CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

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

78%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.

The body is an exemplar of token efficiency and clean structure for a short instruction-only skill. Its main weakness is actionability: the required-adapter specs are incomplete and internally inconsistent with the description's runtime list, leaving gaps an executor would have to fill by guesswork.

Suggestions

Reconcile the runtime lists: add Required Adapters entries for Gemini CLI and Cursor (both named in the description) or explain how the Antigravity/Generic entries cover them.

Specify where the Codex plugin manifest lives and correct the Claude Code entry, which currently places 'command, agent, and skill adapter' all under `.claude/commands/`.

Include a one-line example of thin adapter text that 'points back to AGENTS.md' so the required adapter content is concrete rather than implied.

DimensionReasoningScore

Conciseness

Twenty-three lean lines where every bullet states a rule or a concrete path (e.g., '`.agentlas/global-commands.json` records the command each adapter exposes'); nothing explains what Claude already knows and nothing could be trimmed.

5 / 5

Actionability

Concrete file paths are given per runtime ('commands/<slug>.md', '.claude/commands/', 'antigravity/workflows/<slug>.md'), but key details are missing: no location for the Codex plugin manifest, no example adapter text, the imprecise 'command, agent, and skill adapter under `.claude/commands/`', and Gemini CLI/Cursor (named in the description) have no adapter specs while Antigravity appears only here.

3 / 5

Workflow Clarity

A simple single-purpose skill with a coherent Rules-to-Required-Adapters structure, but the single action is not fully unambiguous because the runtime lists differ between the description ('Gemini CLI, Cursor'), the Rules ('.cursor/'), and Required Adapters (neither).

4 / 5

Progressive Disclosure

Under 50 lines with no external references needed, organized into clear 'Rules' and 'Required Adapters' sections — matching the simple-skill guideline for full marks.

5 / 5

Total

17

/

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 description with explicit what-and-when structure, natural trigger terms, and a distinct niche. Minor gaps in action specificity (what an adapter consists of) and keyword synonyms keep specificity and trigger quality just below full marks.

DimensionReasoningScore

Specificity

Names the domain and concrete targets ('Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core'), but the action coverage is limited to 'creating adapters' without enumerating what adapters involve (manifest, command, skill files).

4 / 5

Completeness

Explicitly answers both 'what' ('creating ... runtime adapters from one canonical agent core') and 'when' with two concrete trigger clauses ('Use when ...', 'Use whenever a generated repo needs multiple AI runtimes without duplicating instructions').

5 / 5

Trigger Term Quality

Good natural keyword coverage ('Codex', 'Claude Code', 'Gemini CLI', 'Cursor', 'AGENTS.md', 'runtime adapters', 'multiple AI runtimes'), though common variations like 'adapter', 'mirror', or 'multi-runtime support' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — generating multi-runtime adapters from a canonical core with named CLIs — making it unlikely to trigger for the wrong skill.

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

agentlas-ai/Agentlas-OS

Path

.agents/skills/runtime-adapters/SKILL.md

Revision

2b4e27b

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill