Recently Written · git

ai-config

One canonical AI agent config (rules, skills, MCP servers) rendered into Claude Code, Codex, Copilot CLI and Antigravity by acsync

git clone https://github.com/equwal/ai-config

Log | Files | Refs


skills/impactful-writing/SKILL.md (10955 bytes)

1 ---
2 name: impactful-writing
3 description: Write clear, emotionally resonant, and well-structured content that readers remember and act upon. Use when writing or editing any text - Twitter posts, articles, documentation, emails, comments, updates - for maximum clarity, engagement, and impact.
4 metadata:
5   version: "0.1.4"
6   categories: "creative, knowledge"
7   topics: "writing, editing, storytelling, clarity, copywriting"
8   openclaw:
9     homepage: https://github.com/tenequm/skills/tree/main/skills/impactful-writing
10     emoji: "✍️"
11 ---
12 
13 # Impactful Writing
14 
15 ## Overview
16 
17 Transform any content into clear, memorable, and actionable text using research-backed principles that work across all platforms and contexts. This skill synthesizes 50+ years of readability research, neuroscience of memory, and platform engagement studies into practical techniques.
18 
19 **Core insight**: The same psychological principles drive engagement everywhere - clarity reduces cognitive load, specificity creates memory, and structure enables scanning. Master these universal patterns and apply them to any writing context.
20 
21 ## When to Use This Skill
22 
23 - Writing or editing Twitter/X posts, threads, or social content
24 - Creating blog posts, Medium articles, or long-form content
25 - Drafting documentation, README files, or technical writing
26 - Composing emails, Slack messages, or professional communication
27 - Writing GitHub comments, PR descriptions, or code reviews
28 - Creating update messages, announcements, or change logs
29 - Editing any existing content for clarity and impact
30 
31 ## Universal Writing Principles
32 
33 These evidence-based principles work across all platforms and contexts.
34 
35 ### 1. Clarity Through Simplicity
36 
37 **Sentence length determines comprehension:**
38 - 14 words: 90%+ reader comprehension
39 - 25 words: Difficulty begins
40 - 43 words: <10% comprehension
41 
42 **Target: 15-20 words average, 25 words maximum per sentence.**
43 
44 **Word choice matters:**
45 - Simple words process 76% faster than jargon
46 - Active voice processes 15-20% faster than passive
47 - Concrete beats abstract (activates sensory brain regions)
48 
49 ### 2. Structure for Scanning
50 
51 **79% of readers scan rather than read.** Design for this reality:
52 
53 - Front-load key information (inverted pyramid)
54 - Use descriptive headings every 3-4 paragraphs
55 - Keep paragraphs to 3-5 sentences maximum
56 - Use bullet points for 3+ related items
57 - Optimal line length: 50-75 characters
58 
59 ### 3. Emotional Resonance
60 
61 **Stories trigger oxytocin release**, enabling empathy and memory formation:
62 
63 - Open with a hook (question, surprising fact, brief story)
64 - Use sensory, concrete language
65 - Create curiosity gaps (specific questions readers want answered)
66 - Close with memorable takeaways (recency effect)
67 
68 ### 4. Specificity Over Abstraction
69 
70 Specific details outperform vague statements:
71 
72 - "45% increase" beats "significant growth"
73 - "in 5 minutes" beats "quickly"
74 - "10 ways" beats "several ways"
75 - Concrete examples beat abstract explanations
76 
77 ## Quick Start Workflow
78 
79 ### Writing New Content
80 
81 1. **Define the core message** in one sentence
82 2. **Open with a hook** (question, fact, or story)
83 3. **Structure with headings** for scannability
84 4. **Use short sentences** (15-20 words average)
85 5. **Close with clear takeaway** or call-to-action
86 
87 ### Editing Existing Content
88 
89 1. **Read aloud** to identify awkward passages
90 2. **Cut word count** by 10-30% without losing meaning
91 3. **Convert passive to active** voice
92 4. **Replace jargon** with simple words
93 5. **Add structure** (headings, bullets, white space)
94 
95 ## Platform-Specific Guidance
96 
97 ### Twitter/X Posts
98 
