workflows

Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.

Personal assistant for email, calendar, tasks, notes, and Google Workspace. Use for: inbox, email, compose, reply, calendar, schedule, events, free time, tasks, todo, notes, daily notes, obsidian, drive, docs, sheets. Wraps: superhuman (email), morgen (calendar/tasks), obsidian (notes), gws (Google Workspace).

Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

Use for EDA, data profiling, and dataset exploration

Systematic hypothesis-driven debugging agent. User = reporter, Claude = investigator. Don't ask what's causing the bug — investigate it yourself. Spawned by dev-debug workflow for each investigation cycle.

Development implementation subagent with automatic linting. Use for dev workflow TDD tasks. Spawned by dev-delegate for each implementation task in PLAN.md.

Verifies plans will achieve goals before execution. Goal-backward analysis. Spawned by dev-plan-reviewer skill. Read-only — cannot modify plans.

Goal-backward verification agent. Verifies phase GOALS were achieved, not just tasks completed. Task completion ≠ goal achievement. A file existing ≠ feature working. Spawned by dev-verify and dev-review skills.

Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Runs /update-codemaps and /update-docs, generates docs/CODEMAPS/*, updates READMEs and guides.

Data analysis subagent with automatic linting. Use for DS workflow implementation tasks. Spawned by ds-delegate for each analysis task in PLAN.md.

Data engineering subagent for pipeline, ETL, and data transformation tasks. Spawned by ds-delegate for engineering-type tasks. Enforces determinism, schema validation, and idempotency.

End-to-end testing specialist using Playwright. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.

Personal knowledge library search. Use for: NotebookLM, Readwise, Google Scholar, Google Workspace. NO web search - only searches user's curated library and academic literature. **IRON LAW: Main chat NEVER calls readwise CLI directly.** Delegate EVERY Readwise call to this agent.

Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.

Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.

Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.

Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.

Test coverage gap auditor. Fills test gaps by generating missing tests. NEVER modifies implementation code — writes tests only or escalates. Spawned by dev-test-gaps skill after gap analysis.

Read-only reviewer that grades prose quality against domain style rules (Volokh/S&W/McCloskey), AI anti-patterns, and prose-quality constraints. Dispatched by writing-review during Level 1 review. Does not fix — reports only.

Read-only reviewer that verifies every citation in a draft traces to references/sources.md and matches the source entry. Adapted from the teaching workflow's exam-source-fidelity-reviewer. Dispatched by writing-review during Level 1 or Level 3 review.

This skill should be used when reviewing AI-generated text, checking for AI writing patterns, detecting undisclosed AI content, or before finalizing any written content. Covers 12 categories of AI writing indicators from Wikipedia's comprehensive guide.

This skill should be used when the user asks to 'iteratively improve', 'audit and fix', 'hill-climb quality', 'grade and improve', 'score and fix', 'audit loop', 'quality loop', or needs structured iterative improvement of an artifact using scored independent audits. Also use when the user invokes a ralph loop for quality improvement rather than task completion.

This skill should be used when the user asks to 'audit footnotes', 'check Bluebook formatting', 'audit citations', 'run footnote audit', 'check my footnotes', 'bluebook audit', or needs systematic Bluebook compliance checking of a law review manuscript.

This skill should be used when the user asks to “cite a case”, “format a citation”, “check Bluebook format”, “cite a statute”, “use id. or supra”, “format footnotes”, “cite a law review article”, or needs Bluebook 21st Edition citation guidance. Covers cases, statutes, secondary sources, signals, and short forms.

Verify academic citations against source PDFs using Gemini File Search API. Use when 'check citations', 'verify cites', 'cite-check', 'run citation review', 'are my citations grounded', 'does source X support claim Y', 'what does source X say about Y', or validating that pandoc citations in markdown drafts are supported by their source documents.

This skill should be used when the user asks to "search Consensus", "consensus search", "find RCT papers", "find clinical papers", "search medical literature via consensus", "find papers on consensus.app", or needs to search Consensus.app for academic/medical literature via the consensus CLI tool.

This skill should be used when the user asks to 'extract patterns from this session', 'save what we learned', 'create a skill from this workflow', 'learn from this conversation', 'capture reusable knowledge', or wants to turn session patterns into reusable skills.

This skill should be used when the user asks to 'set up data analysis for our database', 'extract tribal knowledge about dataset', 'generate data skill', 'document this dataset', 'what does this column mean', 'create data dictionary', 'help me understand this data schema', 'capture domain knowledge about our data', or needs to create a reusable data context skill from dataset expertise.

