Explore skills

Take a screenshot (full screen, region, or monitor) and save to /tmp/claude-screenshots/ for use with @ in prompts. Usage: /cshot [full|region|monitor [N]] [delay_seconds]

Scans a project for agent-harness gaps and outputs a prioritised list with paste-ready config snippets to close them. Covers hooks, CI, pre-commit, instruction file quality, init.sh, and session discipline. Use when starting a new project, auditing an existing harness, writing or reviewing CLAUDE.md/AGENTS.md, setting up CI gates, beginning multi-day autonomous work, or when user says "set up harn

Review the current project state and continuously guide the project toward better Harness and Compound Engineering practices. Identify: - behaviors that align with best practices - anti-patterns or weak workflows - missing operational discipline, evals, harnesses, or feedback loops Then recommend the next highest-leverage step, including: - what to do next - why it matters now - what commands, too

Consolidated performance dashboard across Meta, Google, and LinkedIn Ads. Aggregates spend, clicks, conversions, CTR, CPC, CPA into a single HTML report with spend/conversion share donut charts. Triggers on prompts about overall performance, cross-channel reports, or "how are we doing this month".

Bulk edit LinkedIn campaigns from CSV — status, daily budget, unit cost (bid). Preview before apply, confirmation required. Triggers on prompts about mass campaign edits, pausing many campaigns at once, or budget reallocations.

🤖 My Claude Code config!

Iteratively improve a context document.

🤖 My Claude Code config!

🤖 My Claude Code config!

Add, update, or delete tests for changes in the current commit.

Manage Arthur's personal productivity system through AI-first task capture, Todoist MCP task updates, lightweight Google Calendar/time-block planning, active-seven triage, emoji/category conventions, and cross-device constraints. Use when Arthur asks to manage personal tasks, life admin, reminders, Todoist, calendar planning, weekly/daily triage, backlog anxiety, or the evolving personal operating

Run the feature-advisor query-time subagent over the full ontology to produce a structured impact assessment for a proposed feature or change. Maintainer asks "I want to add X — what's affected?" The agent reads sidecars + concepts.yaml + implicit-adrs.md + refactoring-scopes.md + doc-gaps.md + test-map.yaml + existing adrs/ + live ODD docs (via WebFetch), and emits `lineage/{repo}/feature-walks/{