mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-04-09 19:03:28 +08:00
Ports functionality from 10+ separate plugins into ECC so users only need one plugin installed. Consolidates: pr-review-toolkit, feature-dev, commit-commands, hookify, code-simplifier, security-guidance, frontend-design, explanatory-output-style, and personal skills. New agents (8): code-architect, code-explorer, code-simplifier, comment-analyzer, conversation-analyzer, pr-test-analyzer, silent-failure-hunter, type-design-analyzer New commands (9): commit, commit-push-pr, clean-gone, review-pr, feature-dev, hookify, hookify-list, hookify-configure, hookify-help New skills (8): frontend-design, hookify-rules, github-ops, knowledge-ops, lead-intelligence, oura-health, pmx-guidelines, remotion Enhanced skills (8): article-writing, content-engine, market-research, investor-materials, investor-outreach, x-api, security-scan, autonomous-loops — merged with personal skill content New hook: security-reminder.py (pattern-based OWASP vulnerability warnings on file edits) Totals: 36 agents, 69 commands, 128 skills, 29 hook scripts
5.2 KiB
5.2 KiB
name, description, origin
| name | description | origin |
|---|---|---|
| article-writing | Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter. | ECC |
Article Writing
Write long-form content that sounds like a real person or brand, not generic AI output.
When to Activate
- drafting blog posts, essays, launch posts, guides, tutorials, or newsletter issues
- turning notes, transcripts, or research into polished articles
- matching an existing founder, operator, or brand voice from examples
- tightening structure, pacing, and evidence in already-written long-form copy
Core Rules
- Lead with the concrete thing: example, output, anecdote, number, screenshot description, or code block.
- Explain after the example, not before.
- Prefer short, direct sentences over padded ones.
- Use specific numbers when available and sourced.
- Never invent biographical facts, company metrics, or customer evidence.
Voice Capture Workflow
If the user wants a specific voice, collect one or more of:
- published articles
- newsletters
- X / LinkedIn posts
- docs or memos
- a short style guide
Then extract:
- sentence length and rhythm
- whether the voice is formal, conversational, or sharp
- favored rhetorical devices such as parentheses, lists, fragments, or questions
- tolerance for humor, opinion, and contrarian framing
- formatting habits such as headers, bullets, code blocks, and pull quotes
If no voice references are given, default to a direct, operator-style voice: concrete, practical, and low on hype.
Banned Patterns
Delete and rewrite any of these:
- generic openings like "In today's rapidly evolving landscape"
- filler transitions such as "Moreover" and "Furthermore"
- hype phrases like "game-changer", "cutting-edge", or "revolutionary"
- vague claims without evidence
- biography or credibility claims not backed by provided context
Writing Process
- Clarify the audience and purpose.
- Build a skeletal outline with one purpose per section.
- Start each section with evidence, example, or scene.
- Expand only where the next sentence earns its place.
- Remove anything that sounds templated or self-congratulatory.
Structure Guidance
Technical Guides
- open with what the reader gets
- use code or terminal examples in every major section
- end with concrete takeaways, not a soft summary
Essays / Opinion Pieces
- start with tension, contradiction, or a sharp observation
- keep one argument thread per section
- use examples that earn the opinion
Newsletters
- keep the first screen strong
- mix insight with updates, not diary filler
- use clear section labels and easy skim structure
Tone Calibration
Match tone to context:
| Context | Tone |
|---|---|
| Technical content | Direct, opinionated, practical. Share what works from experience. |
| Personal/journey | Honest, reflective. No performative humility, no toxic positivity. |
| Security content | Urgent but not alarmist. Evidence-based. Show the vulnerability, then the fix. |
| Community updates | Grateful but not sycophantic. Numbers speak louder than adjectives. |
| Product launches | Matter-of-fact. Let features speak. No hype language. |
Approved Voice Patterns
These patterns work well for developer and founder audiences:
- "here's exactly how..."
- "no fluff."
- "zero [X]. just [Y]."
- "the short version:"
- Direct address: "you want X. here's X."
- Parenthetical asides for personality and self-awareness (use roughly once every 2-3 paragraphs)
Platform-Specific Structure
Technical Guides
- open with what the reader gets
- use code or terminal examples in every major section
- use "Pro tip:" callouts for non-obvious insights
- end with concrete takeaways as short bullets, not a summary paragraph
- link to resources at the bottom
Essays / Opinion Pieces
- start with tension, contradiction, or a sharp observation
- keep one argument thread per section
- use examples that earn the opinion
Newsletters
- keep the first screen strong
- mix insight with updates, not diary filler
- use clear section labels and easy skim structure
- proper capitalization
- short paragraphs (2-3 sentences max)
- first line is the hook (truncates at ~210 chars)
- professional framing: impact, lessons, takeaways
- 3-5 hashtags at the bottom only
X/Twitter Threads
- each tweet must standalone (people see them individually)
- hook in first tweet, no "thread:" or "1/" prefix
- one point per tweet
- last tweet: CTA or punchline, not "follow for more"
- 4-7 tweets ideal length
- no links in tweet body (kills reach). Links in first reply.
Quality Gate
Before delivering:
- verify factual claims against provided sources
- remove filler and corporate language
- confirm the voice matches the supplied examples
- ensure every section adds new information
- check formatting for the intended platform
- zero banned patterns in entire document
- at least 2-3 parenthetical asides for personality (if voice calls for it)
- examples/evidence before explanation in each section
- specific numbers used where available