Data & AI skills

Scientific model and eval tuning loop for prompt/skill/system-prompt changes, model configuration, runtime options, and local/Ollama model sizing or environment variables. Use when tuning eval performance, comparing local or remote models, improving tool-use behavior, reducing timeouts/loops, or deciding whether an eval optimization is worth keeping.

The English summary is being prepared. Showing the original description.

Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

The English summary is being prepared. Showing the original description.

Puts the agent into a cautious production mode for live systems: read-only inspection may proceed, but credentials and out-of-scope personal data need permission first, every state-changing action needs explicit per-action approval with its resource risks and rollback stated, and anything unexpected halts work until the user decides. Use when the user invokes `/prod` or `$prod`, or says they are working on production, a live or customer-facing server, a mail server, or a production database, or asks for care on a system where mistakes affect real users.

The English summary is being prepared. Showing the original description.

Deletes files and directories through a wrapper that avoids the usual per- command permission prompt. Use only when content must genuinely be deleted, such as clearing build artifacts or dropping obsolete files during a refactor. Moves, renames, and relocations that preserve content use mv instead.

The English summary is being prepared. Showing the original description.

Generate a Product Requirements Prompt (PRP) from a feature description. Use when starting work on a new feature.

The English summary is being prepared. Showing the original description.

Create Claude Code slash commands, OpenCode command files, Pi prompt templates, and Codex custom prompts that delegate to the right subagent or skill. Use when creating new commands, porting commands across agent platforms, or refactoring existing commands to follow platform conventions.

The English summary is being prepared. Showing the original description.

Adds or changes allowed commands in AI agent permission configs for OpenCode and Claude Code. Use when a command needs adding to an agent's allow list, when permission settings for existing commands need changing, when setting up a new AI tool that requires command permissions, or when the user asks to stop being prompted for a particular command.

The English summary is being prepared. Showing the original description.

Review every Beads issue waiting on a person, one at a time, using the interactive questionnaire UI rather than plain-text prompts. Use when asked to go through blockers, clear the human queue, answer beads waiting on the user, triage `bd human list`, or unblock agent work that needs a decision.

The English summary is being prepared. Showing the original description.

Re-run the analysis pipeline on all runs matching an RQ, reaggregate metrics, and propose findings updates against the fresh data. Trigger when the user says "reanalyze RQ-N", "reanalyse RQ-N", "Runs neu analysieren", or wants to refresh metrics/findings after a pipeline change (analyze-run.sh fix, adapter added, ESLint config).

The English summary is being prepared. Showing the original description.

Use when writing raw SQL — MariaDB/MySQL syntax, parameterization, raw migrations, seeders with `DB::statement`; fires even on a pasted query asking 'why is this slow'.

The English summary is being prepared. Showing the original description.

Pre-spend contradiction gate for AI-video runs: checks every prompt in the batch, blocks on style / character / physics mismatch. Triggers 'validate the prompts', 'check the storyboard'.

The English summary is being prepared. Showing the original description.

Use when reviewing data flows, support macros, refund templates for GDPR/CCPA/HIPAA fit — regime, consent, PII redaction (email, order-id), breach triage. Triggers 'is this GDPR-safe', 'PII redact'.

The English summary is being prepared. Showing the original description.

Refine a Jira/Linear ticket before planning — 'refine ticket', 'tighten AC on PROJ-123', 'ist das Ticket klar?'; rewritten ticket, risks, persona voices, close-prompt.

The English summary is being prepared. Showing the original description.

Reconstruct a free-form prompt into actionable AC + assumptions + confidence band before the engine plans — '/work "…"', 'baue X', 'ist der Prompt klar genug für die Engine?'.

The English summary is being prepared. Showing the original description.

When the user wants a prompt optimized for ChatGPT, Claude, Gemini, or another AI — 'make this prompt better', 'optimize for ChatGPT', 'rewrite my prompt' — even without saying 'optimize'.

The English summary is being prepared. Showing the original description.

Use when designing production-LLM prompts — few-shot, chain-of-thought, system prompts, templates, self-verification — distinct from prompt-optimizer and refine-prompt.

The English summary is being prepared. Showing the original description.

Use when creating and embedding a documentation screenshot — detect and redact sensitive data, human-gate data-bearing shots before ship. Triggers 'screenshot for docs', 'screenshot admin panel'.

The English summary is being prepared. Showing the original description.

Translate an image brief into provider-specific prompt grammar per model. Use when writing or refining an image-generation prompt for Ideogram, Flux, Gemini, GPT Image 2, or Recraft.

The English summary is being prepared. Showing the original description.

Use for deep Laravel project analysis: boot flow, request lifecycle, container usage, Eloquent/data flow, async systems, and Laravel-specific failure patterns.

The English summary is being prepared. Showing the original description.

Use for deep Zend Framework or Laminas project analysis: bootstrap, config merge order, service manager, MVC flow, data layer, and migration-specific risks.

The English summary is being prepared. Showing the original description.

Use when packaging a codebase to a single AI-friendly file for LLM analysis — local or remote, XML/Markdown/JSON, token counting, gitignore filtering, peer-side `repomix` CLI.

The English summary is being prepared. Showing the original description.

Before stating any specific fact about an LLM provider's product — models, pricing, limits, context windows, SDK/API — for OpenAI, Gemini, Claude & others, verify against official docs, not memory.

The English summary is being prepared. Showing the original description.

When turning a locked still + blueprint into a provider-tuned motion prompt — camera, primary + secondary motion, physics, native-audio sync. Triggers 'motion prompt for Veo/Kling/Sora'.

The English summary is being prepared. Showing the original description.

When scoring whether an agent response defended against an injection — treated untrusted content as data, refused role-takeover, ignored fake boundaries. Inverted axis; never auto-gates.

The English summary is being prepared. Showing the original description.