sartoris-digital
33 verified skills
cancel
Cancel active execution mode (ralph, autopilot) and clean up state
tools
autopilot
Full autonomous execution from idea to working code — expand, plan, implement, QA, validate
development
deep-interview
Socratic deep interview with mathematical ambiguity scoring before planning and execution
tools
code-review
Use when performing a comprehensive multi-agent code review of a pull request or branch diff
development
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
testing
plan
Unified planning entry point — detects broad vs. specific requests and routes to appropriate planning workflow
testing
receiving-code-review
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
development
simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found
development
troubleshooting
Use when diagnosing bugs using multi-agent parallel investigation
data-ai
deepsearch
Thorough codebase search using structured search strategy via scout agent
development
dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
testing
brainstorming
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.
development
deepinit
Deep codebase initialization — create hierarchical AGENTS.md documentation across the entire project
development
ecomode
Token-efficient model routing modifier — shifts tier preferences down to save costs
testing
external-context
Fetch external documentation and references — decompose query into facets, search in parallel
documentation
security-review
Use when performing a security-focused review of code changes to identify exploitable vulnerabilities
development
finishing-a-development-branch
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
development
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
development
ralplan
Consensus planning with adversarial review — planner, architect, and critic iterate until approved
tools
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
tools
ralph
PRD-driven persistence loop — keep working until all user stories pass with architect verification
tools
learner
Extract a hard-won debugging insight from the current conversation into a reusable skill file
development
ultraqa
Autonomous QA cycling - verify, diagnose, fix, repeat until goal met (max 5 cycles)
tools
ultrawork
Parallel execution engine — fire multiple independent agents simultaneously with smart model tier routing
data-ai
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
tools
trace
Evidence-driven causal tracing — competing hypotheses, disconfirmation, discriminating probe
testing
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
testing
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
development
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
development
verification-before-completion
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
data-ai
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
development
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
development
ai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
development