runtime-adapters

Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.

Quality

81%

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

72%

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

A concise, well-organized body that names the right files per runtime but lacks file-level templates and validation steps. Adding minimal structure templates and a consistency check would lift the weaker dimensions.

Suggestions

Add minimal templates or field lists for each adapter file (e.g. the plugin manifest JSON keys and the .gemini/commands/<slug>.toml shape) so the guidance is copy-paste ready rather than naming files only.

Include an explicit verification step, such as confirming every adapter's text points back to AGENTS.md and that .agentlas/global-commands.json records the command, to give this batch operation a validation checkpoint.

Provide a short ordered procedure for generating the adapters (e.g. write AGENTS.md core first, then derive each adapter, then register in global-commands.json) so the multi-runtime task has a clear sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with every line carrying information and no padding or explanation of concepts Claude already knows.	3 / 3
Actionability	It names concrete paths and per-runtime file targets, but as an instruction-only skill it stops short of showing file structure or templates (e.g. the manifest JSON shape or the .toml command format), leaving key details missing rather than copy-paste ready.	2 / 3
Workflow Clarity	The Required Adapters list functions as a set of targets rather than a sequenced procedure, and there are no validation checkpoints to confirm each adapter correctly points back to AGENTS.md or stays consistent across runtimes, which caps clarity at 2 for this batch operation.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into two clear sections (Rules, Required Adapters), so the simple-skill provision applies.	3 / 3
	Total	10 / 12 Passed

Description

90%

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, well-scoped description with explicit what/when triggers and natural product-name keywords. The only weakness is that it leans on a single action verb rather than enumerating multiple distinct capabilities.

Dimension	Reasoning	Score
Specificity	It names a concrete domain (canonical agent core, multiple AI runtimes) and lists five specific runtime targets, but the action set is essentially a single verb ("creating ... runtime adapters") rather than multiple distinct concrete actions, so it is not comprehensive enough for the top anchor.	2 / 3
Completeness	It explicitly states what the skill does ("creating ... runtime adapters from one canonical agent core") and when to use it ("Use when creating ..." and "Use whenever a generated repo needs multiple AI runtimes without duplicating instructions"), satisfying both what and when.	3 / 3
Trigger Term Quality	It uses the exact product names a user would naturally say ("Codex", "Claude Code", "Gemini CLI", "Cursor", "AGENTS.md") with explicit "Use when" / "Use whenever" triggers, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The niche is highly specific (multi-runtime adapters derived from one canonical core) and anchored to named products, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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: agentlas-ai/Agentlas-OS
Path: .agents/skills/runtime-adapters/SKILL.md
Commit: 2eb39ad

Reviewed: 4 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.