Prompt Improver
Takes a rough prompt and makes it more useful by applying LLM best practices. It pushes you to add verifiability (like test cases or screenshots), specify file paths and constraints, and separate exploration from execution when a task is complex. The workflow is methodical: it classifies your task type and complexity, flags anti-patterns like vague instructions or missing verification commands, then rewrites your prompt with concrete examples and questions about what's missing. Honestly most valuable when you're about to ask Claude to "fix the login bug" and realize you should probably mention the error message and which files are involved. Includes task-specific templates for bugfixes, refactors, research, and ops work.
- skills.sh installs
- 514
- GitHub stars
- 3
- last updated
- Aug 21, 2026
Install
$ npx -y skills add dotneet/claude-code-marketplace --skill prompt-improver --agent claude-codeInstalls into .claude/skills of the current project.
Files
Prompt Improver
Overview
A skill that analyzes and improves prompts based on general LLM/agent best practices. It focuses on verifiability, clear scope, explicit constraints, and context economy so the agent can execute with minimal back-and-forth.
If you are running in Claude Code, also read references/claude.md and apply the additional Claude-specific techniques.
If you are running in Codex CLI, also read references/codex.md and apply the additional Codex-specific techniques.
When the input is a document that instructs an agent (e.g., plan files, AGENTS.md, system instruction docs), treat the document as the improvement target; identify issues and propose concrete improvements, and include a revised draft when helpful.
Workflow
Step 0: Classify Task and Complexity
Classify the task and decide whether an explicit exploration/planning phase should be recommended:
- Task type: bugfix, feature, refactor, research, UI/visual, docs, ops
- Complexity: single-file/small change vs multi-file/uncertain impact
- Risk: data safety, security, compatibility, performance
- Input type: prompt vs agent-instruction document (plan files, AGENTS.md, system instruction docs)
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/dotneet/claude-code-marketplace
- Categories
- Git & Pull Requests, Code Review & Quality, AI & Agent Building, Release Management
- First seen
- Jun 3, 2026
More from dotneet/claude-code-marketplace
All 10Recommended
More Git & Pull Requests
ui-ux-pro-maxgalaxy-dawn/claude-scholarThis skill should be used when the user asks to design or review a UI, create a landing page or dashboard, choose colors or typography, improve accessibility, o514skills.sh installs
typescript-unit-testingbmad-labs/skillsUnit testing for TypeScript/NestJS projects using Jest, @golevelup/ts-jest (DeepMocked/createMock), and in-memory databases, with AAA structure. Use whenever th511skills.sh installs
skill-creatordalestudy/skillsDaleStudy/skills 저장소의 스킬 생성, 수정, 검증 시 사용. 다음 상황에서 활성화: (1) 새 스킬 생성 요청 시, (2) skills/ 디렉토리 내 SKILL.md 파일 수정 시, (3) SKILL.md 변경 검토 또는 리뷰 시, (4) 스킬 frontmatter 또는 509skills.sh installs
debugparcadei/continuous-claude-v3Debug issues by investigating logs, database state, and git history509skills.sh installs
groove-groovebook-publishandreadellacorte/groovePublish a workflow learning to the groovebook shared commons as a GitHub PR. Use after groove-work-compound when a learning is worth sharing.506skills.sh installs
generatorsrshankras/claude-code-apple-skillsCode generator skills that produce production-ready Swift code for common app components. Use when user wants to add logging, analytics, onboarding, review prom505skills.sh installs