prompt-leverage
Strengthen a raw user prompt into an execution-ready instruction set for Codex or another AI agent. Use when the user wants to improve an existing prompt, build a reusable prompting framework, wrap the current request with better structure, add clearer tool rules, or create a hook that upgrades prompts before execution.
What this skill does
# Prompt Leverage If `.khuym/onboarding.json` is missing or stale for the current repo, stop and invoke `khuym:using-khuym` before continuing. Turn the user's current prompt into a stronger working prompt without changing the underlying intent. Preserve the task, fill in missing execution structure, and add only enough scaffolding to improve reliability. ## Workflow 1. Read the raw prompt and identify the real job to be done. 2. Infer the task type: coding, research, writing, analysis, planning, or review. 3. Rebuild the prompt with the framework blocks in `references/framework.md`. 4. Keep the result proportional: do not over-specify a simple task. 5. Return both the improved prompt and a short explanation of what changed when useful. ## Transformation Rules - Preserve the user's objective, constraints, and tone unless they conflict. - Prefer adding missing structure over rewriting everything stylistically. - Add context requirements only when they improve correctness. - Add tool rules only when tool use materially affects correctness. - Add verification and completion criteria for non-trivial tasks. - Keep prompts compact enough to be practical in repeated use. ## Framework Blocks Use these blocks selectively. - `Objective`: state the task and what success looks like. - `Context`: list sources, files, constraints, and unknowns. - `Work Style`: set depth, breadth, care, and first-principles expectations. - `Tool Rules`: state when tools, browsing, or file inspection are required. - `Output Contract`: define structure, formatting, and level of detail. - `Verification`: require checks for correctness, edge cases, and better alternatives. - `Done Criteria`: define when the agent should stop. ## Output Modes Choose one mode based on the user request. - `Inline upgrade`: provide the upgraded prompt only. - `Upgrade + rationale`: provide the prompt plus a brief list of improvements. - `Template extraction`: convert the prompt into a reusable fill-in-the-blank template. - `Hook spec`: explain how to apply the framework automatically before execution. ## Hook Pattern When the user asks for a hook, model it as a pre-processing layer: 1. Accept the current prompt. 2. Classify the task and risk level. 3. Expand the prompt using the framework blocks. 4. Return the upgraded prompt for execution. 5. Optionally keep a diff or summary of injected structure. Use `scripts/augment_prompt.py` when a deterministic first-pass rewrite is helpful. ## Quality Bar Before finalizing, check the upgraded prompt: - still matches the original intent - does not add unnecessary ceremony - includes the right verification level for the task - gives the agent a clear definition of done If the prompt is already strong, say so and make only minimal edits.
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.