create-subcommand
Add a new CLI subcommand to an agent binary (agent, cluster-agent, etc.)
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/create-subcommand/SKILL.mdQuality
Discovery
40%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 clear, narrow task (adding CLI subcommands to agent binaries) which gives it good distinctiveness, but it lacks a 'Use when...' clause and doesn't enumerate the specific steps or artifacts involved. It would benefit from explicit trigger guidance and more concrete action details.
Suggestions
Add a 'Use when...' clause with trigger terms like 'add subcommand', 'new CLI command', 'agent binary command', 'cobra command'.
Expand the capability description with more concrete actions, e.g., 'Scaffolds command file, registers the subcommand in the root command, adds flags and argument parsing, and wires up handler logic'.
Include common natural language variations users might use, such as 'command line', 'new command', 'CLI tool', or framework-specific terms like 'cobra' if applicable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names a specific domain (CLI subcommand for agent binaries) and one action (add), but doesn't list multiple concrete actions or elaborate on what the process involves beyond 'add a new CLI subcommand'. | 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, missing 'Use when' caps completeness at 2, and the 'what' is also thin, 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', or 'CLI flag'. The parenthetical examples help but coverage is incomplete. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche—adding CLI subcommands to agent binaries—which is unlikely to conflict with other skills. The mention of specific binary types (agent, cluster-agent) further narrows the scope. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
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 that clearly maps out the workflow for adding a CLI subcommand to any Datadog Agent binary. Its main strength is the efficient use of lookup tables and a clear multi-step process with verification. Its main weakness is the lack of inline code templates or bundle files—Claude must read external codebase files to understand the actual code patterns, which makes the skill less self-contained and less immediately actionable.
Suggestions
Add a minimal inline code skeleton for at least the 'Simple (no Fx)' pattern so Claude has a copy-paste-ready template without needing to read external files first.
Consider adding a bundle file (e.g., TEMPLATES.md) with annotated code templates for each of the three patterns (simple, config/IPC, shared) to improve progressive disclosure and actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The table of agent binaries is a necessary lookup reference, instructions are terse but complete, and there's no explanation of what Cobra or Fx are—Claude already knows. No wasted tokens. | 3 / 3 |
Actionability | The skill provides specific file paths, reference files to read, and build/test commands, which is good. However, it relies on reading external reference files rather than providing inline code templates or snippets for the command structure, meaning Claude must infer the actual code to write rather than having copy-paste-ready templates. | 2 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation at the end (build, test help output, lint). The information-gathering step is well-structured with conditional logic for shared vs. agent-specific placement. The workflow covers the full lifecycle from gathering requirements to verification. | 3 / 3 |
Progressive Disclosure | The skill is well-organized with tables and clear sections, but there are no bundle files to support the references to external patterns. The skill references multiple files in the codebase (e.g., `cmd/agent/subcommands/version/command.go`) as templates but doesn't provide any supplementary documentation or examples in companion files. For a skill of this complexity, a brief inline code skeleton or a bundled template file would improve navigation. | 2 / 3 |
Total | 10 / 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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
- Commit
a41685a
- 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.