Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Use ignored .scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed…
Install Scratch Work
$ npx skills add pellegre/libcrafter --skill scratch-work -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install pellegre/libcrafter scratch-work --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/pellegre/libcrafter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/scratch-work .claude/skills/scratch-work && 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 "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .claude/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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/pellegre/libcrafter/tree/master/.agents/skills/scratch-workType 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 pellegre/libcrafter --skill scratch-work -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install pellegre/libcrafter scratch-work --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pellegre/libcrafter.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/scratch-work .agents/skills/scratch-work && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .agents/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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 pellegre/libcrafter --skill scratch-work -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install pellegre/libcrafter scratch-work --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pellegre/libcrafter.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/scratch-work .cursor/skills/scratch-work && 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 "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .cursor/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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/pellegre/libcrafter.git --path .agents/skills/scratch-work--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 pellegre/libcrafter --skill scratch-work -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install pellegre/libcrafter scratch-work --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pellegre/libcrafter.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/scratch-work .gemini/skills/scratch-work && 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 "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .gemini/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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 pellegre/libcrafter scratch-workInstalls 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 pellegre/libcrafter --skill scratch-work -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/pellegre/libcrafter.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/scratch-work .github/skills/scratch-work && 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 "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .github/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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 pellegre/libcrafter --skill scratch-work -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install pellegre/libcrafter scratch-work --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/pellegre/libcrafter.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/scratch-work .opencode/skills/scratch-work && 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 "scratch-work" agent skill from https://github.com/pellegre/libcrafter/tree/master/.agents/skills/scratch-work into .opencode/skills/scratch-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "scratch-work", 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.
Facts
- Skill name
scratch-work- GitHub stars
- 312
- Token cost
- ~669 tokens
- SKILL.md length
- 328 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use ignored .scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed…
- Works in 6 steps: Ensure .scratch/ is ignored in the… → Create one workspace per experiment → Add a README.md in the scratch workspace… → …
- Development work in your project
- SKILL.md covers Workflow, Network Experiments, Script Rules and Promotion
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Scratch Work is an agent skill from pellegre/libcrafter. Use ignored .scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed until promoted.
Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development. The repository describes itself as: A Rust library for constructing, sending, capturing, and decoding network packets. The licence is MIT.
When your agent uses it
- Development work in your project
Example prompts
- “/scratch-work”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Ensure .scratch/ is ignored in the repository before creating scratch
- Create one workspace per experiment
- Add a README.md in the scratch workspace with
- Keep ad hoc code under scripts/, src/, guest/, or similarly explicit
- Keep artifacts under artifacts/, state/, pcaps/, or logs/ inside the
- Do not commit scratch files directly. Promote only hardened pieces by moving
What it can do on your machine
Read from SKILL.md and the folder at commit f9ef000. 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
Scratch Work loads about 669 tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 328 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.
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 pellegre/libcrafter at commit f9ef000, republished under its MIT licence (© pellegre). 328 words, ~669 tokens.
Download SKILL.mdSave it as
.claude/skills/scratch-work/SKILL.md (or your agent's skills folder).- name
- scratch-work
- description
- Use ignored .scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed until promoted.
Scratch Work
Use this skill when work should be explored locally without immediately adding prototype code, logs, captures, generated files, or one-off scripts to tracked repo paths.
Workflow
- Ensure
.scratch/is ignored in the repository before creating scratch files. Add the ignore rule if it is missing. - Create one workspace per experiment:
.scratch/<short-topic-slug>/. - Add a
README.mdin the scratch workspace with:- goal and date
- host or execution assumptions
- exact commands run
- observed outputs worth preserving
- cleanup notes
- candidates for later promotion into
docs/,tools/, or tests
- Keep ad hoc code under
scripts/,src/,guest/, or similarly explicit subdirectories inside that workspace. - Keep artifacts under
artifacts/,state/,pcaps/, orlogs/inside the scratch workspace. - Do not commit scratch files directly. Promote only hardened pieces by moving them into tracked repo locations and adding tests or docs appropriate for the promoted behavior.
