skills.rest
chrissstellee
chrissstelleeCOMMUNITY
Explore all skills by this author →
GitHub

reprompt

Rewrites vague user requests into structured goal-context-task-constraints-success specifications.

Updated Jul 26, 2026
Search Tags:#prompt engineering#spec writing#clarification#reprompt#prompt refinement#requirement structuring
One-click install
npx skills add https://github.com/chrissstellee/Movix --skill reprompt-chrissstellee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reprompt
Source: https://github.com/chrissstellee/Movix/tree/main/.agents/skills/reprompt
Command: npx skills add https://github.com/chrissstellee/Movix --skill reprompt-chrissstellee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Vague or underspecified requests lead to misaligned outputs and wasted iterations. This Skill converts a rough ask into a tight working spec before acting, so the task is executed against a clear, agreed structure rather than guesswork. ## Core Features & Use Cases - Structured Rewriting: Transforms any rough request into a five-part spec covering Goal, Context, Task, Constraints, and Success criteria. - Ambiguity Gating: Asks 1-3 targeted clarifying questions when genuine ambiguity would change the outcome, otherwise proceeds directly. - Personalized Defaults: Reads ~/.stellar/profile.md (honoring STELLAR_HOME) to apply learned preferences like domain, stack, and tone. - Use Case: A user types "reprompt this: make the escrow page better" and receives a sharpened spec defining the actual goal, scope limits, and success criteria before any work begins. ## Quick Start Ask the assistant to reprompt your rough request, for example by saying "reprompt this: add wallet support to the app".

Frequently Asked Questions about reprompt

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I improve a vague prompt before running it?▼

Invoke the reprompt skill with your rough request, and it rewrites the ask into a structured spec covering Goal, Context, Task, Constraints, and Success. If genuine ambiguity exists, it asks 1-3 clarifying questions first, then acts on the sharpened spec.

What structure does a reprompted request follow?▼

The sharpened spec uses five labeled fields: Goal (the outcome actually wanted), Context (assumptions and environment), Task (smallest precise actions), Constraints (scope limits and must-nots), and Success (how completion is verified).

Does reprompt personalize rewrites based on my usage?▼

Yes. If ~/.stellar/profile.md exists, the skill reads it and applies learned defaults such as domain, typical scope, preferred stack, and tone. It honors the STELLAR_HOME environment variable when set.

What is the difference between reprompt and the automatic prompt sharpener?▼

The automatic sharpener runs every turn via the UserPromptSubmit hook with no invocation needed, while reprompt is the manual, on-demand version for explicit heavier rewrites. Disable the automatic one with STELLAR_BUILD_NO_REPROMPT=1.

When should I not use explicit reprompting?▼

Skip it when the request is already clear and specific, since the skill is designed for vague or underspecified asks. For routine turns, the automatic per-turn sharpener handles lightweight refinement without manual invocation.

Related Skills

Explore More Product & Management Skills→
tradertunantetradertunante

interview-me

Ask one focused question at a time to clarify underspecified user intent.

Community
Intermediate
rpamisrpamis
2.9k

executing-plans

Executes written implementation plans task-by-task with verification checkpoints and review gates.

Official
Intermediate
stellar-zkstellar-zk
3

reprompt

Rewrites vague user requests into structured specs with goal, context, task, constraints, and success criteria.

Official
Intermediate
abrahamgreysonabrahamgreyson

ios-fix

Fix iOS app bugs by patching source, rebuilding, redeploying, and verifying on a real device.

Community
Advanced