Results for “prompt optimization”

Optimize existing CLAUDE.md, SKILL.md, agent definitions, and other AI-facing files for Claude comprehension and economy. Scope: optimization of existing content only — not upstream sync, not read-only auditing. Measures baseline metrics, delegates to the ai-doc-optimizer agent with file-type-specific context, runs independent verification via second agent, measures post-optimization metrics, and presents comprehensive before/after report. Supports iterative mode for large targets. Use when improving prompt effectiveness, reducing token waste, or rewriting instructions for LLM consumption. Invoke with /optimize-claude-md <file-or-directory>.

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

Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patterns following Anthropic's official best practices.

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

Analysis criteria, transformation patterns, output format, and validation checklist for refactoring Claude Code agent prompt files. Load this skill when preparing to run the subagent-refactorer agent or when reviewing agent prompt files for structural, model optimization, or instruction quality improvements.

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

Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.

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

Use when the user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence. Generated skills must use a specialized-skill-first workflow, full-feasible local PDF coverage where available, startup-plan-only first replies, target-paper candidate/final image isolation, mandatory image-embedded visual-structure explanation, mandatory non-target concept/modeling example display for abstract visual decisions, saved subtype/style illustration atlases, ChatGPT web Create image / ChatGPT Images 2.0 rendering, Codex $imagegen-first rendering, sample-image transfer rules, all-step/current-position state footers, and a mandatory first-round diverse candidate board followed by P6b/P6c paper-local best-practice optimization before final prompt construction.

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

Detects seven structural anti-patterns in Claude Projects that cause unpredictable output, ignored instructions, and degraded quality. Diagnoses Monolith, Orphan File, Echo Chamber, Phantom Conversation, Kitchen Sink, Misaligned Hierarchy, and Blurred Layers. Use when user says "what's wrong with my project," "Claude ignores my instructions," "diagnose my project," "why is output inconsistent," "review my project setup." Also trigger on symptom-phrased: "Claude doesn't follow my rules," "my instructions keep getting overridden," "my Project isn't behaving as designed." Use alongside rootnode-project-audit if available for deeper structural analysis. Activate whenever the user describes symptoms of unreliable, inconsistent, or degraded Claude Project output, even if they do not name a specific pattern. Do NOT use when the user's primary request is Memory-layer rebalancing (use rootnode-memory-optimization if available) or scoring a single prompt (use rootnode-prompt-validation if available).

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

Use when optimizing token usage, KV cache efficiency, or context window management for LLM agents. Keywords: context optimization, KV cache, prompt caching, token budget, semantic pruning, lost-in-the-middle.

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

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

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

Use when Agentforce run costs are climbing, you need to forecast scale, or you want to reduce tokens per conversation without hurting quality. Covers topic (now subagent) design impact on cost, prompt/template reuse, grounding size discipline, caching, and model-tier selection. Triggers: 'agentforce cost', 'tokens per conversation too high', 'reduce agentforce runs spend', 'forecast agentforce scale cost', 'einstein trust layer tokens'. NOT for capping spend per user with a budget gate and fallback — use agentforce/agent-rate-limit-strategy. NOT for org-wide model-tier and BYOLLM platform strategy — use architect/ai-platform-architecture.

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

Declarative programming framework for optimizing LLM prompts through compilation and automatic tuning

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

Use when user says "simmer this", "refine this", "hone this", "iterate on this", or asks to improve a specific artifact over multiple rounds. Runs an iterative refinement loop with investigation-first judges that read the code, understand the problem, and propose evidence-based improvements. Auto-selects single judge or multi-judge board based on complexity. Works on any artifact type: documents, prompts, specs, emails, creative writing, API designs, pipelines, codebases. Supports multi-file workspace targets, runnable evaluators, and open-ended optimization (model selection, pipeline topology, prompt tuning).

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

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.

Expert en ingénierie du contexte IA (compression de prompts, chunking, gestion tokens, optimisation fenêtre)

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

Expert en optimisation des coûts d'agents IA (sélection modèle, caching, compression prompts, budgeting tokens)

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

When the user wants to improve their app's onboarding experience, increase activation rate, reduce Day 1 drop-off, or optimize the first-run flow. Use when the user mentions "onboarding", "first-run", "activation", "tutorial", "day 1 retention", "new user flow", "permission prompts", "sign-up conversion", "onboarding funnel", or "users dropping off early". For overall retention strategy, see retention-optimization. For paywall placement, see monetization-strategy.

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

Benchmark stellar-build skills to measure quality and the lift from optimization. Use when the user says "bench my skills", "bench-skills", "benchmark skills", "did optimization help", "measure my skills", "stellar-loop bench", or wants to quantify whether /optimize-skills actually improved things. Held-out eval prompts scored by an LLM judge, reproducible with fixed seeds. Fully local.

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

Plan, evaluate, and adopt agent infrastructure for a named workload. Use for agent runtime/framework selection, agent evaluation or observability plans, memory and tool boundaries, infrastructure cost controls, and organizational adoption. Covers workload-first comparison, risk and recovery planning, held-out evaluation, cost accounting, and staged rollout. Not a vendor ranking or a production certification. NOT for implementing a specific agent behavior (agentic-patterns), building a specific agent (ai-engineer), prompt optimization (prompt-engineer), or conventional ETL workflow design (jury_rig-architect).

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

Comprehensive Power BI DAX formula optimization prompt for improving performance, readability, and maintainability of DAX calculations.

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

Evolve prompts/regex/SQL/code with Imbue's evolution loop.

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

Reduces LLM costs and improves response times through caching, model selection, batching, and prompt optimization. Provides cost breakdowns, latency hotspots, and configuration recommendations. Use for "cost reduction", "performance optimization", "latency improvement", or "efficiency".

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

Repeat candidate searches and comparisons while keeping an append-only decision log. Record evidence, compare results with earlier winners, and check replay, freshness, and approval requirements before moving to live trading or production actions.

• Comparing candidates through repeated trials
• Keeping an evidence trail for decisions
• Reassessing earlier winners with fresh information

Review a Power BI data model’s tables, relationships, storage choices, performance, maintainability, and security. Use the findings to identify design issues and build a prioritized improvement plan with concrete recommendations and implementation guidance.

• Reviewing a Power BI model before production release
• Investigating slow queries and oversized models
• Checking table relationships and storage choices

Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.

• Setting up an LLM server on NVIDIA GPUs
• Configuring FP8 or INT4 quantization
• Distributing large models across multiple GPUs

Plan and carry out research by refining questions, improving searches, evaluating sources, and checking claims across independent references. Turn findings into cited reports that explain the evidence, conflicting views, confidence levels, and remaining gaps.

• Comparing options using multiple sources
• Checking source reliability and conflicting claims
• Writing research reports with citations