Agent skill

Re Create

by sickn33 in sickn33/agentic-awesome-skills

Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.

MITAuto-check passed

Install Re Create

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills re-create --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/re-create .claude/skills/re-create && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
re-create
GitHub stars
47k
Used in
1 other repo
Token cost
~2.7k tokens
SKILL.md length
1,198 words
Files
1
Skills in repo
1,354
Repo updated
First seen
Licence
MIT

At a glance

Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.

  • Works in 6 steps: Justify the Erasure → Read the Target Completely → Erasure Declaration (User Must Confirm) → …
  • SKILL.md covers Overview, When to Use This Skill, How It Works and Self-Ask Before Erasure, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Re Create is an agent skill from sickn33/agentic-awesome-skills. Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.

Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

Example prompts

  • “/re-create”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Justify the Erasure
  2. Read the Target Completely
  3. Erasure Declaration (User Must Confirm)
  4. Controlled Erasure
  5. Rebuild Against the Preservation List
  6. Blast Radius Verification

What it can do on your machine

Read from SKILL.md and the folder at commit ec02547. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Re Create loads about 2.7k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 1,198 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit ec02547, republished under its MIT licence (© sickn33). 1,198 words, ~2,673 tokens.

Download SKILL.mdSave it as .claude/skills/re-create/SKILL.md (or your agent's skills folder).
name
re-create
description
Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.
risk
critical
source
community
date_added
2026-06-27

re-create — Controlled Erasure & Rebuild Protocol

Overview

Hollow Purple is Gojo's most destructive technique — blue and red combined into total erasure of the target. But Gojo doesn't use it carelessly. He knows exactly what he's erasing and why. Same here: this skill is the nuclear option, invoked only when patching is the wrong call, executed with full control over what gets erased and what must survive.

Rewrites are dangerous not because rebuilding is hard, but because it is easy to silently erase behavior that was working and expected. This skill enforces a complete inventory of what must survive before a single line is deleted, and a full verification that everything survived after the rebuild.


When to Use This Skill

  • Use when a file, module, or component needs to be completely deleted and rewritten from scratch
  • Use when structural rot is so deep that individual fixes would only make it worse
  • Use when accumulated technical debt makes the code unmaintainable
  • Use when the target is fundamentally broken and beyond saving
  • DO NOT use for partial refactors, single-function fixes, or targeted edits

How It Works

PHASE 1 — Justify the Erasure

The AI must prove that a full rewrite is necessary. It must answer all of the following:

  1. What specifically is broken or unsalvageable?
    • Not "it's messy" — specific structural problems that make targeted fixes impossible or counterproductive
  2. Why would targeted edits make things worse, not better?
    • Patching on top of rot, compounding complexity, architectural mismatch
  3. What is the concrete cost of keeping the current implementation?
    • Maintenance burden, bug surface, performance, developer velocity

If the AI cannot clearly answer all three, it must fall back to targeted edits instead of a rewrite. A rewrite is not a reward for messy code — it is a last resort.

The bar is high. "This code is ugly" does not justify hollow purple. "The architecture assumes X but the system now requires Y and every patch makes the mismatch worse" does.


PHASE 2 — Read the Target Completely

Before proposing deletion, the AI must read the entire target (file, module, or component) in full.

The AI must identify and catalog:

  1. Public interfaces — functions, classes, types, or exports that other parts of the codebase call
  2. Implicit contracts — behaviors that other files depend on even if not formally typed
  3. Working behaviors — things the current implementation does correctly that must continue to work
  4. Non-obvious logic — edge cases, guards, or special handling that looks incidental but is intentional
  5. Blast radius — every file in the codebase that imports from or depends on the target

The AI cannot skip this phase even if it has read the file before. The purpose is not familiarity — it is building the Preservation List.


PHASE 3 — Erasure Declaration (User Must Confirm)

The AI outputs a complete erasure plan and waits for user confirmation before deleting or writing anything.

HOLLOW PURPLE — ERASURE PLAN
─────────────────────────────────────────
TARGET FOR ERASURE:
  [file path or module name]

WHY TARGETED FIXES ARE WRONG:
  [specific justification — architectural rot, fundamental mismatch, etc.]

PRESERVATION LIST (must survive the rewrite):
  - [public interface / export 1] → [what it does, who depends on it]
  - [public interface / export 2] → [what it does, who depends on it]
  - [working behavior 1]          → [what it does, why it must be kept]
  - [non-obvious logic 1]         → [what it guards against]

BLAST RADIUS (files that depend on the target):
  - [file path] → depends on [what specifically]
  - [file path] → depends on [what specifically]

NEW IMPLEMENTATION PLAN:
  [Description of what the rebuild will look like — structure, approach, key decisions]

WHAT WILL NOT BE PRESERVED:
  [Anything intentionally dropped and why — dead code, deprecated behavior, etc.]
─────────────────────────────────────────
Confirm to proceed with erasure and rebuild.

