From skillkit-essentials
Transforms rigid AI-generated Markdown docs (checklists, templates, CAPS emphasis) into flowing conversational prose with personality, preserving accuracy.
npx claudepluginhub rfxlamia/skillkit --plugin skillkit-essentialsThis skill uses the workspace's default tool permissions.
This skill transforms robotic AI-generated documentation into prose that sounds like an actual human wrote it. Think: destroying checkbox spam, dismantling perfect paragraph structures, and injecting the kind of conversational flow you'd get from a colleague explaining something over coffee.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
This skill transforms robotic AI-generated documentation into prose that sounds like an actual human wrote it. Think: destroying checkbox spam, dismantling perfect paragraph structures, and injecting the kind of conversational flow you'd get from a colleague explaining something over coffee.
The approach is aggressive deformalization - not just tweaking tone, but fundamentally restructuring how information flows to break AI's predictable patterns.
Clear signals you're dealing with AI-generated docs:
- [x] Task 1: Do the thing (AC: #1)Examples from the wild:
Before transforming, confirm you're actually dealing with AI output. Load the detection checklist:
[See references/detection-patterns.md for complete list]
Quick test: Does the doc have 5+ of these?
If yes → proceed. If no → might already be human-written, be careful.
Execute transformations in order. Each pattern targets specific AI signatures:
[See references/core-transformations.md for detailed rules]
Quick reference:
Critical rule: Don't apply all transformations everywhere. Humans are inconsistent - some sections stay formal, others get playful. That's the point.
Read the output aloud (or mouth the words). Does it sound like you'd actually say this to someone?
Red flags the transformation failed:
Good signals:
Different doc types need different intensity levels:
High personality OK:
Moderate personality:
Gentle touch only:
[See references/examples-gallery.md for before/after samples]
If you just need to make something readable without full transformation:
Done. Not perfect, but 70% better readability.
## Task 2: Configure Dependencies
**CRITICAL**: The following steps MUST be completed in order.
- [x] Install package A (required for Task 3)
- [x] Verify installation with command X
- [x] Proceed to next task only after confirmation
It is important to note that failure to follow these steps will result in errors.
## Setting Up Dependencies
Okay, you'll need to install package A first - and yeah, this actually matters because
Task 3 depends on it. Run command X to verify it worked.
Once you get the confirmation, you're good to move on. If it errors out, the next step
will definitely break, so... don't skip this.
Notice:
Don't:
Do:
This skill uses reference documentation loaded into context:
The 5 core transformation patterns with detailed rules, examples, and edge cases. Load this for complex transformations or when you need to understand WHY a pattern works.
Complete AI signature checklist with detection heuristics. Load when you're unsure if a doc needs transformation or want to explain what makes text feel "AI-generated".
Before/after transformation showcase across different document types (technical guides, READMEs, API docs). Load for inspiration or to calibrate transformation intensity.
Future: Domain-specific adjustments for legal, academic, and specialized documentation.
Philosophy: AI writes like it's afraid to break rules. Humans write like they're explaining something to a friend while occasionally remembering they should probably sound professional. Capture that tension.