agentleFS
Sign inStart free
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/coding/starlight-devex-review/SKILL.md

starlight-devex-review

Skill1 starsChanged 4 months agoMITView on GitHub

Review an API, CLI, SDK, plugin, package, or installation flow for discoverability, safe defaults, actionable errors, compatibility, documentation, and time to verified value. Use before publishing a developer-facing interface or when onboarding friction is suspected.

1 other project uses a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    Test commands and examples in a supported environment.

    line 28
  2. Distinctive:

    Check names, types, defaults, help text, and error remediation.

    line 29
  3. Distinctive:

    Use the actual package, API schema, CLI help, and official runtime documentation.

    line 40
  4. Distinctive:

    Every documented command is copyable and scoped to a supported runtime.

    line 44

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Starlight DevEx Review

Purpose

Make the correct path easy to discover, safe to execute, and simple to verify without hiding prerequisites or host-specific limits.

When it fires

  • A public API, CLI, package, plugin, schema, or install guide changes.
  • Users must cross authentication, marketplace, configuration, or runtime boundaries.
  • Errors or setup steps are causing support load.

Inputs

  • Intended user and first successful outcome.
  • Supported environments, prerequisites, permissions, and version policy.
  • Interface definitions, examples, error messages, and telemetry/support evidence.

Workflow

  1. Trace discovery through install, configure, first action, verification, update, and removal.
  2. Test commands and examples in a supported environment.
  3. Check names, types, defaults, help text, and error remediation.
  4. Make host-specific approval, authentication, and compatibility steps explicit.
  5. Review versioning, deprecation, migration, rollback, and support ownership.
  6. Measure time and steps to verified value; report the observed context rather than a universal target.

Output contract

Return journey map, observed setup time, friction points, API/CLI findings, error-quality findings, compatibility/versioning findings, documentation gaps, prioritized fixes, and verification commands.

Tools & MCP

Use the actual package, API schema, CLI help, and official runtime documentation. Do not claim one-click installation when review, OAuth, admin consent, or manual verification remains.

Quality bar

  • Every documented command is copyable and scoped to a supported runtime.
  • Errors state what failed, where, and the safest next action.
  • Removal and rollback are documented alongside installation.
  • Current limitations are visible before a user invests time.

Example

Input: “Review our cross-runtime plugin install.”

Good output: distinguish native marketplace install, local package install, staged adapter, and generic MCP connection; verify each path independently; and label unverified hosts honestly.

Built on SIP — Starlight Intelligence Protocol Vertical: starlight-agent-skills · portable capability layer

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free