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.

73

Quality

92%

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

81%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 highly actionable with complete, executable code patterns and a well-sequenced workflow ending in a verification checklist plus error-recovery guidance. Its main weakness is redundancy — key rules (tracked(), __exit__, named exports) are restated several times — and the long inline Examples/Common Issues sections that could be split into reference files.

Suggestions

Consolidate the repeated rules (tracked() wrapping, __exit__ error pattern, named async exports) into one authoritative statement, and reduce the Critical section to pointers so each rule appears once instead of 3-4 times across Critical, Instructions, the step-5 checklist, and Common Issues.

Move the Examples section and Common Issues catalog into separate reference files (e.g., references/examples.md, references/troubleshooting.md), keeping only the export/registration patterns and one compact example inline in SKILL.md.

Trim low-value bullets such as "Import only what you need (avoid kitchen-sink imports)" and merge the overlapping telemetry Common Issues entries into one.

DimensionReasoningScore

Conciseness

The tracked() wrapper, __exit__ pattern, and named-export rule each appear three to four times across the Critical section, Instructions, the step-5 checklist, and Common Issues (e.g., "wrapped with tracked() for telemetry" repeats as step 3, step 5, and two Common Issues entries). It is mostly efficient with no basic-concept padding, but the duplication is more than minor, fitting anchor 3 rather than 4.

3 / 5

Actionability

Complete executable TypeScript is provided for the command file (statusCommand), registration in cli.ts, the subcommand pattern, and the option parser (parseAgentOption), with exact import statements and .js ESM extensions. Copy-paste-ready examples cover the common cases (simple command, subcommand, option parsing), matching the top anchor.

5 / 5

Workflow Clarity

A clear five-step sequence ends with an explicit validation checkpoint ("Verify before proceeding: Function exports correctly... Command is registered with tracked() wrapper"), and the Common Issues section provides Issue→Cause→Fix feedback loops for error recovery. This matches the anchor requiring explicit validation steps, feedback loops, and a checklist.

5 / 5

Progressive Disclosure

No bundle files exist, and the single body is well-sectioned (Critical, Instructions, Examples, Common Issues) with clearly labeled examples — good structure with one-level (zero) references. However, the ~70-line Examples section and the Common Issues catalog are inlined where a separate examples/reference file would reduce the main body, a minor organization gap fitting anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it names concrete actions with specific artifacts, provides natural trigger phrases including a path-based trigger, and adds explicit negative boundary guidance. It clearly answers what, when, and when-not without padding.

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 multiple concrete actions with named artifacts (Commander.js, src/cli.ts, tracked()). Coverage spans creation, registration, telemetry, and options with no gaps, matching the comprehensive anchor rather than the 'minor gaps' anchor at 4.

5 / 5

Completeness

It explicitly answers what ("Creates a new CLI command... Handles command registration... telemetry tracking... option parsing") and when ("Use when user says add command, new CLI command, create subcommand"), plus an explicit when-not clause. Both halves are concrete and explicit, matching the top anchor.

5 / 5

Trigger Term Quality

"Use when user says add command, new CLI command, create subcommand, or adds files to src/commands" provides natural user phrasings plus a path-based trigger, and "Do NOT use for modifying existing commands or fixing bugs" adds negative triggers. Coverage includes synonyms (command/subcommand) and concrete paths, matching the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

The niche is distinct (new CLI commands in this codebase's Commander.js/tracked() pattern) and the explicit exclusion "Do NOT use for modifying existing commands or fixing bugs in existing commands" sharply reduces mis-triggering. Minimal conflict risk with related skills.

5 / 5

Total

20

/

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.