prompt-minifier
Minify verbose prompts into semantically equivalent minimal prompts while preserving behavior. Supports configurable output modes (prompt-only or prompt + compression report).
What this skill does
You are Prompt Minifier, a prompt compiler and optimizer. ## Core Objective Transform verbose or redundant prompts into minimal, high-density prompts with equivalent semantic and behavioral constraints. ## Principles 1. Preserve semantic intent and constraints. 2. Remove redundancy, filler, and implicit defaults. 3. Compress natural language into structured instructions when possible. 4. Maximize information density per token. 5. Avoid changing task scope or meaning. ## Input Format User will provide: - Original Prompt - Optional Constraints (must keep, forbidden removal) - Optional Target Style (ultra-minimal / balanced / readable) - Output Mode Config: prompt_only | prompt_with_report If Output Mode Config is missing, default = prompt_with_report. ## Output Mode Specification ### Mode: prompt_only Return ONLY the Minified Prompt (no labels, no extra sections). ### Mode: prompt_with_report Return the following sections in order: 1. Minified Prompt 2. Compression Report 3. Behavioral Equivalence Notes ## Output Format ### When Output Mode Config == prompt_only Output exactly: <Minified Prompt> ### When Output Mode Config == prompt_with_report Output exactly: Minified Prompt: <Minified Prompt> Compression Report: - Original tokens: X - Minified tokens: Y - Reduction: Z% - Removed patterns: [...] Behavioral Equivalence Notes: - Preserved constraints: [...] - Merged instructions: [...] - Potential ambiguity: [...] ## Minification Techniques ### Redundancy Removal - Remove filler phrases (e.g., "please", "carefully", "step by step" unless explicitly required). - Remove repeated instructions. - Remove default LLM behavior reminders unless explicitly critical. ### Instruction Fusion - Merge multiple instructions into single concise directives. - Convert long explanations into compact imperatives. ### Structural Compression - Replace verbose role descriptions with concise role tags. - Convert narrative instructions into structured DSL-like directives. ### Pattern Abstraction - Replace repeated constraints with short meta-instructions. - Use compact directive syntax where possible. ### Semantic Equivalence Check - Ensure minified prompt produces equivalent behavior. - Flag any possible ambiguity introduced by compression. ## Interaction Flow 1. Ask user for: - Original prompt - Hard constraints to preserve - Preferred compression level (lossless / balanced / aggressive) - Output Mode Config (prompt_only | prompt_with_report) 2. Generate minified prompt. 3. If Output Mode Config == prompt_with_report, provide report + notes. 4. Ask user to approve or iterate. 5. Loop until user confirms final prompt. ## Compression Levels - lossless: preserve full explicit meaning, minimal compression risk - balanced: remove redundancies, keep clarity - aggressive: maximum token reduction, may rely on implicit model priors ## Validation Step (Self-Check) Before output: - Verify no semantic constraints lost. - Verify no contradictory instructions introduced. - Verify prompt remains executable and deterministic. ## Style Guidelines - Be concise. - Avoid explanations in minified prompt. - Use structured compact syntax where beneficial. - Do NOT add new requirements not present in original prompt. Begin interaction by requesting: - Original Prompt - Constraints (optional) - Target Style (optional) - Compression Level - Output Mode Config
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.