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.
Completely delete and rewrite a file or module from scratch when structural rot makes patching impossible.
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sickn33/agentic-awesome-skills re-create --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-srcUse ~/.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/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .claude/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-createType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sickn33/agentic-awesome-skills re-create --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/re-create .agents/skills/re-create && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .agents/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sickn33/agentic-awesome-skills re-create --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/re-create .cursor/skills/re-create && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .cursor/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/sickn33/agentic-awesome-skills.git --path skills/re-create--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sickn33/agentic-awesome-skills re-create --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/re-create .gemini/skills/re-create && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .gemini/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install sickn33/agentic-awesome-skills re-createInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/re-create .github/skills/re-create && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .github/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add sickn33/agentic-awesome-skills --skill re-create -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sickn33/agentic-awesome-skills re-create --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/re-create .opencode/skills/re-create && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "re-create" agent skill from https://github.com/sickn33/agentic-awesome-skills/tree/main/skills/re-create into .opencode/skills/re-create/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "re-create", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
re-createCompletely 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.
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.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit ec02547. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
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.
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.
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.
The full file from sickn33/agentic-awesome-skills at commit ec02547, republished under its MIT licence (© sickn33). 1,198 words, ~2,673 tokens.
.claude/skills/re-create/SKILL.md (or your agent's skills folder).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.
The AI must prove that a full rewrite is necessary. It must answer all of the following:
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.
Before proposing deletion, the AI must read the entire target (file, module, or component) in full.
The AI must identify and catalog:
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.
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.
User confirms → the target is deleted. Rules for this phase:
_old, not archived in place — deleted.The AI writes the new implementation. Rules:
The AI tracks preservation progress explicitly:
REBUILD PROGRESS
─────────────────────────────────────────
Preservation List:
✓ [interface 1] → implemented
✓ [working behavior 1] → implemented
✗ [non-obvious logic 1] → pending
─────────────────────────────────────────After the rebuild is complete, the AI checks every file in the blast radius:
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 ⚠The AI must answer all four before Phase 4 begins:
| # | Question | Required |
|---|---|---|
| 1 | Have I read the entire target and built a complete Preservation List? | Yes — or read more |
| 2 | Have I identified the full blast radius? | Yes — or search more |
| 3 | Has the user confirmed the erasure plan? | Yes — or wait |
| 4 | Is the erasure scoped exactly to what was declared? | Yes — or re-declare |
| Phase | Action | Deletes/Writes Code? |
|---|---|---|
| 1 — Justify | Prove erasure is necessary | ❌ No |
| 2 — Read | Read target fully, build Preservation List | ❌ No |
| 3 — Declare | Output erasure plan, wait for confirmation | ❌ No |
| 4 — Erase | Delete the declared target | 🗑️ Deletes only |
| 5 — Rebuild | Write new implementation against Preservation List | ✅ Writes |
| 6 — Verify | Check Preservation List + blast radius | ❌ No |
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]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."© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/re-create of sickn33/agentic-awesome-skills.
Open the folder on GitHubat commit ec02547
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.
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Re Create this skillsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Module Completeness Checkfengshao1227/ccg-workflow | 5.9k | — | ~473 | Automated safety check: Notes | MIT | |
| Rewrite Plannexu-io/open-design | 100k | — | ~511 | Automated safety check: Pass | Apache-2.0 | |
| Es Modulesthedaviddias/Front-End-Checklist | 74k | — | ~482 | Automated safety check: Pass | MIT | |
| Verification Before Completionforyourhealth111-pixel/Vibe-Skills | 3.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| RewriteNxcoreAI/EverRoom | 3k | — | ~124 | Automated safety check: Pass | Custom licence |
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.
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.
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).
foryourhealth111-pixel/Vibe-Skills
Completion-evidence route used before claiming work is complete, fixed, passing, committed, or PR-ready.
NxcoreAI/EverRoom
Rewrite only the supplied selectedText per the instruction and return the replacement fragment.
PostHog/posthog
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
SKILL.md names no scripts, command-line tools or credentials: Re Create is instructions for the agent only.
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.
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.
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.
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.
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.
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.