Cleans, dedupes, and refines documentation to ensure project clarity.
Install
mkdir -p .claude/skills/re0 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17550" && unzip -o skill.zip -d .claude/skills/re0 && rm skill.zipInstalls to .claude/skills/re0
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Refresh an existing artifact into the current best v0. Use when the user asks to clean up, sync up, dedupe, de-noise, smooth, rewrite, or update an artifact after iteration; when nearby artifacts may have drifted; or when changes in one place should be reflected across related artifacts while keeping the result minimal.Key capabilities
- →Remove scaffolding residue from artifacts
- →Fold durable lessons into artifacts
- →Rewrite instead of appending to remove noise
- →Smooth prose and source noise
- →Refresh artifacts to a clean v0 state
How it works
It reads the target artifact and related ones, then removes stale data, noise, and redundant information. It rewrites sections to reflect current truth, smooths prose and source formatting, and aims for a minimal, clean v0 result.
Inputs & outputs
When to use re0
- →Cleaning up project specs
- →Syncing documentation after refactors
- →Refining messy draft files
About this skill
Refresh the target artifact as if it were the first clean version.
Goal
The result must be lighter, more current, and more accurate than the input. It should not read like a changelog, cleanup note, or patch over an older draft.
Workflow
- Identify the target artifact from the user's request or the active context.
- Read the target artifact end to end before editing.
- Check nearby artifacts that must stay aligned with it.
- Remove scaffolding residue, stale deltas, duplicated process noise, deprecated information, and over-specific history.
- Fold durable lessons into the place they should have lived from the start.
- Rewrite instead of appending when appending would preserve noise.
- Preserve the artifact's useful voice and structure; simplify everything else.
- Smooth prose noise: fold a parenthetical that interrupts a sentence or list into its own clause or cut it, keep a word or point repeated within reach of itself only once, and unwind padding that adds length but not meaning.
- Smooth source noise: unwrap a hard line break that splits a sentence mid-flow so each paragraph or list item lives on one source line, matching how sibling artifacts format theirs; make a plain-text pointer to a named section or file followable, a link where the medium supports one; leave code, tables, and quoted material as formatted.
- Re-read the result and cut again.
Rules
- A pass that finds nothing to genuinely improve changes nothing.
- Prefer editing existing sections over adding new ones.
- Convert "what changed" into "what is true now".
- Keep only details that improve future execution, accuracy, or recall.
- Do not leave old/new traces unless the artifact is explicitly a changelog.
- Fix machine-clear residue; surface judgment calls — never auto-resolve an ambiguity or "fix" a deliberate look-alike.
- Repair from the source of truth — the canonical or sibling artifact, not the damaged surface — and mutate with edit-safety: assert the target exists (report a MISS, never a silent no-op), edit unicode-safe (
PYTHONUTF8=1), replace positional targets per occurrence rather than by blanket sweep, and script large structural moves. - Do not create extra files unless the user asks.
Verification
The result reads as a clean v0 to fresh eyes — no trace of the older draft, no sign it was patched rather than rewritten. If unsure, re-read it cold, as a stranger with no prior context would. Report what noise was removed and what durable truth was kept.
When not to use it
- →When the user wants to preserve old/new traces in the artifact
- →When the user wants to auto-resolve ambiguities or 'fix' deliberate look-alikes
Limitations
- →Does not create extra files unless requested
- →Preserves the artifact's useful voice and structure
- →A pass that finds nothing to genuinely improve changes nothing
How it compares
This skill systematically refreshes artifacts by rewriting and removing noise, ensuring they read as a clean initial version rather than a series of patches or updates, unlike simple appending or manual cleanup.
Compared to similar skills
re0 side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| re0 (this skill) | 0 | 21d | No flags | Intermediate |
| docx | 93 | 5mo | Review | Advanced |
| transcription | 1 | 6mo | Review | Intermediate |
| granola-core-workflow-a | 1 | 10d | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by LowyShin
View all by LowyShin →You might also like
docx
anthropics
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
transcription
MadAppGang
Audio/video transcription using OpenAI Whisper. Covers installation, model selection, transcript formats (SRT, VTT, JSON), timing synchronization, and speaker diarization. Use when transcribing media or generating subtitles.
granola-core-workflow-a
jeremylongshore
Meeting preparation and template setup workflow with Granola. Use when preparing for important meetings, setting up note templates, or configuring meeting-specific capture settings. Trigger with phrases like "granola meeting prep", "granola template", "prepare granola meeting", "granola agenda", "granola setup meeting".
lark-doc
Rabbit-Ivan
飞书云文档:创建和编辑飞书文档。从 Markdown 创建文档、获取文档内容、更新文档(追加/覆盖/替换/插入/删除)、上传和下载文档中的图片和文件、搜索云空间文档。当用户需要创建或编辑飞书文档、读取文档内容、在文档中插入图片、搜索云空间文档时使用;如果用户是想按名称或关键词先定位电子表格、报表等云空间对象,也优先使用本 skill 的 docs +search 做资源发现。
kb-meeting-protocol
kvcop
Build meeting protocols from transcripts in tmp/: validate inputs (Voice Recognition transcript required), generate artifacts under notes/meetings/artifacts/, create a meeting note under notes/meetings/ (YYYY-MM-DD-slug.md) with a copy-ready Russian protocol block, and update notes/work/typos.md via
docs-write
metabase
Write documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).