CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-creator

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

58

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/agent-creator/SKILL.md
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 a tight, well-structured, actionable guide with a copy-paste template and concrete commands, scoring well across all dimensions. Minor gains would come from clarifying the command-vs-paste workflow and trimming the redundant already-configured/first-time sections.

DimensionReasoningScore

Conciseness

The body is efficient with a copy-paste template and one-line command, assuming Claude's competence; the only trimmable redundancy is the split between 'Quick Usage (Already Configured)' and 'First-Time Setup', which restates the same command, keeping it just below the lean-every-token-earns-its-place anchor 5.

4 / 5

Actionability

It provides executable guidance — `opencode agent create` and a complete copy-paste agent template with frontmatter — but the relationship between the interactive command and the manual paste step is slightly muddled, leaving a minor gap versus the fully-copy-paste-ready anchor 5.

4 / 5

Workflow Clarity

The First-Time Setup gives a clear two-step sequence (run command, choose scope, paste template, adjust tools); creating a config file is non-destructive so the validation cap does not apply, but the already-configured vs first-time split introduces minor ambiguity rather than a single unambiguous path.

4 / 5

Progressive Disclosure

The skill is under 50 lines with well-organized sections and no bundle files needed; its single external pointer (official OpenCode docs URL) is one level deep and clearly signaled, so the simple-skill exception lets well-organized sections score 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 is specific and distinct but incomplete: it states what the skill does concretely yet omits any 'when to use it' trigger guidance, which caps its completeness. Adding a Use-when clause with natural trigger phrases would lift the two lowest dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to create, add, or set up a new OpenCode agent.'

Broaden trigger terms with natural synonyms users say ('make', 'add', 'configure', 'scaffold an agent') to improve trigger_term_quality.

Optionally mention scope variants ('project or global agent') to lift specificity toward a second concrete action.

DimensionReasoningScore

Specificity

It names the domain ('OpenCode agents') and a concrete action ('Create new') plus a specific configured default ('gpt-5.2-codex'), but offers only one action with no broader coverage, fitting the 'names domain and 1-2 concrete actions' anchor rather than the multi-action anchor 5.

3 / 5

Completeness

It clearly answers 'what' (create OpenCode agents with a default model) but provides no 'when' guidance at all, hitting the explicit cap of 3 for a missing 'Use when…' clause and matching the clear-what / missing-when anchor exactly.

3 / 5

Trigger Term Quality

Natural terms like 'create' and 'OpenCode agents' appear, but there is no 'Use when…' trigger clause and common synonyms ('make', 'add', 'configure') are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

'Create new OpenCode agents with a gpt-5.2-codex default' carves a clear niche with low overlap risk, though the bare term 'agents' could brush against generic agent-tooling skills, placing it at 'mostly distinct; minor overlap risk' rather than the fully-distinct anchor 5.

4 / 5

Total

13

/

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
trackdubllc/Babel-Player-Alpha
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.