Maximalism
sickn33/agentic-awesome-skills
Web and App implementation guide for Controlled Maximalism. An agent skill from sickn33/agentic-awesome-skills.
Maximal project health pass. An agent skill from mrchantey/beet.
Apache-2.0Auto-check: notes
Install Test The Works
$ npx skills add mrchantey/beet --skill test-the-works -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mrchantey/beet test-the-works --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/mrchantey/beet.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/test-the-works .claude/skills/test-the-works && 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 "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .claude/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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/mrchantey/beet/tree/main/.agents/skills/test-the-worksType 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 mrchantey/beet --skill test-the-works -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mrchantey/beet test-the-works --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrchantey/beet.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/test-the-works .agents/skills/test-the-works && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .agents/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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 mrchantey/beet --skill test-the-works -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mrchantey/beet test-the-works --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrchantey/beet.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/test-the-works .cursor/skills/test-the-works && 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 "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .cursor/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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/mrchantey/beet.git --path .agents/skills/test-the-works--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 mrchantey/beet --skill test-the-works -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mrchantey/beet test-the-works --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrchantey/beet.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/test-the-works .gemini/skills/test-the-works && 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 "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .gemini/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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 mrchantey/beet test-the-worksInstalls 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 mrchantey/beet --skill test-the-works -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mrchantey/beet.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/test-the-works .github/skills/test-the-works && 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 "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .github/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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 mrchantey/beet --skill test-the-works -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mrchantey/beet test-the-works --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mrchantey/beet.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/test-the-works .opencode/skills/test-the-works && 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 "test-the-works" agent skill from https://github.com/mrchantey/beet/tree/main/.agents/skills/test-the-works into .opencode/skills/test-the-works/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "test-the-works", 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
test-the-works- GitHub stars
- 135
- Token cost
- ~1k tokens
- SKILL.md length
- 565 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Maximal project health pass. An agent skill from mrchantey/beet.
- Works in 5 steps: run core tests → run all tests → run examples → …
- Asked to run the works
- SKILL.md covers Ownership, 1. run core tests, 2. run all tests and 3. run examples, plus 2 more sections
- Calls cargo and just
What it does
Test The Works is an agent skill from mrchantey/beet. Maximal project health pass. Run core tests, all tests, the example smoke set, the rsxsite verification and every downstream repo in sequence, fixing every failure and warning surfaced along the way. Use when asked to run 'the works' or fully verify the project.
Its SKILL.md is about 1k 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: An Atmospheric OS for homegrown tech. The licence is Apache-2.0.
When your agent uses it
- Asked to run the works
- Fully verify the project
Example prompts
- “the works”
- “/test-the-works”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit eaa6012. 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
Shell commands in SKILL.md call:
cargojust
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
Test The Works loads about 1k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 565 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:55
om arch-config's `install-rust`, plus a `.env` holding its Wi-Fi credentials (`cp .env.example .env`, which its build ba
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 mrchantey/beet at commit eaa6012, republished under its Apache-2.0 licence (© mrchantey). 565 words, ~1,039 tokens.
Download SKILL.mdSave it as
.claude/skills/test-the-works/SKILL.md (or your agent's skills folder).- name
- test-the-works
- description
- Maximal project health pass. Run core tests, all tests, the example smoke set, the rsx_site verification and every downstream repo in sequence, fixing every failure and warning surfaced along the way. Use when asked to run 'the works' or fully verify the project.
The Works
This task is for maximally ensuring the project is running smoothly, beet and every repo built on it.
Ownership
Every failure, error and warning this skill surfaces is yours to fix, wherever it lives. That includes code you never touched, code another agent just committed, a feature or target combination no recipe names but a step happened to build (a downstream's wasm build, a bare-metal testing_embedded build), and every downstream repo in step 5.
None of these are reasons to leave something unfixed, they are exactly the findings this skill exists to produce:
- "pre-existing" or "not from my changes"
- "not a supported configuration" or "outside the recipe"
- "only a warning"
- "flaky, passed on rerun": a flake is a race, find it and fix it
- "the toolchain or tool is missing": install it, through the machine's provisioning (
/home/pete/me/arch-config'sjustfile) so a fresh install gets it too
The only things a report may leave standing are those that live outside every repo here and cannot be fixed from them: a third-party crate's future-incompat notice, host environment noise (a broken ~/.XCompose), a step needing a password or physical hardware the session does not have. Each is named in the report with why it cannot be fixed here and the exact command or action that unblocks it.
1. run core tests
run this skill to completion: .agents/skills/test-run/SKILL.md
2. run all tests
run this skill to completion: .agents/skills/test-run/SKILL.md but replace test-core with test-all
3. run examples
run this skill to completion: .agents/skills/test-examples/SKILL.md
4. verify rsx_site
rsx_site (the typed-authoring example) is a workspace member but is excluded from the test-core/test-all recipes, and its src/codegen/ route modules are gitignored (generated, not committed). So a stale or missing codegen breaks any workspace-wide build, yet nothing above catches it. Verify it explicitly:
- regenerate the route codegen (compiles without the generated modules, so it needs
--no-default-features):sh cargo run -p rsx_site --no-default-features --features codegen - render a route to the terminal and confirm the page body appears (not a
not found/ available-routes listing):sh cargo run -p rsx_site --features=cli -- counter
Both must exit 0, and step 2 must show the page content wrapped in the site shell. Fix any breakage (a common cause is generated route code drifting from a beet_router API change) and rerun.
