agent-creator

Create new OpenCode agents with a gpt-5.2-codex default.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/agent-creator/SKILL.md

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 content is a tight, actionable reference: concrete commands, exact file paths, and a complete minimal template, with no padding or generic explanation. Its only weaknesses are minor redundancy between the two setup sections and the absence of a verification step after agent creation.

Suggestions

Merge or cross-reference the "Quick Usage" and "First-Time Setup" sections, since both center on running "opencode agent create", to remove redundancy.

Add a verification step after creation (e.g., checking that the agent appears in the agents list or that the file exists at the expected path).

Show one concrete filled-in example of the tool access configuration instead of only "adjust tools as needed".

Dimension	Reasoning	Score
Conciseness	The body is lean and OpenCode-specific (commands, paths, template) with no explanation of concepts Claude already knows; however, "opencode agent create" is described in both "Quick Usage" and "First-Time Setup", a minor redundancy that keeps it below the 'every token earns its place' anchor.	4 / 5
Actionability	Concrete executable guidance is present: the "opencode agent create" command, exact agent file locations, and a copy-paste-ready YAML template with per-tool flags. Minor gaps (the template's description line is a placeholder and "adjust tools as needed" lacks example configurations) keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	The sequence is clear (run create, choose scope, paste the template, adjust tools) with correct separation of already-configured vs first-time cases, but "Already Configured" is never defined and there is no step to verify the agent was created, so checkpoints are incomplete rather than explicit.	4 / 5
Progressive Disclosure	The body is under 50 lines, well-organized into clearly labeled sections, needs no external reference files (none exist in the bundle), and points to the official docs URL for deeper material, matching the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

50%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.

The description states a clear, single capability with a specific default model, but it reads more like a one-line summary than a trigger-rich skill description. It lacks any "use when" guidance and natural trigger synonyms, which limits discoverability and completeness.

Suggestions

Add an explicit trigger clause, e.g., "Use when creating or customizing OpenCode agents/subagents or when the user mentions agent files in .opencode/agents."

Include natural trigger variations such as "subagent", "custom agent", "agent file", and ".opencode/agents" so users' phrasing matches the description.

Broaden capability coverage slightly (e.g., "create and configure agents: set mode, model, and per-agent tool access") to improve specificity and completeness.

Dimension	Reasoning	Score
Specificity	"Create new OpenCode agents with a gpt-5.2-codex default" names the domain and 1-2 concrete actions (creating agents, applying a default model) but does not cover related actions like editing agents, configuring tool access, or setting modes, so it is not comprehensive.	3 / 5
Completeness	The "what" is clear (create OpenCode agents with a default model), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"OpenCode" and "agents" are relevant keywords, but common natural phrases users would say are missing (e.g., "subagent", "custom agent", "agent file", ".opencode/agents"), matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	"OpenCode agents" is somewhat specific and unlikely to trigger for unrelated domains, but it could still overlap with generic agent-creation or assistant-configuration skills, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	12 / 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: trackdubllc/Babel-Player-Alpha
Path: .opencode/skills/agent-creator/SKILL.md
Commit: 2237ca2

Reviewed: 13 hours 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.