CtrlK
BlogDocsLog inGet started
Tessl Logo

adding-a-command

Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing. Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/. Do NOT use for modifying existing commands or fixing bugs in existing commands.

68

Quality

85%

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

The canonical home for this skill is adding-a-command in caliber-ai-org/ai-setup

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

Highly actionable content with complete executable examples, a clearly sequenced workflow with verification steps, and good single-file organization. The main weakness is redundancy: the error-signaling pattern and several Common Issues entries duplicate the Instructions and Critical sections.

Suggestions

Consolidate the throw new Error('__exit__') guidance into one canonical statement (e.g., the Critical section or step 2) and reference it elsewhere instead of restating it in step 5 and two Common Issues entries.

Make step 5's verification checklist executable by naming the concrete commands to run (e.g., the project's build or typecheck command) rather than advisory checks like "Verify the function exports correctly".

Trim Common Issues entries that merely restate Instructions (telemetry, option declaration, subcommand registration) to the ones covering genuinely new failure modes (module export errors, .ts vs .js import extensions).

DimensionReasoningScore

Conciseness

The body is dense and project-specific, assuming Claude's competence with TypeScript and Commander, but the throw new Error('__exit__') pattern is restated in four places (Critical, step 2, step 5, and two Common Issues entries), and Common Issues substantially restate the Instructions. It fits anchor 3 (mostly efficient but could be tightened) better than anchor 4, where over-explanation would be only minor.

3 / 5

Actionability

All three examples (simple command, subcommand, option parsing) include complete, copy-paste-ready code with exact export signatures, import paths with .js extensions, and registration snippets; the guidance is fully executable.

5 / 5

Workflow Clarity

Five clearly sequenced steps end in a "Verify before proceeding" checklist, and the Common Issues section provides cause/fix feedback loops. However, the verification checkpoints are advisory rather than executable (no build or typecheck command to run), leaving minor validation gaps that keep it below anchor 5.

4 / 5

Progressive Disclosure

No bundle files exist, so everything is in SKILL.md, which is appropriately sized and well-organized into Critical, Instructions, Examples, and Common Issues sections with clear headers. Minor gaps (stray --- separators between examples, no explicit navigation cues) keep it at anchor 4 rather than 5.

4 / 5

Total

16

/

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/when coverage, concrete file-level actions, natural trigger phrases, and clear negative boundaries. The only weakness is modest coverage gaps in the action list (error-signaling conventions are unmentioned) and a few missing trigger synonyms.

DimensionReasoningScore

Specificity

"Creates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts, telemetry tracking via tracked() wrapper, and option parsing" lists several concrete, file-anchored actions, but omits the error-signaling conventions that are central to the skill body, so coverage has minor gaps.

4 / 5

Completeness

It explicitly answers both what (create command file, register in cli.ts, telemetry via tracked(), option parsing) and when (concrete "Use when user says..." trigger phrases), and adds negative boundary guidance ("Do NOT use for modifying existing commands or fixing bugs").

5 / 5

Trigger Term Quality

"Use when user says add command, new CLI command, create subcommand, or adds files to src/commands/" provides good natural keyword coverage including a path-based trigger, but misses a few plausible user phrasings like "implement a command" or "wire up a command".

4 / 5

Distinctiveness Conflict Risk

The description is anchored to codebase-specific artifacts (Commander.js, src/commands/, src/cli.ts, tracked()) and explicitly excludes modifying or fixing existing commands, giving it a clear niche with minimal conflict risk.

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
caliber-ai-org/ai-setup
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.