prompt-improvement
Skill4 starsChanged 3 months agoMITView on GitHub
Improve vague, incomplete, ambiguous, risky, or poorly structured prompts into clear executable prompts for AI agents, coding assistants, automations, reports, research, or model-specific workflows. Use when the user asks to rewrite, clarify, optimize, score, translate, structure, or improve a prompt.
In this repository58 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/project-docs-prep/templates/AGENTS.mdAGENTS.md
- skills/project-docs-prep/templates/CLAUDE.mdCLAUDE.md
- deep-planningSkill
- deep-planningSkill
- deprecatedSkill
- architecture-reviewSkill
- code-reviewSkill
- diagnoseSkill
- tddSkill
- ui-design-engineeringSkill
- ux-ui-design-assessmentSkill
- in-progressSkill
- mcp-tool-managementSkill
- skill-managementSkill
- obsidian-canvasSkill
- obsidian-markdownSkill
- obsidian-notion-bridgeSkill
- obsidian-vault-workflowSkill
- boomz-preferencesSkill
- personal-agent-workflowSkill
- personalSkill
- automation-designSkill
- grill-with-docsSkill
- handoffSkill
- inbox-meeting-triageSkill
- markdown-reportSkill
- project-docs-prepSkill
- claim-citation-checkSkill
- daily-news-reportSkill
- github-skill-researchSkill
- project-discoverySkill
- repo-tourSkill
- research-methodologySkill
- seo-website-evaluatorSkill
- thaiSkill
- thai-addressSkill
- thai-customer-serviceSkill
- thai-date-formatSkill
- thai-festival-cardSkill
- thai-government-formSkill
- thai-id-validateSkill
- thai-invoiceSkill
- thai-pdpaSkill
- thai-resumeSkill
- thai-social-captionSkill
- thai-text-processingSkill
- thai-translateSkill
- backtest-expertSkill
- dividend-value-screenerSkill
- drawdown-circuit-breakerSkill
- exposure-coachSkill
- market-breadth-analyzerSkill
- portfolio-managerSkill
- position-sizerSkill
- tradingSkill
- trader-memory-coreSkill
- uptrend-analyzerSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Do not invent requirements.
- Distinctive: line 24
Ask 1 to 3 concise questions only when missing information changes the correct outcome.
- Distinctive: line 29
Add context, requirements, process, output format, quality rules, and language guidance only when useful.
- Distinctive: line 30
Keep identifiers, file paths, commands, schema keys, model IDs, and API names unchanged.
- Distinctive: line 76
Keep reusable model-facing prompt text in English when it improves portability.
- Distinctive: line 77
Do not make prompts longer unless the added structure improves execution.
- Distinctive: line 78
Do not remove explicit constraints.
- Distinctive: line 79
Do not convert uncertainty into fact.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Prompt Improvement
Turn rough intent into a clear prompt without changing what the user asked for.
Core Principle
Preserve explicit intent. Add assumptions only when labeled.
Workflow
- Classify the problem
- Identify whether the prompt is vague, ambiguous, overbroad, missing inputs, missing output format, missing audience, risky, or already good enough.
- Extract intent
- Separate explicit requirements, inferred goals, missing information, assumptions, constraints, and risks.
- Do not invent requirements.
- Decide whether to ask or rewrite
- Ask 1 to 3 concise questions only when missing information changes the correct outcome.
- Proceed with assumptions for low-risk drafting, brainstorming, research, reports, templates, and clear-enough tasks.
- Rewrite
- Make the task executable.
- Add context, requirements, process, output format, quality rules, and language guidance only when useful.
- Keep identifiers, file paths, commands, schema keys, model IDs, and API names unchanged.
- Check fidelity
- Confirm the rewrite preserves the user's request.
- Remove hidden goals.
- Mark assumptions and open questions clearly.
Default Output
## Improved Prompt
```text
[Prompt ready to use]What Changed
Assumptions
Questions
## Reusable Prompt Skeleton
```text
Role:
Task:
Context:
Requirements:
Process:
Output Format:
Quality Rules:
Language And Tone:Rules
- Respond in the user's language.
- Keep reusable model-facing prompt text in English when it improves portability.
- Do not make prompts longer unless the added structure improves execution.
- Do not remove explicit constraints.
- Do not convert uncertainty into fact.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

