CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 instruction skill that conveys canonical rules and per-runtime adapter requirements without padding. Adding minimal adapter content templates or a brief verification step would lift actionability and workflow clarity.

Suggestions

Provide a minimal example adapter file (e.g. a stub .claude/commands/<slug>.md) so guidance is copy-paste ready and actionability reaches 5.

Add a short verification step confirming each adapter points back to AGENTS.md and is recorded in .agentlas/global-commands.json, which would add a validation checkpoint to the workflow.

Consider an explicit ordering (e.g. author AGENTS.md first, then derive each adapter) to make the workflow sequence unambiguous.

DimensionReasoningScore

Conciseness

Lean and efficient: every line is either a canonical rule or a concrete per-runtime adapter spec, with no padding or explanation of concepts Claude already knows.

5 / 5

Actionability

Gives concrete, specific file paths and per-runtime adapter requirements (e.g. 'Codex: plugin manifest plus skill and commands/<slug>.md'); it stops short of providing adapter content templates, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

The Required Adapters list functions as a clear checklist of what to create per runtime, but there is no explicit sequencing or verification step across the adapters.

4 / 5

Progressive Disclosure

Under 50 lines with no external references needed and well-organized sections (Rules, Required Adapters), matching the simple-skill exception for a top score.

5 / 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, well-targeted description that clearly states both capability and trigger conditions with concrete product names. It could be marginally more comprehensive on action verbs and synonyms, but is otherwise exemplary.

DimensionReasoningScore

Specificity

Names the concrete domain (creating runtime adapters from a canonical agent core) and enumerates specific runtimes (Codex, Claude Code, Gemini CLI, Cursor, AGENTS.md); the action set is narrow (mainly 'creating adapters') so it is not a comprehensive 5.

4 / 5

Completeness

Explicitly answers both 'what' (creating runtime adapters from one canonical agent core) and 'when' (two 'Use when/whenever' clauses with concrete triggers), matching the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural product-name triggers users would say ('Codex', 'Claude Code', 'Gemini CLI', 'Cursor', 'AGENTS.md', 'multiple AI runtimes') with good coverage; a few synonymous phrasings are missing, keeping it just below 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (multi-runtime adapters from a canonical core) with specific named tools, making overlap with other skills minimal.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentlas-ai/Agentlas-OS
Reviewed

Table of Contents

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.