prompt-shaping
Propose structured interpretations of underspecified requests. Use when a user's request is vague or incomplete but reasonable assumptions can be made. Rapidly prototypes intent by restating, structuring, and committing to a next action.
What this skill does
# Prompt Shaping Rapid prototyping of user intent through structured proposals. ## When to Apply User request is underspecified but agent can infer plausible intent. ## Process 1. **Restate in natural language** - Articulate what you understand the user wants, making assumptions explicit 2. **Bullet the structure** - Break the restatement into scannable components 3. **Propose an iterative grounding loop** - Define how you will verify the work is complete 4. **State the next action** - Commit to a concrete step if the interpretation is correct ## Grounding Loop (Iterative Testing) Before committing to action, propose how you will verify completion: - **Define success criteria** - What observable outcome proves the request is fulfilled? - **Propose a verification method** - A concrete check the agent can execute (test, command, assertion) - **Commit to iteration** - Run the verification repeatedly until it passes The grounding loop ensures the agent doesn't just claim success—it demonstrates success through executable feedback. Example proposals: > "I'll add the API endpoint, then write a test that calls it and asserts the expected response. I'll iterate until the test passes." > "I'll fix the bug by first writing a failing test that reproduces it, then modifying the code until the test passes." > "I'll refactor the module, running the existing test suite after each change to ensure no regressions." The loop terminates when the verification passes, not when the agent believes the work is done. ## Example > **User**: "I want to add some kind of caching" > > **Agent**: "It sounds like you want to reduce redundant computation or network calls by storing results temporarily. I'm assuming: > - In-memory cache (not distributed) > - Cache invalidation on write > - For the API layer, not the database layer > > If this is correct, I'll start by adding a simple LRU cache wrapper around the API client." ## Context Grounding (Environment Scan) Before proposing, orient to the environment: - Scan for existing patterns that inform reasonable defaults - Note what's present that the proposal should integrate with - Identify constraints the user may not have stated but likely expects
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.