This skill should be used when the user asks to "deep research", "comprehensive research on", "thorough investigation of", "research report on", "deep dive into", "literature review on", or needs Gemini Deep Research for web-grounded multi-source synthesis beyond what Google Scholar and Consensus provide.

Asks targeted clarification questions based on codebase exploration findings.

This skill should be used when the user asks to 'debug', 'fix bug', 'investigate error', 'why is it broken', 'trace root cause', 'find the bug', or needs systematic debugging with fresh-context subagent iterations and progress-gated escalation.

Internal skill used by dev-implement during Phase 5 of /dev workflow. NOT user-facing - should only be invoked by dev-ralph-loop inside each implementation iteration.

This skill should be used when the user asks to 'design the approach', 'propose architecture', or 'choose between approaches'.

This skill should be used when the user asks to 'explore the codebase', 'map architecture', 'find similar features', or in Phase 2 of /dev workflow.

This skill should be used when the user asks to 'pause work', 'hand off session', 'save progress', 'create handoff', or when context is running low and work needs to continue in a new session.

“This skill should be used when the user asks to 'implement the plan', 'start building', or 'execute the tasks'.”

Internal skill used by dev-design at Phase 4 exit gate. Dispatches a reviewer subagent to verify PLAN.md quality before implementation. NOT user-facing.

This skill should be used when REQUIRED by dev-implement for per-task implementation loops.

This skill should be used when the user asks to 'review the code', 'check implementation quality', or 'run code review'.

Internal skill used by dev-brainstorm at Phase 1 exit gate. Dispatches a reviewer subagent to verify SPEC.md completeness before exploration. NOT user-facing.

This skill should be used when the user asks to 'implement using TDD', 'test-driven development', 'RED-GREEN-REFACTOR', or 'write failing test first'.

This skill should be used when testing web applications with Chrome MCP tools, debugging console errors, monitoring network requests, executing JavaScript in browser, recording GIF test evidence, or when dev-test routes to Chrome-based browser testing.

This skill should be used when the user asks to "test Electron app", "automate Electron desktop app", "debug Electron renderer", "test VS Code extension", "E2E test Electron", or needs Chrome DevTools Protocol automation for Electron applications. Use for renderer process debugging, main process control, native menu automation, and file dialog testing.

This skill should be used when validating test coverage against requirements, after implementation tasks complete (Phase 5.5 of /dev workflow). Invoked automatically by dev-implement before review phase.

This skill should be used when the user asks to "debug macOS app", "test native app", "automate macOS workflow", "test native macOS application", or needs desktop automation for testing macOS applications with Hammerspoon. Use for application launch/control, window management, keyboard/mouse simulation, and visual verification.

This skill should be used when the user asks to "test Linux desktop apps", "automate GTK/Qt applications", "test with ydotool", "test with xdotool", "verify Linux UI interactions", "capture screenshots on Linux", "control D-Bus services", "test Wayland applications", "test X11 applications", or needs Linux desktop E2E testing. Provides comprehensive guidance for Linux automation with ydotool (Wayland), xdotool (X11), grim, and D-Bus.

This skill should be used when testing web applications with Playwright MCP, running headless E2E tests, cross-browser testing, CI/CD test automation, or when dev-test routes to Playwright-based browser testing.

This skill should be used when the user needs to 'debug web applications', 'test UI interactions', 'capture screenshots or network requests', 'test desktop automation', or needs to select between testing tools. Routes to platform-specific E2E testing skills: Chrome MCP for debugging, Playwright for CI/CD, Hammerspoon for macOS, Linux for X11/Wayland.

This skill should be used when the user asks 'what development tools are available', 'list dev plugins', 'what MCP servers can I use', 'enable code intelligence', 'what testing tools exist', or needs to discover development plugins like serena, playwright, or context7. Use this for general development tool discovery; use ds-tools for data science-specific tools.

This skill should be used when the user asks to 'verify completion', 'check that tests pass', 'confirm feature works', or REQUIRED Phase 7 of /dev workflow (final). Enforces fresh runtime evidence before claiming completion.

This skill should be used when the user asks to "create an isolated worktree", "set up worktree for feature", "create a feature branch worktree", or needs workspace isolation with automatic dependency setup and test verification.

This skill should be used when the user asks to 'start a feature', 'build a feature', 'implement a feature', 'develop', 'new feature', or needs the full 7-phase development workflow with TDD enforcement.

