superset-automation
Manage a single Superset automation: edit its prompt in $EDITOR, view recent runs, or trigger a one-off run.
A command is the one you type. It runs exactly when you ask it to, and never before.
9,227 commands across 665 plugins.
Manage a single Superset automation: edit its prompt in $EDITOR, view recent runs, or trigger a one-off run.
Inspect and control the current AO session's target-isolated browser. The desktop app must be open. The agent and user share the same live page, cookies,…
Run local AO health checks. Use this to diagnose setup problems or verify the environment is correctly configured.
Import reads the legacy Agent Orchestrator flat-file store (`~/.agent-orchestrator`) read-only and ports its projects and per-project settings into the rewrite…
Surface and validate Claude's hidden assumptions about the project for user confirmation
Approve synthesis findings and create implementation tickets from discovery
Reference for: Common Ground Load when: Classifying assumptions, determining type or tier
Generate comprehensive PR descriptions following repository templates
Create git commits with user approval and no Claude attribution
Generate a PR description from the current branch changes
Orchestrate parallel implementation through subagents
Generate tests for a completed phase based on UAT criteria and implementation
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
Open interactive code review for current changes or a PR URL; --base <ref> / --diff-type <type> pin the session's opening diff (session-only, git-only)
Audit a file, directory, or whole repo for insecure default configuration: fallback secrets, default credentials, fail-open switches, weak crypto, permissive…
Run a structured discovery flow from problem framing through opportunity mapping and validation planning.
Guide PM to Director to VP/CPO transition planning with role-fit diagnostics and onboarding guidance.
Turn strategy and validated opportunities into a sequenced roadmap with clear tradeoffs.
Ask a codebase question and get a cited, synthesised answer with a confidence rating (costs an LLM call).
Triage card for files, modules, or symbols — layer, hotspot, fix history, freshness (relationships, not source bytes).
Ingest or inspect test-coverage reports — LCOV, Cobertura/Clover, or coverage.py .coverage (builds the per-test map when contexts are present).
Autonomous iteration loop: modify, verify, keep/discard against any metric
Analyze iteration results: trends, plateaus, regressions, recommendations
Strip the signatures that make a UI look AI-generated — flat hierarchy, no focal point, monotone layout, timid palettes, generic tokens, defaulted type,…
Strict, multi-pass craft and visual-hierarchy review of a UI build, with severity scoring and an explicit approval bar. The design counterpart to a deep…
name: sc:agent description: SC Agent — session controller that orchestrates investigation, implementation, and review category: orchestration personas: [] ---
Comprehensive code analysis across quality, security, performance, and architecture domains
Work from the project directory. Once eve is installed, the full docs are bundled with the installed package and match its version exactly. In most installs,…
If the user's intent is not already clear, ask the questions one at a time, use the coding harness's prompt tools when available, and do not guess.
The project at `{{workingDirectory}}` is already scaffolded. Work with the user to complete it, running the commands below from that directory.
Alias for /force-model — pin this session to a specific model via the Weave Router.
Show which external bug-bounty tools are installed on this machine and print install hints for the missing ones. Curated from high-signal repos. Use to…
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot…
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic