CtrlK
BlogDocsLog inGet started
Tessl Logo

create-subcommand

Add a new CLI subcommand to an agent binary (agent, cluster-agent, etc.)

49

Quality

55%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/create-subcommand/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured, concise skill with a clear multi-step workflow and good decision-tree logic for different subcommand patterns. Its main weakness is the lack of inline code examples or bundled reference files—it relies on reading existing repo files at runtime, which makes it less self-contained and less immediately actionable. The verification steps are solid with build, test, and lint checks.

Suggestions

Add inline code snippets showing the minimal structure of a simple command.go and the registration pattern in subcommands.go, so Claude doesn't need to read reference files to understand the expected output.

Bundle the reference files (e.g., version/command.go, hostname/command.go) or include trimmed versions as examples within the skill to make it self-contained.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It assumes Claude knows Go, Cobra, and Fx patterns. Every section serves a purpose—the table of agent binaries is a quick reference, not an explanation. No unnecessary preamble or concept explanations.

3 / 3

Actionability

The skill provides concrete file paths, build commands, and naming conventions, but lacks executable code examples. It relies on reading reference files at runtime rather than showing the actual code patterns inline (e.g., what a simple command.go looks like, what the import/registration looks like). This makes it dependent on external files that aren't bundled.

2 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced with explicit verification steps (build, test help output, lint). The information-gathering step properly handles pre-filled arguments. The decision points (simple vs Fx, shared vs not) are clearly mapped to different paths.

3 / 3

Progressive Disclosure

The skill references multiple external files (reference commands, registration files, command.go) for reading at runtime, which is good progressive disclosure in principle. However, no bundle files are provided, so the skill depends entirely on files it doesn't control. The content itself is well-structured with tables and clear sections, but the lack of any bundled reference material means Claude must find and read repo files each time.

2 / 3

Total

10

/

12

Passed

Description

32%

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 identifies a reasonably specific task—adding CLI subcommands to agent binaries—but lacks a 'Use when...' clause, which is critical for skill selection. It also doesn't enumerate the concrete steps or artifacts involved, and misses common user-facing trigger terms that would help Claude match this skill to user requests.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to add a new CLI subcommand, register a command handler, or extend an agent binary's command-line interface.'

Include more natural trigger terms users might say, such as 'command line', 'new command', 'cobra command', 'CLI argument', or 'subcommand handler'.

List more specific concrete actions, e.g., 'Scaffolds command files, registers subcommands in the command tree, adds flags and arguments, and wires up command handlers for agent binaries.'

DimensionReasoningScore

Specificity

Names the domain (CLI subcommand for agent binaries) and a specific action (add a new CLI subcommand), but doesn't list multiple concrete actions or detail what the process involves (e.g., registering commands, adding flags, writing help text).

2 / 3

Completeness

Describes what (add a new CLI subcommand) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also only partially described, so this scores a 1.

1 / 3

Trigger Term Quality

Includes relevant terms like 'CLI', 'subcommand', 'agent binary', 'cluster-agent', but misses common variations users might say such as 'command line', 'new command', 'cobra', 'CLI command', or 'add command'.

2 / 3

Distinctiveness Conflict Risk

Somewhat specific to CLI subcommands for agent binaries, which narrows the domain, but could overlap with general CLI development skills or agent configuration skills. The mention of specific binaries (agent, cluster-agent) helps but 'etc.' weakens distinctiveness.

2 / 3

Total

7

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
DataDog/datadog-agent
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.