Network Experiments
For USB dongle, wire-level packet, or LAN probing work:
- Keep host mutation in documented setup steps. Do not hide root-requiring changes inside casual scratch scripts.
- Use only an authorized execution environment for raw packet work.
- Record interface names, USB IDs, driver assumptions, and observed MAC/IP addresses in the workspace README.
- Put captures and logs in scratch artifacts. Redact secrets before promoting any output.
- Keep machine selection and hardware lifecycle in operator-supplied tooling outside this repository.
Script Rules
- Make scratch scripts small, direct, and parameterized with environment variables or flags.
- Print commands and paths clearly enough that the user can rerun them.
- Avoid embedding credentials, Wi-Fi passphrases, service tokens, or private network secrets in files.
- Add timeouts to sniffing, scanning, packet generation, or remote commands.
- Treat scratch results as evidence, not final implementation. Summarize what worked and what should be promoted.
Promotion
When a scratch experiment stabilizes, move the durable pieces out of .scratch/
and update the repo normally. Typical destinations are tools/ for reusable
scripts, docs/ for workflow documentation, tests/ for fixtures or checks,
and .agents/skills/ for reusable agent procedure.
© pellegre, 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 .agents/skills/scratch-work of pellegre/libcrafter.
Open the folder on GitHubat commit f9ef000
Compare with similar skills
Scratch Work 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 |
|---|---|---|---|---|---|---|
| Scratch Work this skillpellegre/libcrafter | 312 | — | ~669 | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 59 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from pellegre/libcrafter
Agent Cargo Publish
pellegre/libcrafter
Publish the libcrafter crafter crate to crates.io only after the local release gate, cargo publish dry-run, package summary, ask-tool confirmation, and crates.io/docs.rs verification.
Commit Changes
pellegre/libcrafter
Create, amend, reword, split, squash, or prepare libcrafter commits with the repository's Conventional Commits policy and scoped staging discipline.
Prepare PR
pellegre/libcrafter
Open, update, title, review, or prepare libcrafter pull requests so commits are ready for rebase-and-fast-forward landing and required validation is documented.
Create Branch
pellegre/libcrafter
Create, rename, check out, or prepare libcrafter branches and worktrees with typed branch names such as feature/slug or fix/slug instead of bare task names.
Packet Validation
pellegre/libcrafter
Add or run deterministic libcrafter packet behavior validation through oracle specs, reference backends, offline checks, pcap checks, probe plans, and artifacts.
Related
Categories
Questions about Scratch Work
What does Scratch Work do?
Use ignored .scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed…. Scratch Work is an agent skill from pellegre/libcrafter.scratch workspaces for experiments, disposable prototypes, network probes, hardware exploration, generated code, and any task where the user asks for work that should not be committed until promoted.
When should I use Scratch Work?
Scratch Work fits situations like: development work in your project.
How do I install Scratch Work in Claude Code?
Run `npx skills add pellegre/libcrafter --skill scratch-work -a claude-code`. Or copy the skill folder (.agents/skills/scratch-work in pellegre/libcrafter) into .claude/skills/scratch-work in your project. Claude Code loads it when a task matches its description.
How do I install Scratch Work in Codex?
Run `npx skills add pellegre/libcrafter --skill scratch-work -a codex`. Or copy the skill folder (.agents/skills/scratch-work in pellegre/libcrafter) into .agents/skills/scratch-work in your project. Codex loads it when a task matches its description.
Can I use Scratch Work 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 pellegre/libcrafter --skill scratch-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scratch-work, .gemini/skills/scratch-work, .github/skills/scratch-work and .opencode/skills/scratch-work in your project.
What does Scratch Work need to run?
SKILL.md names no scripts, command-line tools or credentials: Scratch Work is instructions for the agent only.
Does Scratch Work 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 Scratch Work 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 Scratch Work use?
Scratch Work 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 Scratch Work use?
About 669 tokens (SKILL.md is roughly 2.7k 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 Scratch Work?
Skills that share tags, products or a category with Scratch Work: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Scratch Work?
pellegre (a GitHub user) maintains it in pellegre/libcrafter, which has 312 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 4, 2026.
Source: pellegre/libcrafter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.