Repair DOCX footnote damage from Google Docs or Word Online round-trips, and convert hardcoded supra/infra note references to auto-updating NOTEREF field codes. Use this skill whenever a user's .docx footnotes are broken after editing in a cloud editor — common symptoms include missing footnote separator lines, stripped paragraph styles (pStyle), author bio custom marks (*, †, ‡) replaced with numbers, footnote numbering starting at the wrong number, or TOC separator paragraphs that inflate to fill a whole page. Also use this skill when the user wants to convert 'supra note N' cross-references to NOTEREF fields, fix footnote numbering offsets caused by customMarkFollows bio footnotes, or perform any OOXML-level footnote surgery on a Word document. Even if the user doesn't mention OOXML or XML directly — if they describe footnote formatting problems in a .docx that was edited in Google Docs or Word Online, this is the right skill.

Subagent delegation for data analysis. Dispatches fresh Task agents with output-first verification.

This skill should be used when the user asks to 'fix analysis', 'wrong results', 'notebook error', 'reviewer feedback', 'data changed', 'debug notebook', or needs mid-analysis course-correction for wrong results, notebook errors, or data changes.

Create structured handoff document for DS workflow session pause/resume.

Phase 3 of /ds workflow. Execute analysis tasks with output-first verification.

Internal skill used by ds-plan at Phase 2 exit gate. Dispatches a reviewer subagent to verify PLAN.md quality before implementation. NOT user-facing.

REQUIRED Phase 2 of /ds workflow. Profiles data and creates analysis task breakdown.

This skill should be used when running Phase 4 of the /ds workflow or reviewing data analysis methodology.

Internal skill used by ds-brainstorm at Phase 1 exit gate. Dispatches a reviewer subagent to verify SPEC.md completeness before planning. NOT user-facing.

This skill should be used when the user asks 'what data science tools are available', 'list data analysis plugins', 'what skills work with data', 'enable data science code intelligence', or needs to discover data-specific plugins and skills like wrds, lseg-data, gemini-batch, or data context skills. Use this for data science tool discovery; use dev-tools for general development tool discovery.

Validate analysis outputs against SPEC.md requirements using DQ checks.

This skill should be used when the user asks to 'verify analysis results', 'check reproducibility', 'validate data science output', 'confirm completion', or as Phase 5 of the /ds workflow.

This skill should be used when the user asks to 'start data analysis', 'brainstorm analysis approach', 'plan a data project', 'clarify analysis requirements', or needs the full 5-phase data science workflow with output-first verification.

This skill should be used when the user asks to "use Gemini Batch API", "process documents at scale", "submit a batch job", "upload files to Gemini", or needs large-scale LLM processing. Includes production gotchas and best practices.

This skill should be used when the user asks to "search Google Scholar", "find academic papers", "scholar search", "lookup papers", "find citations", "academic search", "search for papers by author", "find journal articles", "get BibTeX", "cite this paper", "download paper", or needs to search Google Scholar for academic literature via the scholar CLI tool.

Use this skill when the user asks to add news headline cards, 'Last Week Tonight'-style cards, headline slides, news quote slides, or media quote cards to a Typst presentation. Also use when the user wants to modify existing headline cards (add/remove cards, change quotes, swap logos, fix layout issues). Trigger on: 'add a headline', 'news card', 'LWT card', 'headline slide', 'quote card', 'media quote', 'add a quote from [publication]'.

Use when working with jupytext — converting notebooks to/from text formats, syncing paired .ipynb/.py files, multi-kernel projects (Python/R/Stata/SAS), or executing notebooks via papermill.

Use this skill when the user asks to 'generate a docx', 'create the Word file', 'export to docx', 'apply the law review template', 'build the document', 'make a Word version', or wants to convert their law review markdown drafts into a formatted .docx file.

This skill should be used when the user asks to 'look at', 'analyze', 'describe', 'extract from', or 'what's in' media files like PDFs, images, diagrams, screenshots, or charts. Triggers include: 'what does this image show', 'extract the table from this PDF', 'describe this diagram', 'what's in this screenshot', 'analyze this chart', 'read this image', 'get text from this PDF', 'summarize this document', or requests for specific data extraction from visual or document files. Use when analyzed/interpreted content is needed rather than literal file reading (which uses Read tool).

