to-prompt
Transform code, issues, or context into a detailed prompt/context for another LLM to fix or implement. Use when preparing comprehensive context for external LLM assistance, bug fixes, improvements, or feature implementations. Provides detailed context without implementation suggestions, letting the receiving LLM decide how to implement solutions. Focuses on "what" (problem, requirements, current state) not "how" (implementation approach). Don't use for prompts that already prescribe an implementation, simple one-shot questions, or end-user-facing copy.
What this skill does
# To Prompt Transform code, issues, or context into detailed prompts for another LLM to fix or implement. ## Overview This skill helps create comprehensive, context-rich prompts for external LLM assistance. The goal is to provide all necessary context about the problem, current state, and requirements without prescribing implementation approaches. The receiving LLM decides how to implement the solution based on the context provided. ## Core Principles <critical> - **MUST** explain all context comprehensively and in detail - **MUST** show code snippets only to illustrate current implementation, structure, or problem areas - **MUST NOT** include implementation suggestions, solutions, or "how to fix" instructions - **MUST NOT** show example solutions, code patterns, or step-by-step guides - **MUST** let the receiving LLM decide how to implement the solution based on the context provided - **MUST** focus on "what" (problem, requirements, current state) not "how" (implementation approach) </critical> ## Task Type Guidance ### Bug Fix When transforming a bug fix task, ensure the prompt includes: - **Reproduction steps**: Exact steps to reproduce the bug consistently - **Error messages and logs**: Complete error messages, stack traces, console logs, and any diagnostic output - **Current behavior**: What actually happens when the bug occurs - **Expected behavior**: What should happen instead - **Environment context**: OS, browser, Node version, dependencies versions, configuration - **Recent changes**: What changed recently that might have introduced the bug (git history, recent commits) - **Affected code**: Show the current implementation of code paths involved in the bug - **Related components**: Files, modules, or systems that interact with the buggy code - **Regression tests**: Current tests (if any) and what regression tests should be written to prevent the bug from recurring - **Impact**: Who/what is affected by this bug and severity ### Improvement When transforming an improvement task, ensure the prompt includes: - **Current state**: Detailed description of how things work now - **Current implementation**: Code showing the existing approach - **What needs improvement**: Specific aspects that need enhancement (performance, maintainability, usability, etc.) - **Constraints**: Technical constraints, backward compatibility requirements, or limitations - **Success criteria**: How to measure if the improvement is successful - **Related code**: Files and modules that will be affected - **Dependencies**: External libraries, APIs, or systems involved - **User impact**: How users will benefit from the improvement - **Non-goals**: What should NOT be changed or improved ### Feature When transforming a feature task, ensure the prompt includes: - **Requirements**: Complete functional requirements and user stories - **Current system context**: How the system works now and where the feature fits - **Integration points**: Where the feature connects with existing code - **Data models**: Current data structures and what needs to be added/modified - **API contracts**: Existing APIs and what new endpoints or methods are needed - **User flows**: How users will interact with the feature - **Edge cases**: Boundary conditions and special scenarios to consider - **Constraints**: Technical, business, or design constraints - **Dependencies**: External services, libraries, or systems required - **Testing requirements**: What needs to be tested (unit, integration, E2E) ## What NOT to Include - Implementation suggestions or "how to fix" instructions - Example solutions or code patterns to follow - Step-by-step implementation guides - Prescribed approaches or methodologies - "Before/after" code examples showing solutions ## Usage When asked to transform code, issues, or context into a prompt: 1. **Gather comprehensive context**: Collect all relevant information about the problem, current state, and requirements 2. **Show current code**: Include code snippets to illustrate the current implementation, structure, or problem areas 3. **Describe the problem**: Clearly explain what needs to be fixed, improved, or implemented 4. **Provide context**: Include environment details, related components, dependencies, and constraints 5. **Avoid solutions**: Do not include implementation suggestions, examples, or step-by-step guides 6. **Focus on "what"**: Describe the problem, requirements, and current state, not how to solve it The resulting prompt should be comprehensive enough for another LLM to understand the full context and decide on the best implementation approach independently.
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.