command-creator

Create OpenCode custom commands for repeatable tasks.

Quality

53%

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/command-creator/SKILL.md

Quality

Content

52%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 original authored sections are actionable and well-sequenced, but the file is dominated by a verbatim docs-page dump full of nav chrome, footers, and typos that wrecks conciseness and should live behind the already-provided reference link. Splitting that snapshot into a reference file and trimming it would lift both conciseness and progressive_disclosure.

Suggestions

Remove the inlined 'Docs snapshot' (lines ~45-352) and rely on the existing https://opencode.ai/docs/commands/ link, or move a trimmed version into ./references/commands-reference.md.

Delete navigation chrome and footer artifacts ('Skip to content', '⌘K', '© Anomaly', 'Join our Discord') and fix the typos ('theutput', 'ithe command') if any snapshot content is retained.

Reconcile the model ids used in examples (gpt-5.2-codex vs anthropic/claude-3-5-sonnet) so the copy-paste examples are internally consistent.

Dimension	Reasoning	Score
Conciseness	The original top section is lean, but ~300 lines are a raw pasted 'Docs snapshot' including navigation chrome ('Skip to content', '⌘K', 'GitHub', 'GitLab'), a footer ('© Anomaly', 'Join our Discord'), repeated examples, stale date 'Jan 24, 2026', and typos ('theutput', 'ithe'), which is noticeable padding Claude could derive or fetch, fitting the 2 anchor rather than 3.	2 / 5
Actionability	Provides concrete, copy-paste-ready guidance — `mkdir -p .opencode/commands`, a full command-file example with frontmatter, and explicit `$ARGUMENTS`/`$1`/`!\`command\``/`@file` syntax — with only minor gaps (e.g., inconsistent model ids across examples), matching the 4 anchor of mostly-executable guidance.	4 / 5
Workflow Clarity	As a simple single-purpose skill it gives a clear unambiguous sequence (mkdir the directory, create the .md with frontmatter + template, run /name), with most checkpoints implied; it is not a destructive/batch operation so the cap does not apply, fitting between 4 and 5 but held at 4 by the absence of any verify-the-command-works checkpoint.	4 / 5
Progressive Disclosure	No bundle files exist and the body inlines a massive docs snapshot that clearly belongs in an external reference (a docs link is already given at line 42), matching the 2 anchor where content that should be in a separate file is inlined rather than the 3 anchor of partial structure.	2 / 5
	Total	12 / 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 concise and on-domain but stops at naming the task without any explicit usage trigger, which caps completeness at 3. It is clearly distinct within the OpenCode ecosystem yet lacks the keyword richness that would lift trigger-term quality.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user wants to add or customize slash commands in OpenCode').

Include natural synonyms and concrete file paths in the description, such as 'slash commands', '.opencode/commands/', or 'opencode.json'.

List 2-3 concrete sub-actions (e.g., 'define command templates, wire up $ARGUMENTS, override built-in commands') to lift specificity from 3 to 4.

Dimension	Reasoning	Score
Specificity	Quotes 'Create OpenCode custom commands for repeatable tasks' — names the domain and one concrete action (create) but does not enumerate several specific actions like frontmatter config, argument templating, or file placement, so it sits at the 3 anchor rather than 4.	3 / 5
Completeness	It clearly states the 'what' (create OpenCode custom commands) but provides no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('custom commands', 'repeatable tasks', 'OpenCode') but misses common natural variations users would say ('slash commands', 'opencode commands', '.opencode/commands'), matching the 3 anchor for some keywords with missing synonyms.	3 / 5
Distinctiveness Conflict Risk	Scoped tightly to 'OpenCode custom commands', a distinct niche with minor overlap risk against generic command/skill-creation skills, fitting the 4 anchor rather than 5 because 'custom commands' alone is not uniquely distinctive.	4 / 5
	Total	13 / 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/command-creator/SKILL.md
Commit: 2237ca2

Reviewed: 6 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.