Nothing is deleted until the user explicitly confirms. A reply of "yes", "confirmed", "do it", or equivalent counts. Silence does not.


PHASE 4 — Controlled Erasure

User confirms → the target is deleted. Rules for this phase:

  • Delete cleanly. Not commented out, not renamed to _old, not archived in place — deleted.
  • Delete only the declared target. Nothing outside the declared scope is touched during erasure.
  • Pause if scope expands. If deletion reveals unexpected dependencies not in the blast radius list, the AI stops and reports before continuing.

PHASE 5 — Rebuild Against the Preservation List

The AI writes the new implementation. Rules:

  1. Every item on the Preservation List is an obligation. The rebuild is not complete until every preserved interface, behavior, and edge case is implemented and checked off.
  2. Match the blast radius expectations. Files that depended on the old implementation must be able to use the new one without changes — unless changes to dependent files were declared in Phase 3.
  3. No bonus features. The rebuild implements what was declared. New improvements, extra functionality, and cleanup of adjacent things are a separate task.
  4. Follow existing codebase conventions. The new implementation must use the same patterns, naming conventions, and style as the surrounding codebase — not whatever the AI prefers.

The AI tracks preservation progress explicitly:

REBUILD PROGRESS
─────────────────────────────────────────
Preservation List:
  ✓ [interface 1]         → implemented
  ✓ [working behavior 1]  → implemented
  ✗ [non-obvious logic 1] → pending
─────────────────────────────────────────

Show full SKILL.md (507 more words)Show less
PHASE 6 — Blast Radius Verification

After the rebuild is complete, the AI checks every file in the blast radius:

  1. Re-read each dependent file and confirm it can still use the new implementation
  2. Verify each dependency — the function signatures, exports, and behaviors it relied on are present in the rebuild
  3. Flag any breakage — if a dependent file now has a mismatch, report it and propose a fix before declaring done

Final verification report:

HOLLOW PURPLE — VERIFICATION
─────────────────────────────────────────
Preservation List:          ALL ITEMS ✓
Blast radius files checked:
  - [file] → ✓ compatible with new implementation
  - [file] → ✓ compatible with new implementation
New issues introduced:      NONE / [describe if found]
─────────────────────────────────────────
Status: CLEAN ✓  /  NEEDS FOLLOW-UP ⚠

Self-Ask Before Erasure

The AI must answer all four before Phase 4 begins:

#QuestionRequired
1Have I read the entire target and built a complete Preservation List?Yes — or read more
2Have I identified the full blast radius?Yes — or search more
3Has the user confirmed the erasure plan?Yes — or wait
4Is the erasure scoped exactly to what was declared?Yes — or re-declare

Hard Rules (Never Violated)

  • No deletion before user confirmation. Ever.
  • No deletion before the Preservation List is complete. You cannot protect what you haven't inventoried.
  • No "clean up while I'm at it" during rebuild. The rebuild scope is exactly what was declared.
  • No undeclared blast radius expansion. If a dependent file wasn't in the list, stop and report it.
  • No skipping Phase 6. The rebuild is not done until blast radius files are verified.
  • No rewrites disguised as refactors. If more than 80% of a file is being changed, this protocol applies.

What This Skill Prevents

  • Rewrites that silently drop working edge-case logic that wasn't documented
  • Rebuilds that break dependent files because their interfaces changed
  • Rewrites done for the wrong reason (style preference, boredom) when a targeted fix would have been better
  • Partial rebuilds that leave the codebase in a broken half-old-half-new state
  • Blast radius files breaking silently with no one noticing until runtime

Quick Reference

PhaseActionDeletes/Writes Code?
1 — JustifyProve erasure is necessary❌ No
2 — ReadRead target fully, build Preservation List❌ No
3 — DeclareOutput erasure plan, wait for confirmation❌ No
4 — EraseDelete the declared target🗑️ Deletes only
5 — RebuildWrite new implementation against Preservation List✅ Writes
6 — VerifyCheck Preservation List + blast radius❌ No

Security & Safety Notes

  • Authorized Use Only: This skill involves destructive capabilities (deleting files). Always ensure you have appropriate authorization and backups before triggering a full rebuild.
  • Explicit Confirmation Required: No code should ever be deleted without explicit user confirmation of the Erasure Plan.

Examples

Example 1: Triggering a full module rewrite
text
User: "The authentication module is beyond saving. Rewrite this from scratch."

AI: [Outputs HOLLOW PURPLE — ERASURE PLAN]
"Confirm to proceed with erasure and rebuild."

User: "Confirmed."

