theclauu

Resume from a prior session handoff. Alias for the `session` skill's resume mode (preserves claudefather muscle memory).

Distill the current session's recurring pattern into a reusable skill — runs session introspection, structured intake, and scaffolds a new SKILL.md via writing-skills.

Query, ingest, compile, promote, or lint the data-hive-mind wiki. Default mode (if no keyword) is query.

File a GitHub Issue for discovered follow-up work (not for analyst bug reports — see /file-github-issue). Auto-promotes to Linear on PR merge.

Good morning — sync the hivemind and show today's briefing (Linear / PRs / Notion / Wiki / Team / Handoff).

Create a Linear ticket with dedup + collision detection for fresh intentional work. Always asks whether it should be Work-In-Progress or TODO. Use /theclauu:file-issue for discovered follow-ups instead.

Write an end-of-session handoff. Alias for the `session` skill's handoff mode (preserves claudefather muscle memory).

Scaffold TheClauu's project-level Claude Code config (CLAUDE.md + recommended permissions) into the current directory.

Onboard engineer to TheClauu v0.3+ — cleans legacy claudefather/gstack/superpowers state, configures Linear/Notion/GH auth (1Password or .env), primes the hive-mind cache. Replaces /theclauu-migrate.

SRE agent for Modal infrastructure. Diagnoses production issues with serverless GPU workloads.

Data analysis agent for Neon PostgreSQL. Queries via psql and provides insights.

SRE agent for Railway infrastructure. Diagnoses production issues and analyzes deployments.

Data analysis agent for Snowflake. Queries via snowsql and provides insights.

Spec compliance reviewer. Verifies implementation matches plan requirements exactly -- nothing missing, nothing extra.

SRE agent for Vercel infrastructure. Diagnoses production issues and analyzes deployments.

Analytics engineering agent. Writes, reviews, and tests dbt models against Snowflake.

Code quality reviewer. Evaluates implementation for correctness, clean design, test coverage, and maintainability.

Use for codebase audits across multiple concerns — security, tech-debt, repo-health, docs, design, access paths, data models, frontend perf, cache, and CSO-style security review. Pick the lens that fits the question.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Clean up stale worktrees, merged branches, and dead remote tracking branches. Prompts before deleting.

Use when a session surfaces a repeatable pattern worth codifying — recurring workaround, corrected approach, stabilized workflow, or gotcha that keeps biting. Introspects the session, runs structured intake, and scaffolds a new SKILL.md via writing-skills.

Use when you need to run dbt commands against Snowflake -- build, test, compile, or full-refresh.

Use for UI/visual design work — generating a design system from scratch, exploring design variants, or finalizing a mockup into production HTML/CSS.

Use when a PR has been merged, a development session is ending, or the user asks what else you noticed — surfaces journey-specific observations, systemic patterns, and friction points from the implementation process.

Use to query, ingest, compile, promote, or lint the data-hive-mind wiki (Artemis-xyz/data-hive-mind). Ask questions against durable team knowledge; file discovered learnings; run health checks.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when an analyst wants to file a GitHub issue with a screenshot against a GitHub repo. Expected inputs: a screenshot, a short description, the target repo, and the page URL or app section where the issue was observed (the skill prompts for the URL if missing).

Use when the agent spots follow-up work during an existing PR that is out-of-scope for the current work. Files a GitHub Issue tagged `discovered-by:theclauu`, backlinked to the current PR. Auto-promotes to Linear on PR merge (Slice 3 GH Action).

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use for edit-safety controls — warnings before destructive commands and directory-scoped edit restrictions.

Use when you want to raid a GitHub repo for skills, config patterns, or novel approaches worth adopting into claudefather.

Use when you have a design or development plan document ready to implement against the codebase.

Use when setting up a new project or adding standard Claude Code configuration (CLAUDE.md, CHANGELOG.md, .claude/) to an existing project.

Use when something is broken in production and you need to investigate -- errors, outages, degraded performance, or unexpected behavior.

Batch-fix Dagster/dbt data alerts: triage, deduplicate by DAG lineage, investigate in parallel with team agents, verify locally, PR, and post Slack summary.

Create Linear tickets proactively with dedup + collision detection. For intentional new work the engineer is starting — not for discovered follow-ups (use /theclauu:file-issue for those). Always asks whether the ticket should go to Work-In-Progress or TODO.

Use for Modal serverless operations — deploying, logs, and workspace status. Replaces /modal-deploy, /modal-logs, /modal-status.

Use for Neon PostgreSQL operations — branches, queries, and database info. Replaces /neon-branch, /neon-info, /neon-query.

Use for persistent knowledge — saving/reading cross-session notes and capturing lessons after corrections.

Use when you want to configure macOS or iTerm2 notifications for Claude Code sessions.

Use when you want to run multiple Claude sessions in parallel on different branches using git worktrees.

Use for headless-browser QA work — systematic testing with optional fixes, post-deploy canary monitoring, performance benchmarking, ad-hoc navigation, cookie setup, and autonomous visual crawl.

Use when you want to quickly stage and commit all current changes with a conventional commit message.

Use for Railway operations — deploy, logs, status. Replaces /railway-deploy, /railway-logs, /railway-status.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Review lessons and principles before starting work. Use at session start or before complex tasks.

Use for code review operations — uncommitted changes, a specific PR, or multiple PRs in parallel.

Use when you need to safely refresh or backfill a dbt model in prod without mutating prod first. Builds the model in the user's DEV schema (via clone + incremental OR full-refresh), runs a rigorous dev-vs-prod comparison against the upstream source of truth, then CLONEs dev back to prod on approval. Covers the staleness/frozen-row class of bugs.

Use for session continuity — saving progress, resuming work, labeling a session for /resume.

Use for shipping code — from commit to PR, and optionally through merge and production verification.

Use for Snowflake operations — query via artemis connection, cutover to artemis-python-tools. Replaces /snowflake-query, /snowflake-cutover.

Use when executing implementation plans with independent tasks in the current session

Sync all local branches and worktrees with origin/main. Merges origin/main into active branches, reports conflicts.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when implementing any feature or bugfix, before writing implementation code

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when starting any conversation - establishes how to find and use TheClauu skills, requiring Skill tool invocation before ANY response including clarifying questions

Use for Vercel operations — deploy, logs, status. Replaces /vercel-deploy, /vercel-logs, /vercel-status.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when at a development junction with multiple viable approaches — architecture choices, refactoring strategies, where to put new code, or which pattern to follow. Triggers on 'which approach', 'how should I', 'Option A vs B', or any point where the next step isn't obvious and the wrong choice creates rework.

Use when you have a spec or requirements for a multi-step task, before touching code

Use when creating new skills, editing existing skills, or verifying skills work before deployment

3 hooks across 3 events