astrobyte-verify-project
Skill1 starsChanged 14 days agoMITView on GitHub
Create or maintain a project-local skill that proves CLI, API, UI, service, model, pipeline, or deployment behavior through the real runtime surface. Use when a repository lacks a repeatable verification path or its verification map has drifted.
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
- 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
- setup-astrobyte-skillsSkill
- 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
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 22
Ask the user only for choices the repository cannot reveal.
- Distinctive: line 38
Use relative paths and portable commands.
- Distinctive: line 45
Add newly important features and remove paths that no longer exist.
- Distinctive: line 46
Run the updated skill from a clean starting state.
≈ “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
Astrobyte verify project
Discover
Interview the repository before the user. Find:
- primary user and operator surfaces
- setup and launch commands
- health checks and required services
- representative features and data paths
- observable evidence for success and failure
- cleanup and idempotence requirements
- existing tests, smoke scripts, browser flows, benchmarks, and golden artifacts
Ask the user only for choices the repository cannot reveal.
Create
Create .agents/skills/verify-<project>/SKILL.md with:
- prerequisites and doctor checks
- deterministic launch steps
- a feature map from capability to exact drive action and evidence
- focused verification commands
- real-surface checks for CLI, HTTP, browser, model, artifact, or deployment as applicable
- cleanup and recovery
- known expensive checks and when to run them
When the project needs human acceptance before merge, also define one revision-identifiable preview path appropriate to the product: a private web URL, mobile install link, desktop artifact, CLI invocation, or API smoke target. Include readiness evidence, access boundaries, the exact revision under test, and cleanup. Prefer an existing private project path over adding a hosted preview service.
Use relative paths and portable commands. Keep secrets and machine-specific values in environment variables or local configuration.
Maintain
- Compare the feature map with current source, routes, commands, configs, and docs.
- Drive every mapped feature in one live session when affordable.
- Correct only drift proven by source or runtime evidence.
- Add newly important features and remove paths that no longer exist.
- Run the updated skill from a clean starting state.
The work is complete when another agent can reproduce the verification without undocumented knowledge and every mapped claim has observed evidence.
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.