Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Idioma do texto original: inglês
Menu
Skills neste repositório
O SkillsMP coletou 120 skills de nyldn/claude-octopus. Abra uma skill para revisar a origem e os detalhes.
nyldn/claude-octopusMostrando 40 de 120 skills coletadas.
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Idioma do texto original: inglês
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
Idioma do texto original: inglês
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
Idioma do texto original: inglês
Craft better prompts using proven optimization techniques — use when your prompt needs refinement
Idioma do texto original: inglês
Use when choosing native or multi-LLM handling for init, review, or security requests
Idioma do texto original: inglês
Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product
Idioma do texto original: inglês
Interrogate a plan, decision, or design one question at a time until it holds — use to stress-test your own thinking before committing to it
Idioma do texto original: inglês
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Idioma do texto original: inglês
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
Idioma do texto original: inglês
Use when a reviewer, CI bot, or another AI leaves feedback to address
Idioma do texto original: inglês
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert
Idioma do texto original: inglês
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Idioma do texto original: inglês
URL validation and content sanitization for untrusted sources — use when handling external input safely
Idioma do texto original: inglês
Package and finalize completed work for delivery — use when a feature is done and ready to ship
Idioma do texto original: inglês
Show where you are in the workflow and what to do next — use for progress checks and orientation
Idioma do texto original: inglês
Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress
Idioma do texto original: inglês
Build features with tests-before-code rigor — use for new features needing test coverage
Idioma do texto original: inglês
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
Idioma do texto original: inglês
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Idioma do texto original: inglês
Use when about to declare work complete, fixed, passing, or done
Idioma do texto original: inglês
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
Idioma do texto original: inglês
Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces
Idioma do texto original: inglês
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning
Idioma do texto original: inglês
Configure Claude Octopus — redirects to /octo:setup interactive wizard
Idioma do texto original: inglês
Multi-AI requirements scoping using available external providers (Double Diamond Define phase)
Idioma do texto original: inglês
Multi-AI implementation using available external providers (Double Diamond Develop phase)
Idioma do texto original: inglês
Multi-AI research using available external providers (Double Diamond Discover phase)
Idioma do texto original: inglês
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
Idioma do texto original: inglês
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
Idioma do texto original: inglês
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
Idioma do texto original: inglês
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Idioma do texto original: inglês
Thorough research across multiple sources — use for complex topics needing broad synthesis
Idioma do texto original: inglês
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Idioma do texto original: inglês
Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next
Idioma do texto original: inglês
Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion
Idioma do texto original: inglês
Starter: compare model costs for a described task — maps task shape to the cheapest adequate seat and shows the price spread
Idioma do texto original: inglês
Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider
Idioma do texto original: inglês
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Idioma do texto original: inglês
Audit whether a multi-agent setup earns its coordination cost — use before adding an agent, or when a workflow feels slow or agents agree without adding signal
Idioma do texto original: inglês
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Idioma do texto original: inglês