Votes: 0GitHub stars: 2
- Audit ExperienceAudit the course learn experience for section coverage, sidebar rendering, layout, design token compliance, tenant isolation, accessibility, data flow, and component quality. Use when reviewing course UI code quality or diagnosing learn experience issues. Pass a course slug or "all".Votes: 0GitHub stars: 2