99 - **Optimal length**: 71-100 characters for engagement
100 - **Hook in first line**: Must capture in 3 seconds
101 - **Use numbers**: "10 lessons" outperforms "lessons learned"
102 - **Thread structure**: Each tweet must stand alone AND connect
103 
104 Example transformation:
105 ```
106 Before: "I learned a lot from this experience and want to share some thoughts"
107 After: "5 hard lessons from shipping 10,000 lines of code in 48 hours:"
108 ```
109 
110 ### Blog Posts / Articles
111 
112 - **Optimal reading time**: 7-10 minutes
113 - **Headings**: Every 300-500 words
114 - **First paragraph**: Must deliver the promise
115 - **Conclusion**: Summarize key points, provide clear next step
116 
117 ### Technical Documentation
118 
119 - **Lead with the goal**: What will the reader accomplish?
120 - **Show, don't tell**: Working code examples beat explanations
121 - **Progressive disclosure**: Basic → Advanced
122 - **Consistent terminology**: One term per concept
123 
124 ### Professional Communication (Email/Slack)
125 
126 - **Subject lines**: Specific over clever ("Q4 Report Draft" > "Quick update")
127 - **One topic per message**: Increases response rate
128 - **Front-load action items**: Don't bury the ask
129 - **Keep to half-page maximum**: Longer = lower read rate
130 
131 ### GitHub Comments / PR Descriptions
132 
133 - **Start with context**: What problem does this solve?
134 - **Use bullet lists**: For changes, decisions, trade-offs
135 - **Include "why"**: Reasoning > description
136 - **Be direct but kind**: Critique code, not people
137 
138 ## The Revision Checklist
139 
140 Use this checklist for any content revision:
141 
142 ```
143 Clarity Pass:
144 - [ ] Average sentence length < 20 words
145 - [ ] No sentence > 30 words
146 - [ ] Passive voice < 10% of sentences
147 - [ ] Jargon replaced with simple alternatives
148 
149 Structure Pass:
150 - [ ] Opening hook captures attention
151 - [ ] Key message in first paragraph
152 - [ ] Headings every 3-4 paragraphs (for longer content)
153 - [ ] Bullet points for lists of 3+ items
154 - [ ] Clear call-to-action or takeaway at end
155 
156 Conciseness Pass:
157 - [ ] Removed "very," "really," "quite," "just"
158 - [ ] Replaced multi-word phrases with single words
159 - [ ] Deleted redundant explanations
160 - [ ] Cut 10-30% from original word count
161 ```
162 
163 ## Word Reduction Patterns
164 
165 Common phrases to simplify:
166 
167 | Wordy | Concise |
168 |-------|---------|
169 | due to the fact that | because |
170 | in order to | to |
171 | at this point in time | now |
172 | in the event that | if |
173 | with regard to | about |
174 | a large number of | many |
175 | in spite of the fact that | although |
176 | for the purpose of | to |
177 
178 Complex words to simplify:
179 
180 | Complex | Simple |
181 |---------|--------|
182 | utilize | use |
183 | commence | start |
184 | terminate | end |
185 | demonstrate | show |
186 | facilitate | help |
187 | subsequent | later |
188 | approximately | about |
189 | endeavor | try |
190 
191 ## Hook Patterns That Work
192 
193 ### Question Hook
194 Opens with a question the reader wants answered:
195 ```
196 "What if everything you knew about productivity was wrong?"
197 ```
198 
199 ### Statistic Hook
200 Opens with surprising data:
201 ```
202 "90% of visitors who read your headline also read your CTA - yet most writers spend 10x more time on body copy."
203 ```
204 
205 ### Story Hook
206 Opens with a brief narrative:
207 ```
208 "At 3 AM, with the deploy failing for the sixth time, I realized the bug wasn't in the code."
209 ```
210 
211 ### Declarative Hook
212 Opens with a bold statement:
213 ```
214 "Most advice about writing is wrong. Here's what actually works."
215 ```
216 
217 ### Contradiction Hook
218 Challenges an assumption:
219 ```
220 "The best writers don't write more. They delete more."
221 ```
222 
223 ## Memory and Impact Principles
224 
225 Content that sticks follows these patterns:
226 
227 ### Serial Position Effect
228 - **First items**: ~70% recall (primacy)
229 - **Last items**: ~60% recall (recency)
230 - **Middle items**: ~40% recall
