Loading...
Loading...
Found 71 Skills
Use when the user asks for a broad codebase review, substantial PR/branch review, architecture audit, tech-debt scan, cleanup assessment, structural sanity check, or design-alignment review. Default workflow: use sub-agents when available unless specifically forbidden; do not require the user to mention sub-agents, council mode, delegation, or parallel review. Focus on cruft, duplication, weak boundaries, missed reuse, lifecycle/concurrency risks, test/roadmap drift, and code aesthetics. Do not use for narrow bug fixes, ordinary small-diff reviews, frontend visual QA, repo-onboarding docs, or OpenAI Agents SDK production-readiness review. Output evidence-backed findings first, then pressure points, design alignment, open questions, and follow-through.
Diagnose a recurring failure (STUCK task, clustered CI error, frequent reverts) by dispatching sub-agents to digest CI logs without bloating main context. Returns one root-cause diagnosis.
Test, validate, and improve agent instructions (CLAUDE.md, system prompts) using sub-agents as experiment subjects. Measures instruction compliance, context decay, and constraint strength. Use for "test prompt", "validate instructions", "prompt effectiveness", "instruction decay", or when designing robust agent behaviors.
Comprehensive code review with parallel specialist sub-agents. Analyzes requirements traceability, code quality, security, performance, accessibility, test coverage, and technical debt. Produces detailed findings and calls /qa-gate for final gate decision.
Adopt multiple expert personas sequentially for complex problem analysis from diverse perspectives. Single-agent only — do NOT spawn sub-agents.
Deep dive into a book. Collect information from six dimensions including chapter structure, background key points, problem impacts, solutions, term index, and further reading through parallel sub-agents, then output a Markdown deep learning note after cross-analysis. Trigger words: Analyze the book XX, Study XX, Reading notes for XX, book analysis.
Use this skill when managing cmux terminal panes, surfaces, and workspaces from Claude Code or any AI agent. Triggers on spawning split panes for sub-agents, sending commands to terminal surfaces, reading screen output, creating/closing workspaces, browser automation via cmux, and any task requiring multi-pane terminal orchestration. Also triggers on "cmux", "split pane", "new-pane", "read-screen", "send command to pane", or subagent-driven development requiring isolated terminal surfaces.
PUA Shot — v2 Original Concentrated Version (449 lines full injection), the complete single-file version before splitting, with the strongest flavor. Zero dependencies and zero references, injects all content into the context at once. Suitable for sub-agent injection, scenarios requiring the strongest PUA effect, or those who don't want progressive loading. Triggers on: '/pua:shot', '/pua shot', 'PUA Concentrate', 'Shot Mode', 'Max PUA', 'Full Injection'. Also great for injecting into sub-agents via Read tool since it's self-contained.
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Use when the user asks to create, generate, or scaffold a SeeFlow flow from a natural-language prompt — "create a flow", "show how X works", "diagram our checkout system", "add a flow to this repo". Orchestrates four sub-agents and bun scripts to write a registered, validated flow under <project>/.seeflow/<slug>/.
Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.