CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Create new OpenCode skills with the standard scaffold.

50

Quality

53%

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/skill-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 delivers actionable templates and a reasonable scaffold checklist in a well-structured, self-contained form. It would benefit from tighter deduplication of templates and an explicit numbered workflow with validation checkpoints.

Suggestions

Collapse the frontmatter template and minimal skill template into one canonical template to remove redundancy and tighten conciseness.

Reframe the scaffold bullets as a numbered workflow with explicit validation checkpoints (e.g. verify .env ignored, confirm scripts/ present, dry-run the new skill).

Trim the "Notes from OpenCode docs" section to only non-obvious facts, relying on the existing reference link for basics.

DimensionReasoningScore

Conciseness

The body is mostly efficient but includes some redundancy (overlapping frontmatter and minimal-skill templates) and restates basic facts in "Notes from OpenCode docs" that could be trimmed.

3 / 5

Actionability

Provides copy-paste-ready bash ("mkdir -p .opencode/skills/<skill-name>"), concrete scaffold file lists, and full frontmatter/minimal templates, with only minor gaps.

4 / 5

Workflow Clarity

The scaffold is presented as a bulleted sequence with one verify step ("verify .env is not tracked"), but checkpoints are largely implicit and the steps are not a clearly numbered workflow with feedback loops.

3 / 5

Progressive Disclosure

Content is well-organized into clear sections (Trigger phrases, Frontmatter template, Quick Usage, .env, Minimal template, Notes, Reference) with no need for external bundle files; minor organization gaps keep it below 5.

4 / 5

Total

14

/

20

Passed

Description

46%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 purpose in concise third person but omits any trigger guidance, so Claude has little signal for when to invoke it. Adding a "Use when..." clause with 2-3 natural phrases would lift completeness and trigger quality substantially.

Suggestions

Append a "Use when" clause with 2-3 specific natural phrases, e.g. "Use when the user asks to 'create a skill', 'scaffold a new OpenCode skill', or 'turn this flow into a skill'".

Broaden the action list beyond a single verb to reduce overlap ambiguity, e.g. "Create, scaffold, and configure new OpenCode skills with standard files".

Include a concrete trigger synonym or file-path cue (e.g. ".opencode/skills/") to improve distinctiveness.

DimensionReasoningScore

Specificity

"Create new OpenCode skills with the standard scaffold" names the domain and one concrete action (create skills via a scaffold) but offers no broader coverage of what creation entails.

3 / 5

Completeness

A clear "what" is present but "when" is entirely missing, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Only generic keywords ("create", "skills") appear; there is no "Use when" clause or natural trigger phrase a user would actually say, so common variations are missing.

2 / 5

Distinctiveness Conflict Risk

The skill-creation niche is mostly distinct with only minor overlap risk against other meta/scaffolding skills, though the absence of explicit triggers weakens discrimination.

4 / 5

Total

12

/

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.