setup-astrobyte-skills
Skill1 starsChanged 13 days agoMITView on GitHub
Install the shared Astrobyte profile without onboarding, or configure a personalized profile when requested. Invoke explicitly to install or change this stack on a machine.
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/adopt-skill-stack.mdcCursor rule
- adopt-skill-stackSkill
- api-and-interface-designSkill
- astrobyte-architectSkill
- astrobyte-git-identitySkill
- astrobyte-modeSkill
- astrobyte-project-startupSkill
- astrobyte-pr-workflowsSkill
- astrobyte-recallSkill
- astrobyte-reviewSkill
- astrobyte-show-workSkill
- astrobyte-tddSkill
- astrobyte-verify-projectSkill
- blast-radiusSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- codebase-designSkill
- continual-improvement-checkSkill
- deprecation-and-migrationSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- frontend-designSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- grillingSkill
- handoffSkill
- hermetic-test-suitesSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- pr-feedback-loopSkill
- prototypeSkill
- researchSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- technical-writingSkill
- to-questionnaireSkill
- typescript-best-practicesSkill
- unslopSkill
- update-skill-stackSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Run python3 scripts/install.py --operator <handle> --interview in an interactive terminal.
- Very specific: line 18
Run python3 scripts/validate.py and python3 -m unittest discover -s tests -v from the repository.
≈ “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
Setup Astrobyte skills
Default to the shared Astrobyte profile without onboarding. Follow skills/adopt-skill-stack/references/quick-install.md in the source checkout, or references/quick-install.md in the installed adopt-skill-stack folder. Resolve the source URL supplied by the user if neither is available. Continue below only when the user explicitly requests a machine setup interview or personalization. Personalization records differences from the baseline; installation does not require creating a new profile or private repository.
- Locate the repository root containing
config/repository.json,catalog.json, andscripts/install.py. - Resolve the committed operator handle or approved baseline delta. Use the existing Astrobyte baseline when no personal profile exists. For requested local-only personalization, follow
adopt-skill-stack's delta path; use this machine interview only when machine-specific setup was requested. - Run
python3 scripts/install.py --operator <handle> --interviewin an interactive terminal. Relay every question to the user when the agent product cannot give the script direct terminal input. - Use detected agent products as evidence, not as consent. Confirm active products, preferred product, machine alias, delivery default, autonomy, skill profile, model environment, reviewer model, parallelism, unattended work, interactive and unattended external-action policies, Git workflow, human and per-product Git identities, tracker, docs path, compute, experiment budget, browser tools, and containers. When the working agreement names no reviewer, ask once which model to use and offer to record the answer there.
- Present the script's plan. Apply it only after the operator confirms.
- Run
python3 scripts/validate.pyandpython3 -m unittest discover -s tests -vfrom the repository. - Report the installed profile, machine alias, delivery default, destinations, routing locations, config path, backups, and manual follow-up, such as the Cursor Cloud User Rule in
docs/routing.md.
The setup is complete when python3 scripts/install.py --check passes and each selected harness can discover astrobyte-mode.
Preserve unrelated skills and machine configuration. Treat credentials, private repository access, and harness permission changes as separate user-authorized actions.
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.