Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Langue du texte source : anglais
Menu
Skills dans ce dépôt
SkillsMP a collecté 120 skills depuis nyldn/claude-octopus. Ouvrez un skill pour examiner sa source et ses détails.
nyldn/claude-octopusAffichage de 40 skills collectés sur 120.
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Langue du texte source : anglais
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
Langue du texte source : anglais
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
Langue du texte source : anglais
Craft better prompts using proven optimization techniques — use when your prompt needs refinement
Langue du texte source : anglais
Use when choosing native or multi-LLM handling for init, review, or security requests
Langue du texte source : anglais
Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product
Langue du texte source : anglais
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
Langue du texte source : anglais
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Langue du texte source : anglais
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations
Langue du texte source : anglais
Use when a reviewer, CI bot, or another AI leaves feedback to address
Langue du texte source : anglais
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert
Langue du texte source : anglais
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Langue du texte source : anglais
URL validation and content sanitization for untrusted sources — use when handling external input safely
Langue du texte source : anglais
Package and finalize completed work for delivery — use when a feature is done and ready to ship
Langue du texte source : anglais
Show where you are in the workflow and what to do next — use for progress checks and orientation
Langue du texte source : anglais
Manage tasks with Claude Code native tools — use to track TODOs, delegate work, and monitor progress
Langue du texte source : anglais
Build features with tests-before-code rigor — use for new features needing test coverage
Langue du texte source : anglais
Brainstorm creatively with pattern spotting and paradox hunting — use for ideation and exploration
Langue du texte source : anglais
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Langue du texte source : anglais
Use when about to declare work complete, fixed, passing, or done
Langue du texte source : anglais
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs
Langue du texte source : anglais
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
Langue du texte source : anglais
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning
Langue du texte source : anglais
Configure Claude Octopus — redirects to /octo:setup interactive wizard
Langue du texte source : anglais
Multi-AI requirements scoping using available external providers (Double Diamond Define phase)
Langue du texte source : anglais
Multi-AI implementation using available external providers (Double Diamond Develop phase)
Langue du texte source : anglais
Multi-AI research using available external providers (Double Diamond Discover phase)
Langue du texte source : anglais
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates
Langue du texte source : anglais
NLSpec authoring — use when you need a structured specification from multi-AI research and consensus
Langue du texte source : anglais
System architecture and API design with multi-AI consensus — use for design reviews and new subsystems
Langue du texte source : anglais
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
Langue du texte source : anglais
Thorough research across multiple sources — use for complex topics needing broad synthesis
Langue du texte source : anglais
OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews
Langue du texte source : anglais
Starter: interpret a council run's verdict artifacts — quorum, dissent, cross-lab validity, and what to do next
Langue du texte source : anglais
Starter: frame a decision as a multi-model debate — picks sides, seats providers, and launches /octo:debate with a well-formed motion
Langue du texte source : anglais
Starter: compare model costs for a described task — maps task shape to the cheapest adequate seat and shows the price spread
Langue du texte source : anglais
Starter: one-screen provider health summary — availability, auth method, version drift, and cost posture for every seatable provider
Langue du texte source : anglais
Design UI/UX systems with style guides, palettes, typography, and component specs for new interfaces
Langue du texte source : anglais
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
Langue du texte source : anglais
Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review
Langue du texte source : anglais