Show full SKILL.md (202 more words)Show less
5. verify the downstream repos
Every repo in the downstream-sync skill's list (.agents/skills/downstream-sync/SKILL.md) builds on this checkout by path, so a beet change that compiles here can still break one of them. Each must depend on ../beet itself, never a worktree, so it verifies the tree this skill just tested. Run each repo's own test recipe (its justfile test, plus build-wasm where it has one) and fix what fails, upstream in beet when beet is at fault (a prelude name collision, an API narrowed below what a downstream consumes) and in the downstream when it has drifted from a deliberate beet change. A downstream's own uncommitted work is left in place and built on, never reverted.
beet_esp needs the Espressif Xtensa toolchain (espup, sourced through ~/export-esp.sh) and probe-rs, both from arch-config's install-rust, plus a .env holding its Wi-Fi credentials (cp .env.example .env, which its build bakes in). just check-all builds every target without a board and fails on any warning: the on-device test binary, both firmwares, each example under its own required-features and the host scene types. just test then flashes the on-device suite to an ESP32-S3 over USB; without the board attached the report says that run is waiting on it.
© mrchantey, Apache-2.0. 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/test-the-works of mrchantey/beet.
Open the folder on GitHubat commit eaa6012
Compare with similar skills
Test The Works 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 |
|---|---|---|---|---|---|---|
| Test The Works this skillmrchantey/beet | 135 | — | ~1k | Automated safety check: Notes | Apache-2.0 | |
| Maximalismsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Skin Health Analyzersickn33/agentic-awesome-skills | 47k | 2 repos | ~293 | Automated safety check: Pass | MIT | |
| Codebase Health Dashboardgarrytan/gstack | 136k | — | ~11k | Automated safety check: Notes | MIT | |
| Healthagenticnotetaking/arscontexta | 3.5k | — | ~7.1k | Automated safety check: Notes | MIT | |
| Health Wellnesssickn33/agentic-awesome-skills | 47k | 1 repos | ~3.5k | Automated safety check: Pass | MIT |
Similar skills
Skin Health Analyzer
sickn33/agentic-awesome-skills
Analyze skin health data, identify skin problem patterns, assess skin health status.
Codebase Health Dashboard
garrytan/gstack
Runs a project's own type checker, linter, test runner, dead-code detector and shell linter, combines them into a weighted 0-10 score and tracks the trend.
Health
agenticnotetaking/arscontexta
Run condition-based vault health diagnostics. An agent skill from agenticnotetaking/arscontexta.
Health Wellness
sickn33/agentic-awesome-skills
Wellbeing check-in register: anonymous flag, department, check-in date, wellbeing score, stress and energy levels, support and resource flags, confidentiality and status.
Cost Health
ruvnet/ruflo
Composite CI gate — runs cost-budget-check + cost-burn + cost-anomaly + cost-projection in parallel and surfaces a single combined health status with max exit code.
More from mrchantey/beet
All 11 skills in this repoDownstream Create
mrchantey/beet
Scaffold a new beet downstream repo (beet<name, a sibling of this checkout depending on the beet facade by path) from the template, register it with downstream-sync and run the first sync.
Test Examples
mrchantey/beet
Run the workspace example smoke set to catch regressions unit tests miss, covering every feature gate combination with self-terminating examples and curl-probed servers.
Docs Rust Sweep
mrchantey/beet
Comprehensive public-api quality pass over the core crates, reducing pub visibility and documenting every public item to a deny(missingdocs) standard.
Docs Site
mrchantey/beet
Write and edit the public website docs in site/routes/docs (beet.org/docs).
Infra Deploy
mrchantey/beet
The release process for the beet website. An agent skill from mrchantey/beet.
Downstream Sync
mrchantey/beet
Refresh every downstream repo (beetatproto, beetconnect, beetegress, beetesp, beeteval) with beet's AGENTS.md marker block, its MIT/Apache licenses and shared config files.
Questions about Test The Works
What does Test The Works do?
Maximal project health pass. An agent skill from mrchantey/beet. Test The Works is an agent skill from mrchantey/beet. Maximal project health pass.
When should I use Test The Works?
Test The Works fits situations like: asked to run the works; fully verify the project.
How do I install Test The Works in Claude Code?
Run `npx skills add mrchantey/beet --skill test-the-works -a claude-code`. Or copy the skill folder (.agents/skills/test-the-works in mrchantey/beet) into .claude/skills/test-the-works in your project. Claude Code loads it when a task matches its description.
How do I install Test The Works in Codex?
Run `npx skills add mrchantey/beet --skill test-the-works -a codex`. Or copy the skill folder (.agents/skills/test-the-works in mrchantey/beet) into .agents/skills/test-the-works in your project. Codex loads it when a task matches its description.
Can I use Test The Works 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 mrchantey/beet --skill test-the-works -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/test-the-works, .gemini/skills/test-the-works, .github/skills/test-the-works and .opencode/skills/test-the-works in your project.
What does Test The Works need to run?
Going by SKILL.md and its folder, Test The Works needs the command-line tools its instructions call (cargo and just).
Does Test The Works 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 Test The Works safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Test The Works use?
Test The Works is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Test The Works use?
About 1k tokens (SKILL.md is roughly 4.2k 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 Test The Works?
Skills that share tags, products or a category with Test The Works: Maximalism (sickn33/agentic-awesome-skills, 47k stars), Skin Health Analyzer (sickn33/agentic-awesome-skills, 47k stars), Codebase Health Dashboard (garrytan/gstack, 136k stars) and Health (agenticnotetaking/arscontexta, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Test The Works?
mrchantey (a GitHub user) maintains it in mrchantey/beet, which has 135 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 9, 2026.
Source: mrchantey/beet on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.