docs: refine README for clarity, tone, and structure

- Rewrote all AI-sounding language into plain, direct prose
- Removed all em-dashes throughout the document
- Added emoji to all section headings for scannability
- Wrapped tool profiles, templates, and all 35 pattern tables in collapsible <details> dropdowns to reduce visual noise on first load
- Split the 35 patterns section into 6 labeled dropdowns by category (Task, Context, Format, Scope, Reasoning, Agentic)
- Renamed full examples to reflect their actual content (Image AI, Code AI) instead of generic numbering
- Tightened the hero tagline and intro copy
- Minor formatting fixes across installation and usage sections
- Added Start-History chart (Just to look more cool)
This commit is contained in:
Abu Bakr
2026-03-17 22:02:04 +05:00
committed by GitHub
parent 30d9011cc0
commit 542db5b402
+49 -21
View File
@@ -210,7 +210,7 @@ Prompt Master includes specific profiles for 20+ tools. For anything not on the
<details>
<summary><h3> View all 20+ tool profiles </h3></summary>
<summary><h3> Click to view all 20+ tool profiles </h3></summary>
| Tool | Category | What Prompt Master Fixes |
|------|----------|--------------------------|
@@ -237,10 +237,13 @@ Prompt Master includes specific profiles for 20+ tools. For anything not on the
---
## 12 Prompt Templates Auto-Selected
## 📐 12 Prompt Templates (Auto-Selected)
Prompt Master picks the right architecture for every task automatically and routes silently — you never see the framework name, just the prompt.
<details>
<summary><h3> Click to view all 12 templates</h3></summary>
| Template | Best For |
|----------|----------|
| **RTF** (Role, Task, Format) | Fast one-shot tasks |
@@ -256,11 +259,13 @@ Prompt Master picks the right architecture for every task automatically and rout
| **ComfyUI** | Node-based image workflows — positive/negative split per checkpoint |
| **Prompt Decompiler** | Breaking down, adapting, simplifying, or splitting existing prompts |
</details>
---
## 5 Safe Techniques Applied When Needed
## 🛡️ 5 Safe Techniques, Applied When Needed
Prompt Master only applies techniques with reliable, bounded effects. Fabrication-prone techniques like Tree of Thought, Graph of Thought, Universal Self-Consistency, and prompt chaining are explicitly excluded.
Prompt Master only uses techniques with reliable, bounded effects. Methods known to produce hallucinations or unpredictable output (Tree of Thought, Graph of Thought, Universal Self-Consistency, prompt chaining) are explicitly excluded.
| Technique | What It Does |
|-----------|-------------|
@@ -272,9 +277,10 @@ Prompt Master only applies techniques with reliable, bounded effects. Fabricatio
---
## 35 Credit-Killing Patterns Detected (with Before/After Examples)
## 🚫 35 Credit-Killing Patterns Detected (with Before/After Examples)
### Task Patterns
<details>
<summary><h3> Task Patterns (7)</h3></summary>
| # | Pattern | Before | After |
|---|---------|--------|-------|
@@ -284,7 +290,12 @@ Prompt Master only applies techniques with reliable, bounded effects. Fabricatio
| 4 | **Over-permissive agent** | "do whatever it takes" | Explicit allowed + forbidden actions list |
| 5 | **Emotional task description** | "it's totally broken, fix everything" | "Throws uncaught TypeError on line 43 when `user` is null" |
| 6 | **Build-the-whole-thing** | "build my entire app" | Break into Prompt 1 (scaffold), Prompt 2 (feature), Prompt 3 (polish) |
| 7 | **Implicit reference** | "now add the other thing we discussed" | Always restate the full task never reference "the thing we discussed" |
| 7 | **Implicit reference** | "now add the other thing we discussed" | Always restate the full task, never reference "the thing we discussed" |
</details>
<details>
<summary><h3> Context Patterns (6)</h3></summary>
### Context Patterns
@@ -297,7 +308,11 @@ Prompt Master only applies techniques with reliable, bounded effects. Fabricatio
| 12 | **Undefined audience** | "write something for users" | "Non-technical B2B buyers, no coding knowledge, decision-maker level" |
| 13 | **No mention of prior failures** | (blank) | "I already tried X and it failed because Y. Do not suggest X." |
### Format Patterns
</details>
<details>
<summary><h3> Format Patterns (6)</h3></summary>
| # | Pattern | Before | After |
|---|---------|--------|-------|
@@ -308,28 +323,39 @@ Prompt Master only applies techniques with reliable, bounded effects. Fabricatio
