portal

Continue a coding session on a paired always-on computer. Use when work must survive closing the primary laptop, needs remote computer-use testing, or should run on a scheduled/self-hosted execution host.

Quality

89%

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

88%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 tight, well-structured workflow skill with explicit verification checkpoints and recovery feedback loops that assume Claude's competence. The main gap is actionability: it relies on concrete prose and field names rather than literal executable commands, which suits an instruction-only skill but leaves a small gap versus copy-paste-ready guidance.

Suggestions

Add a few literal executable commands (e.g., the git snapshot/fetch commands or a sample run-enqueue command) to lift actionability toward copy-paste ready.

If detailed field schemas or recovery playbooks grow, split them into one-level-deep reference files and link them explicitly to strengthen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean, imperative, and assumes Claude's competence (it never explains what git, worktrees, or relays are); every section earns its place with no padded exposition.	5 / 5
Actionability	Guidance is concrete and specific (e.g., branch "portal/<timestamp>-<id>", "envPolicy: \"load-local\"", "metadata.executionResidence" with "kind: \"portal\"") with strong diagnostic steps in Operator recovery, but it provides no literal copy-paste commands, so it stops short of fully executable code.	4 / 5
Workflow Clarity	A numbered 5-step Workflow is paired with an explicit Verification checklist (paired host, heartbeating, fetched commit, clean detached worktree, remote workspace metadata) and an Operator recovery feedback loop (retry one bounded run, read remote result), giving clear validation checkpoints for a destructive/batch handoff.	5 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (Workflow, Existing chat transfer, Execution residence, Verification, Operator recovery, Don't, Related skills) with no nested references and a self-contained structure, but it exceeds the ~50-line simple-skill threshold and the Related skills pointers are skill names rather than bundle-file references.	4 / 5
	Total	18 / 20 Passed

Description

87%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 strong, third-person description that clearly answers both what it does and when to use it, with concrete and distinctive trigger phrases. Minor room to broaden trigger-term synonyms and surface a few more concrete capabilities.

Suggestions

Add one or two plain-language trigger synonyms (e.g., "keep a session running after I disconnect", "hand off to another machine") to broaden natural keyword coverage.

Consider naming an additional concrete capability beyond "continue a coding session" to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Continue a coding session on a paired always-on computer") plus several concrete scenarios (survive laptop close, remote computer-use testing, scheduled/self-hosted host), giving specific rather than vague guidance, though it centers on one core action rather than a comprehensive list of many.	4 / 5
Completeness	It explicitly states both what ("Continue a coding session on a paired always-on computer") and when ("Use when work must survive closing the primary laptop, needs remote computer-use testing, or should run on a scheduled/self-hosted execution host") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like "survive closing the primary laptop", "remote computer-use testing", and "scheduled/self-hosted execution host" give good keyword coverage, though some terms ("paired always-on computer", "self-hosted execution host") lean technical and a few plain synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (paired always-on computer handoff for coding sessions) with distinct triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/portal/SKILL.md
Commit: a941a2e

Reviewed: 9 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.