AI: [Executes Phase 4 and 5: Controlled Erasure and Rebuild against the Preservation List]
Example 2: Erasure correctly rejected in Phase 1
text
User: "This data formatting script is a mess, rewrite it from scratch."

AI: [Evaluates Phase 1 criteria]
"I cannot justify a full rewrite. While the code is messy, the structural rot is not deep enough to make patching impossible. The blast radius is limited, and targeted edits will improve it without the risk of erasing undocumented behaviors. I will proceed with surgical refactoring instead."

Trigger Phrases

  • "rewrite this from scratch"
  • "delete this and redo it"
  • "this is beyond saving / beyond repair"
  • "the whole module / component / file is broken"
  • "start over on this"
  • Any situation where patching would compound the problem rather than solve it

Limitations

  • The AI must explicitly justify the rewrite and receive user confirmation before deleting anything.
  • The rebuild scope must exactly match what was declared (no bonus features or extra cleanup).
  • Does not apply to partial refactoring, single-function fixes, or targeted bug fixes.
  • It requires identifying the full blast radius upfront to avoid silently breaking dependencies.

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/re-create of sickn33/agentic-awesome-skills.

Open the folder on GitHubat commit ec02547

Used in 1 other repository

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Re Create next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Re Create compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Re Create this skillsickn33/agentic-awesome-skills47k1 repos~2.7kAutomated safety check: PassMIT
Module Completeness Checkfengshao1227/ccg-workflow5.9k—~473Automated safety check: NotesMIT
Rewrite Plannexu-io/open-design100k—~511Automated safety check: PassApache-2.0
Es Modulesthedaviddias/Front-End-Checklist74k—~482Automated safety check: PassMIT
Verification Before Completionforyourhealth111-pixel/Vibe-Skills3.6k—~1.1kAutomated safety check: PassApache-2.0
RewriteNxcoreAI/EverRoom3k—~124Automated safety check: PassCustom licence

Similar skills

  • Module Completeness Check

    fengshao1227/ccg-workflow

    Scans a module directory for the required README.md and DESIGN.md plus recommended files and reports what is missing, so a module is not delivered incomplete.

    5.9k GitHub stars~473 tokensUpdated 23 days ago
    DevelopmentAuto-check: notes
  • Rewrite Plan

    nexu-io/open-design

    Author a long-running multi-file rewrite plan that subsequent patch-edit + diff-review + build-test stages will execute, with explicit ownership boundaries and patch-safety guarantees.

    100k GitHub stars~511 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Es Modules

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing scripts, client components, bundles, or runtime behavior related to Use ES modules (import/export).

    74k GitHub stars~482 tokensUpdated 2 days ago
    Auto-check passed
  • Verification Before Completion

    foryourhealth111-pixel/Vibe-Skills

    Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.

    3.6k GitHub stars~1.1k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Rewrite

    NxcoreAI/EverRoom

    Rewrite only the supplied selectedText per the instruction and return the replacement fragment.

    3k GitHub stars~124 tokensUpdated today
    Auto-check passed
  • Official

    Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior.

    40k GitHub stars~2.2k tokensUpdated today
    Frontend & DesignAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,354 skills in this repo
  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed
  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed
  • Content Creator

    sickn33/agentic-awesome-skills

    Drafts and reviews audience-specific content from supplied brand examples, with local scripts for brand voice and SEO diagnostics, channel templates and a content calendar.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

Questions about Re Create

What does Re Create do?

Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible. Re Create is an agent skill from sickn33/agentic-awesome-skills. Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.

How do I install Re Create in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill re-create -a claude-code`. Or copy the skill folder (skills/re-create in sickn33/agentic-awesome-skills) into .claude/skills/re-create in your project. Claude Code loads it when a task matches its description.

How do I install Re Create in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill re-create -a codex`. Or copy the skill folder (skills/re-create in sickn33/agentic-awesome-skills) into .agents/skills/re-create in your project. Codex loads it when a task matches its description.

Can I use Re Create in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill re-create -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/re-create, .gemini/skills/re-create, .github/skills/re-create and .opencode/skills/re-create in your project.

What does Re Create need to run?

SKILL.md names no scripts, command-line tools or credentials: Re Create is instructions for the agent only.

Does Re Create access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Re Create safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Re Create use?

Re Create is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Re Create use?

About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Re Create?

Skills that share tags, products or a category with Re Create: Module Completeness Check (fengshao1227/ccg-workflow, 5.9k stars), Rewrite Plan (nexu-io/open-design, 100k stars), Es Modules (thedaviddias/Front-End-Checklist, 74k stars) and Verification Before Completion (foryourhealth111-pixel/Vibe-Skills, 3.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Re Create?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,343 GitHub stars. The repository holds 1,354 skills in this directory. The repository was last updated on October 7, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.