| 18 | **No negative prompts (image AI)** | "a portrait of a woman" | Add: "no watermark, no blur, no extra fingers, no distortion, no text" |
| 19 | **Prose prompt for Midjourney** | Full descriptive sentence | "subject, style, mood, lighting, --ar 16:9 --v 6" |
### Scope Patterns
</details>
<details>
<summary><h3> Scope Patterns (6)</h3></summary>
| # | Pattern | Before | After |
|---|---------|--------|-------|
| 20 | **No scope boundary** | "fix my app" | "Fix only login form validation in `src/auth.js`. Touch nothing else." |
| 21 | **No stack constraints** | "build a React component" | "React 18, TypeScript strict, no external libraries, Tailwind only" |
| 22 | **No stop condition for agents** | "build the whole feature" | Explicit stop conditions + checkpoint after each step |
| 22 | **No stop condition for agents** | "build the whole feature" | Explicit stop conditions + checkpoint after each step |
| 23 | **No file path for IDE AI** | "update the login function" | "Update `handleLogin()` in `src/pages/Login.tsx` only" |
| 24 | **Wrong template for tool** | GPT-style prose used in Cursor | Adapted to File-Scope Template with path + scope |
| 25 | **Pasting entire codebase** | Full repo context every prompt | Scoped to relevant function and file only |
### Reasoning Patterns
</details>
<details>
<summary><h3> Reasoning Patterns (5)</h3></summary>
| # | Pattern | Before | After |
|---|---------|--------|-------|
| 26 | **No CoT for logic task** | "which approach is better?" | "Think through both approaches step by step before recommending" |
| 27 | **Adding CoT to reasoning models** | "think step by step" sent to o1/o3 | Removed reasoning models think internally, CoT instructions degrade output |
| 27 | **Adding CoT to reasoning models** | "think step by step" sent to o1/o3 | Removed, reasoning models think internally and CoT instructions degrade output |
| 28 | **No self-check on complex output** | (nothing) | "Before finishing, verify output against the constraints above" |
| 29 | **Expecting inter-session memory** | "you already know my project" | Always re-provide the Memory Block |
| 30 | **Contradicting prior decisions** | New prompt ignores earlier architecture | Memory Block with all established facts |
### Agentic Patterns
</details>
<details>
<summary><h3> Agentic Patterns (5)</h3></summary>
| # | Pattern | Before | After |
|---|---------|--------|-------|
@@ -339,11 +365,13 @@ Prompt Master only applies techniques with reliable, bounded effects. Fabricatio
| 34 | **Unlocked filesystem** | No file restrictions | "Only edit files inside `src/`. Do not touch `package.json`, `.env`, or any config file." |
| 35 | **No human review trigger** | Agent decides everything | "Stop and ask before: deleting any file, adding any dependency, or touching the database schema" |
</details>
---
## Memory Block System
## 🧠 Memory Block System
When your conversation has history, Prompt Master automatically extracts prior decisions and prepends a Memory Block so the AI never contradicts earlier work:
When your conversation has history, Prompt Master pulls out prior decisions and prepends a Memory Block so the AI never contradicts earlier work:
```
## Memory (Carry Forward from Previous Context)
@@ -354,16 +382,16 @@ When your conversation has history, Prompt Master automatically extracts prior d
- Architecture: no Redux, context API only
```
This solves the #1 cause of wasted re-prompts in long sessions.
This is the single biggest fix for long sessions. Most wasted re-prompts come from the AI forgetting what you already decided.
---
## 🔗 References
## 📚 References
- [Anthropic Prompt Engineering Guide](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview) Primary source for Claude-specific patterns
- [OpenAI Prompt Engineering Guide](https://platform.openai.com/docs/guides/prompt-engineering) GPT-4o best practices
- [Cursor Documentation](https://docs.cursor.com) IDE-specific context patterns
- [Midjourney Prompt Reference](https://docs.midjourney.com/docs/prompts) Image AI parameter guide
- [Anthropic Prompt Engineering Guide](https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview): Primary source for Claude-specific patterns
- [OpenAI Prompt Engineering Guide](https://platform.openai.com/docs/guides/prompt-engineering): GPT-4o best practices
- [Cursor Documentation](https://docs.cursor.com): IDE-specific context patterns
- [Midjourney Prompt Reference](https://docs.midjourney.com/docs/prompts): Image AI parameter guide
---