intent-executor
Clarifies ambiguous developer instructions by inferring intent and requesting confirmation before executing tasks.
Install
mkdir -p .claude/skills/intent-executor && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14622" && unzip -o skill.zip -d .claude/skills/intent-executor && rm skill.zipInstalls to .claude/skills/intent-executor
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Infer user intent from incomplete or vague prompts in a vibe coding session, then execute after confirmation. Use when the user gives a brief or ambiguous instruction that needs clarification before safe execution, such as "작업을 진행하세요", "다음 단계로 넘어가세요", "제안해준 대로 따르겠습니다", or any task instruction that lacks scope, targets, or success criteria. Do NOT use when the user's instruction is already clear and complete.Key capabilities
- →Infer user intent from vague prompts
- →Gather context from session history and project files
- →Construct a concrete execution plan
- →Present the plan for user confirmation
- →Execute approved parts of the plan
- →Refine understanding based on user rejection
How it works
The skill infers user intent by gathering context from session history and project files, constructs an execution plan, and then seeks user confirmation before proceeding.
Inputs & outputs
When to use intent-executor
- →Clarifying ambiguous coding instructions
- →Safely executing vague task requests
- →Bridging the gap between intent and implementation
About intent-executor
Analyzes project context and history to interpret vague prompts. It creates a concrete plan and requests user confirmation to ensure safe and accurate execution.
Infer user intent from incomplete or vague prompts in a vibe coding session, then execute after confirmation. Use when the user gives a brief or ambiguous instruction that needs clarification before safe execution, such as "작업을 진행하세요", "다음 단계로 넘어가세요", "제안해준 대로 따르겠습니다", or any task instruction that l
When not to use it
- →When the user's instruction is already clear and complete
- →When adding friction to already-clear instructions
Limitations
- →Relies on available session history and project files for context
How it compares
This skill explicitly infers and confirms intent for vague instructions, preventing misinterpretations and ensuring safe execution, unlike directly attempting to fulfill an ambiguous request.
Compared to similar skills
intent-executor side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| intent-executor (this skill) | 0 | 7mo | No flags | Intermediate |
| agentic-workflow-designer | 0 | 3mo | No flags | Intermediate |
| command-development | 16 | 10mo | Review | Intermediate |
| prompt-optimize | 13 | 11mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agentic-workflow-designer
Z3Prover
Conversational skill that interviews users to design new agentic workflows
command-development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
prompt-optimize
YYH211
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
prpm-development
pr-pm
Use when developing PRPM (Prompt Package Manager) - comprehensive knowledge base covering architecture, format conversion, package types, collections, quality standards, testing, and deployment
ai-cost-optimizer
ScientiaCapital
Save 40-70% on AI costs with intelligent multi-LLM routing. Automatically selects the optimal model based on task complexity across 40+ models from 8 providers.
rule-identifier
anthropics
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.