repo-install
Skill1 starsChanged 2 months agoApache-2.0View on GitHub
Install and initialize a source-code repository for local development. Use when a user asks to install, bootstrap, set up, or prepare a checkout, archive, or remote repository; detect the documented setup path, initialize dependencies safely, verify the result, and ask about a proxy after a network failure. Do not use to install Codex skills; use skill-installer for that.
In this repository25 other files it gives its agents.
- agent-runtimeSkill
- ball-alignSkill
- canvas-clientSkill
- checkSkill
- chip-designerSkill
- collaboration-panelSkill
- debug-bemuSkill
- debug-compilerSkill
- debug-p2eSkill
- debug-performanceSkill
- debug-verilatorSkill
- domain-modelingSkill
- graph-contractSkill
- grillingSkill
- grill-with-docsSkill
- ip-designerSkill
- model-optimizeSkill
- model-portSkill
- model-recipeSkill
- plugin-verifySkill
- programming-principlesSkill
- reportSkill
- role-identitySkill
- waveformSkill
- workload-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Follow the documented setup path before inferring one from a package manifest.
- Distinctive: line 14
After the first clearly network-related failure from a clone, submodule update, dependency download, or install:
- Distinctive: line 18
If provided, confirm whether it applies only to the command, current shell, or project configuration.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Repository Install
- Inspect the repository root, status, documented setup files, manifests, lockfiles, and submodule state before changing anything. Read
AGENTS.mdonly when it exists. - Follow the documented setup path before inferring one from a package manifest. Preserve lockfiles, user configuration, and uncommitted changes. Do not install globally or delete build output without explicit approval.
- Initialize only required repository-owned dependencies, then run the smallest documented configure, build, or smoke check. Report commands, results, and any remaining manual step.
Network Failure
After the first clearly network-related failure from a clone, submodule update, dependency download, or install:
- Stop retrying.
- State the failed operation and ask the user whether an HTTP/HTTPS or SOCKS proxy is available.
- If provided, confirm whether it applies only to the command, current shell, or project configuration. Reuse an existing proxy environment variable when present; do not persist credentials or change global Git configuration without permission.
- Without a proxy, report available local-cache or offline options and what remains unavailable.
Buckyball
For a fresh Buckyball checkout, follow the documented repository setup: install Nix, then run ./scripts/nix/build-all.sh from the repository root. Use project bbdev_* MCP tools for subsequent compiler, workload, simulation, synthesis, and test operations; poll every returned trace_id to terminal success. Do not call bbdev CLI or nix develop -c bbdev ... directly.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