This skill should be used when the user asks to “access LSEG data”, “query Refinitiv”, “get market data from Refinitiv”, “download fundamentals from LSEG”, “access ESG scores”, “convert RIC to ISIN”, “get shareholder activism data”, “query poison pills”, “access corporate governance data”, “find activist campaigns”, “get syndicated loans data”, “query loan deals”, “get infrastructure projects”, “query project finance data”, “get private equity data”, “query VC investments”, “find PE-backed companies”, “get M&A data”, “query mergers and acquisitions”, “find acquisition deals”, “get IPO data”, “query equity offerings”, “find new issues”, “get joint venture data”, “query strategic alliances”, “get news headlines”, “query news data”, “fetch news articles”, or needs the LSEG Data Library Python API.

Use when working with marimo notebooks — creating, editing, debugging, converting from Jupyter, or pairing with a running marimo server.

This skill should be used when the user asks to "create a notebook", "add source to notebook", "generate audio overview", "create podcast", "manage NotebookLM", "nlm", "add PDF to notebook", "list notebooks", "summarize sources", "generate study guide", "create FAQ", "briefing document", "chat with notebook", "generate outline", "research a topic", "deep research", or needs to interact with Google NotebookLM via the nlm CLI tool.

This skill should be used when the user asks to "debug notebook", "inspect notebook outputs", "find notebook error", "read traceback from ipynb", "why did notebook fail", or needs to understand runtime errors in executed Jupyter notebooks from any source (marimo, jupytext, papermill).

Organize Obsidian notes according to clawd's preferences. Use when user asks to "organize notes", "move notes to right folder", "clean up vault", "tidy vault", "file this note", or when creating new notes in the Obsidian vault. Also use when moving, renaming, or categorizing notes, or when the vault root has stray files.

This skill should be used when the user asks to "add paper", "paperpile add", "fetch PDF for", "find and add", "search paperpile", "find in paperpile", "paperpile search", "label paper", "trash paper", "download paper", "paperpile index", "find PDF online", "search google for PDF", "resolve PDF", "fetch PDF for citation", "get full-text for DOI", "resolve cite to PDF", or any request to manage their Paperpile library or resolve a citation to a local PDF.

This skill should be used when the user asks to 'find repeated feedback', 'what do I keep correcting', 'capture this pattern', 'DRY my prompting', 'stop repeating myself', 'turn this into a check', 'automate this correction', or when the same type of feedback has been given 3+ times across sessions.

This skill should be used when the user asks to 'create a plugin', 'scaffold a plugin', 'set up plugin structure', 'new plugin', 'add plugin components', or needs to substantially edit an existing plugin.

Use when the user asks to "render pptx", "show pptx slide", "compare with pptx", "pptx to image", "export pptx slide", "original slide", "show me the original", "what does the pptx look like", or needs to extract a specific PPTX slide's content for visual comparison.

Chat with Readwise highlights using GPT-5.1 RAG. Use when the user wants to ask questions about their reading library, get summaries across documents, or have a conversation about their highlights. Triggers on "ask readwise", "chat about my highlights", "what do my notes say about", "summarize my reading on".

Manage Readwise Reader documents. Use when the user wants to list, save, update, or delete documents in their Reader library. Triggers on "add to reader", "save article", "list my documents", "readwise list", "reader documents".

Clean up stale Readwise Reader documents. Use when the user wants to declutter their reading library, remove old unread articles, or manage Reader inbox. Triggers on "clean up readwise", "prune reader", "delete old articles", "declutter reading list".

Search Readwise highlights. Use when the user wants to find highlights, quotes, notes, or annotations from their reading library. Triggers on "search highlights", "find in readwise", "what did I highlight about", "my notes on".

This skill should be used when the user asks to "search Readwise", "find highlights", "get quotes from my reading", "add highlights to notebook", "search my annotations", "get full document text", "fetch article content", "add tagged documents to notebook", or needs to query their Readwise library.

This skill should be used when the user asks to "find papers", "search academic literature", "find citations", "literature search", "find research on", "what does the literature say about", or any request to search for academic papers across multiple sources.

This skill should be used when the user asks to 'create a skill', 'improve a skill', 'edit a skill', 'add enforcement patterns', 'audit skill enforcement', or needs to substantially create or edit any SKILL.md file.

This skill should be used when the user asks to 'verify sources', 'check citations', 'fact-check footnotes', 'verify quotes', 'source check', 'are my cites real', 'check for hallucinated citations', or needs to verify that citations in a legal/academic manuscript actually exist and are accurate. Also use when the user wants to check that quoted text actually appears in the cited source.