231 
232 **Implication**: Put most important points first and last.
233 
234 ### Prediction Errors
235 Violated expectations create distinctive memories:
236 ```
237 Before: "The meeting went exactly as planned."
238 After: "The meeting started with our CEO apologizing. In 15 years, I'd never seen that."
239 ```
240 
241 ### Sensory Language
242 Activates multiple brain regions:
243 ```
244 Before: "The code was messy."
245 After: "The code sprawled like tangled Christmas lights - one pull and everything breaks."
246 ```
247 
248 ## Common Anti-Patterns
249 
250 ### Over-Explaining
251 **Problem**: Explaining what readers already know
252 **Fix**: Assume intelligence, provide only new information
253 
254 ### Buried Lede
255 **Problem**: Key point in paragraph 3
256 **Fix**: Move conclusion to opening, support with details
257 
258 ### Wall of Text
259 **Problem**: Dense paragraphs without visual breaks
260 **Fix**: Add headings, bullets, white space
261 
262 ### Passive Avoidance
263 **Problem**: "Mistakes were made" (who made them?)
264 **Fix**: "The team missed the deadline" (clear ownership)
265 
266 ### Jargon Cascade
267 **Problem**: "We synergized cross-functional paradigms"
268 **Fix**: "We got the teams to work together"
269 
270 ## Proven Content Frameworks
271 
272 ### AIDA (Attention → Interest → Desire → Action)
273 
274 Classic persuasion structure that works for any content with a goal:
275 
276 ```
277 Attention: "Most developers waste 3 hours/day on preventable bugs."
278 Interest: "Static analysis catches 85% of these before they ship."
279 Desire: "Teams using this approach ship 2x faster with fewer incidents."
280 Action: "Add this one-line config to your CI pipeline."
281 ```
282 
283 ### PAS (Problem → Agitate → Solution)
284 
285 Effective for blog posts, landing pages, and persuasive content:
286 
287 ```
288 Problem: "Your documentation is outdated the moment you write it."
289 Agitate: "New devs waste days. Senior devs answer the same questions. Nobody trusts the docs."
290 Solution: "Generate docs from code comments. Always current, always trusted."
291 ```
292 
293 ### BAB (Before → After → Bridge)
294 
295 Transformation narrative that creates emotional resonance:
296 
297 ```
298 Before: "I spent 6 hours debugging a production issue."
299 After: "Now I catch these problems before they deploy."
300 Bridge: "Here's the monitoring setup that changed everything."
301 ```
302 
303 ### 1-2-3 Structure
304 
305 For instructional content - simple, scannable, actionable:
306 
307 ```
308 1. The Problem: What's wrong and why it matters
309 2. The Solution: What to do about it
310 3. The How: Specific steps to implement
311 ```
312 
313 ## Detailed References
314 
315 For deeper guidance on specific topics:
316 
317 - **[references/clarity-science.md](references/clarity-science.md)**: Research on readability, cognitive load, and plain language with specific metrics
318 - **[references/emotional-impact.md](references/emotional-impact.md)**: Neuroscience of storytelling, memory, and persuasion
319 - **[references/structure-patterns.md](references/structure-patterns.md)**: Eye-tracking research, scanning patterns, and formatting
320 - **[references/revision-frameworks.md](references/revision-frameworks.md)**: Professional editing processes and before/after examples
321 
322 ## Quick Reference: The CLEAR Framework
323 
324 **C** - Concise: Cut 10-30% without losing meaning
325 **L** - Lead with value: Key point in first sentence
326 **E** - Evidence-based: Specific data beats vague claims
327 **A** - Active voice: Subject-verb-object structure
328 **R** - Reader-focused: What do they need to know?
329 
330 ## Validation: Content Quality Check
331 
332 After writing, verify:
333 
334 1. **Core message test**: Can you state it in one sentence?
335 2. **So what test**: After each paragraph, can you answer "so what"?
336 3. **Grandmother test**: Would a non-expert understand the main point?
337 4. **Action test**: Does the reader know what to do next?
338 5. **Cut test**: Can you remove any sentence without losing meaning?
339 
340 If any test fails, revise that section.