Automation
Task automation and scripting
code-quality-workflow
by NickCrew
Use when assessing or improving code quality, maintainability, performance, or security hygiene - provides workflows for analysis, code review, and systematic improvements with validation steps.
multi-llm-consult
by NickCrew
Consult external LLMs (Gemini, OpenAI/Codex, Qwen) for second opinions, alternative plans, independent reviews, or delegated tasks. Use when a user asks for another model's perspective, wants to compare answers, or requests delegating a subtask to Gemini/Codex/Qwen.
feature-implementation
by NickCrew
Use when implementing a feature or multi-file code change - provides structured implementation flow with persona selection, validation, and testing guidance.
evaluator-optimizer
by NickCrew
Iterative refinement workflow for polishing code, documentation, or designs through systematic evaluation and improvement cycles. Use when refining drafts into production-grade quality.
documentation-production
by NickCrew
Use when generating, updating, or organizing documentation (component/API docs, project indexes, diagrams, tutorials, learning paths) - provides structured workflows and references for docs generation, indexing, diagrams, and teaching.
roadmap-prioritization
by proflead
Prioritize roadmap initiatives with tradeoffs. Use when a senior developer needs help ranking projects.
create-hat-collection
by mikeyobrien
Generates new Ralph hat collection presets through guided conversation. Asks clarifying questions, validates against schema constraints, and outputs production-ready YAML files.
evaluate-presets
by mikeyobrien
Use when testing Ralph's hat collection presets, validating preset configurations, or auditing the preset library for bugs and UX issues.
code-task-generator
by mikeyobrien
Generates structured .code-task.md files from descriptions or PDD implementation plans. Auto-detects input type, creates properly formatted tasks with Given-When-Then acceptance criteria.
team-onboarding-guide
by proflead
Create an onboarding guide for new engineers. Use when a senior developer needs structured onboarding materials.
feature-flag-playbook
by proflead
Plan feature flag rollout and cleanup. Use when a mid-level developer needs controlled release guidance.
tech-debt-portfolio
by proflead
Assess and prioritize tech debt items. Use when a senior developer needs an investment plan for debt reduction.
small-script-generator
by proflead
Generate a small helper script for repetitive tasks. Use when a junior developer needs a quick automation snippet.
human-writing
by doodledood
'Research-backed principles for writing prose that avoids AI tells. Apply when writing articles, blog posts, emails, marketing copy, social media, or any prose content. Covers vocabulary, structure, tone, rhythm, and craft techniques that make writing feel authentically human. Not for code, commit messages, or technical documentation.'
background-jobs
by cosmix
Background job processing patterns including job queues, scheduled jobs, worker pools, and retry strategies. Use when implementing async processing, job queues, workers, task queues, async tasks, delayed jobs, recurring jobs, scheduled tasks, ETL pipelines, data processing, ML training jobs, Celery, Bull, Sidekiq, Resque, cron jobs, retry logic, dead letter queues, DLQ, at-least-once delivery, exactly-once delivery, job monitoring, or worker management.
queue-processing-patterns
by proflead
Design safe queue consumers and retries. Use when a mid-level developer needs reliable background processing.
k8s-backup
by rohitg00
Kubernetes backup and restore with Velero. Use when creating backups, restoring applications, managing disaster recovery, or migrating workloads between clusters.
k8s-cost
by rohitg00
Optimize Kubernetes costs through resource right-sizing, unused resource detection, and cluster efficiency analysis. Use for cost optimization, resource analysis, and capacity planning.
Hold my hand
by melodic-software
"Standing posture for multi-step work: only the current phase (exact steps, expected output, common failure, who acts, advancing reply), later ones as a 'Phase 1 of 8' count. Use when: 'hold my hand', 'walk me through this', 'one step at a time', 'one phase at a time', 'don't show me the next step yet', 'guide me through all of this', 'exact steps', 'hand-hold'. Not adhd:shape (shows every step), adhd:clarify (one message), wizard:generate (human-run script), session-flow:workflow (next stage)."
auto-dev-setup
by miles990
設定 Auto-Dev workflow，實現 Human-in-the-Loop 自動化開發
csharp-dotnet
by miles990
C# and .NET development patterns
extract-test-set
by tradingstrategy-ai
Extract raw price dataframe for a test case
check-vault-onchain
by tradingstrategy-ai
Check our feature flagging against an onchain vault
claudish-usage
by MadAppGang
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.