worktree-ports

Discover and use stable per-app ports assigned to a local monorepo worktree. Use when starting, opening, testing, or debugging local apps, or when worktree slots, localhost ports, PORT, app URLs, or .worktree-env.json are involved.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, actionable body with strong progressive disclosure into real bundled scripts. The main weakness is workflow clarity: the guidance is a flat bullet list without explicit validation checkpoints for what is effectively a configuration-validation workflow.

Suggestions

Convert the bullets into a short numbered workflow with an explicit validation checkpoint, e.g. after running `bun dev:info --json`, verify the returned app URL/port before starting the app.

Add one copy-paste-ready example showing `bun dev:info --json` output shape and a minimal `.worktree-env.json` so the common case is fully executable from the skill alone.

Include a brief validate-fix-retry loop for when an app's offset conflicts or a port falls outside the valid range, since the bundled resolver throws on these cases.

Dimension	Reasoning	Score
Conciseness	Every bullet earns its place with concrete commands, filenames, and template syntax; no padding or explanation of concepts Claude already knows. Lean and assumes Claude's competence.	5 / 5
Actionability	Concrete commands (`bun dev:info --json`, `bun dev*` scripts), specific files (`.worktree-env.json`, `.env.worktree.local`), and template syntax (`{apps.<name>.url}`) are present, but there is no copy-paste-ready example of the resolver invocation/output or a sample `.worktree-env.json`, leaving minor gaps versus fully executable examples.	4 / 5
Workflow Clarity	The bullets imply a sequence ('before accessing local apps') but are a flat list rather than numbered steps, and there are no explicit validation checkpoints or validate-fix-retry feedback loops for the configurable port/env setup, which the rubric caps at 3 for risky config operations without validation.	3 / 5
Progressive Disclosure	A concise overview body that signals the bundled implementation one level deep ('The generic resolver and command wrapper are bundled in `scripts/`'), with real referenced files verified to exist in scripts/ and assets/; content is appropriately split and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A precise, well-triggered description that answers both what and when with concrete natural-language terms and a distinctive filename. The only minor gap is that the 'what' is a single compound action rather than an enumerated list of concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('stable per-app ports assigned to a local monorepo worktree') and concrete actions ('Discover and use'), plus several specific trigger activities, but it is a single compound action rather than multiple distinct concrete actions, so it sits below the comprehensive anchor at 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Discover and use stable per-app ports assigned to a local monorepo worktree') and 'when' ('Use when starting, opening, testing, or debugging local apps, or when worktree slots, localhost ports, PORT, app URLs, or .worktree-env.json are involved') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms including 'starting, opening, testing, or debugging local apps', 'worktree slots', 'localhost ports', 'PORT', 'app URLs', and the '.worktree-env.json' file extension — synonyms and the concrete filename are all present.	5 / 5
Distinctiveness Conflict Risk	A clear niche (worktree-specific port allocation) with highly specific triggers and the distinctive '.worktree-env.json' filename, giving minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: FranciscoMoretti/chat-js
Path: .agents/skills/worktree-ports/SKILL.md
Commit: 14113a9

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.