Auto-loaded at session start via SessionStart hook. Teaches skill invocation protocol, tool selection rules (look-at for media, skills for workflows), agent delegation patterns, and enforcement mechanisms. NOT user-triggered - provides foundational skill usage discipline for all sessions.

This skill should be used when the user asks to 'mockup the layout', 'sketch the diagram', 'show me the layout before coding', 'draft the positions', 'quick visual of the layout', 'matplotlib mockup', 'interactive mockup', 'drag and drop layout', 'draw a rough layout', 'prototype the diagram', 'let me arrange the nodes', 'mockup the chart before CeTZ', or when you're about to write a diagram with 4+ nodes or a CeTZ chart and want to confirm the visual with the user first.

This skill should be used when the user asks to 'verify visual output', 'check how it looks', 'render and review', 'visual verify', 'check the slide', 'does this look right', or when any task produces rendered visual output (slides, charts, documents, UI). Starts a render-vision-fix loop using Gemini vision.

This skill should be used when the user asks to 'revise workshop slides', 'fix presentation', 'update slides', 'change slide', 'fix notes', 'workshop feedback', or needs to modify existing workshop presentation slides or speaker notes.

This skill should be used when the user asks to 'create a workshop presentation', 'prepare a workshop talk', 'make slides for a workshop', 'presentation for faculty workshop', 'workshop slides from paper', or needs to create academic workshop presentation slides and speaker notes from a research paper.

This skill should be used when the user asks to "query WRDS", "access Compustat", "get CRSP data", "pull Form 4 insider data", "query ISS compensation", "download SEC EDGAR filings", "get ExecuComp data", "access Capital IQ", "write SAS code for WRDS", "SAS ETL", "SAS hash merge", "SGE array job", "qsas", "qsub SAS", "TAQ data", "trades and quotes", "NBBO", "intraday data", "millisecond data", "closing auction", "VWAP TAQ", "order imbalance", "FJC database", "federal court cases", "securities litigation data", "Form D data", "Reg D data", "private placements data", "private offering data", "Regulation D filings", "IPO data", "SEO data", "new issues", "equity offerings", "SDC new issues", "SDC Platinum", "SDC M&A", "mergers acquisitions data", "M&A database", "FISD", "bond issuances", "144A offerings", "high yield bonds", "investment grade bonds", "Mergent bond data", "fund formation data", "hedge fund registrations", "private equity fund data", "closed-end fund filings", "Form ADV data", "investment adviser registrations", or needs WRDS PostgreSQL query patterns or SAS ETL performance patterns.

Internal skill for expanding section outlines into prose. Called after section outlines are complete.

Internal skill for economics and finance writing. Loaded by /writing when style=econ. Based on McCloskey's "Economical Writing".

Internal skill for Strunk & White writing rules. Loaded by /writing for quick edits or as base layer for domain skills.

Create structured handoff document for writing workflow session pause/resume.

Internal skill for academic legal writing. Loaded by /writing when style=legal. Based on Volokh's "Academic Legal Writing".

Internal skill used by writing-outline at exit gate. Dispatches a reviewer subagent to verify OUTLINE.md quality before drafting. NOT user-facing.

Internal skill for creating detailed section outlines. Called by /writing workflow after PRECIS and master OUTLINE are complete.

Internal skill used by writing-setup at exit gate. Dispatches a reviewer subagent to verify PRECIS.md quality before outlining. NOT user-facing.

Internal skill for hierarchical document review. Called by writing-validate after claim validation passes.

This skill should be used when the user asks to 'revise writing', 'fix review issues', 'polish draft', 'apply review feedback', 'complete writing workflow', or after /writing-review produces REVIEW.md with issues to fix.

Internal skill for creating PRECIS.md, OUTLINE.md, and ACTIVE_WORKFLOW.md. Called after brainstorm sources are gathered.

Validate draft sections cover all PRECIS claims before review.

This skill should be used when the user asks to 'write a paper', 'start a writing project', 'draft an article', 'write about', 'brainstorm writing topics', 'gather sources for a paper', 'what should I write about', or needs the writing workflow entry point for any writing task.

This skill should be used when the user asks to 'test a slide', 'isolate a slide', 'debug a slide', 'preview a single slide', 'test this slide', 'render one slide', or when you need to visually verify a single Typst slide from a presentation in isolation. Provides the exact file setup pattern to avoid access-denied and import errors.

13 hooks across 6 events