create-subcommand
Add a new CLI subcommand to an agent binary (agent, cluster-agent, etc.)
62
55%
Does it follow best practices?
Impact
Pending
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
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 specific task (adding CLI subcommands to agent binaries) but is too terse and lacks a 'Use when...' clause, making it difficult for Claude to reliably select this skill at the right time. It would benefit from listing concrete steps involved and explicit trigger conditions.
Suggestions
Add a 'Use when...' clause with trigger terms like 'add subcommand', 'new CLI command', 'agent binary command', 'cobra command', or 'extend CLI'.
List more specific actions involved, such as 'scaffolds command file, registers subcommand in root command, adds flags and arguments, wires up handler logic'.
Include common user phrasings and file/framework references (e.g., 'cobra', 'command-line interface', 'CLI plugin') to improve trigger term coverage.
| 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 CLI subcommand to an agent binary) 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 fairly thin, warranting 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 command'. The parenthetical examples help but coverage is incomplete. | 2 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to CLI subcommands for agent binaries, which narrows the domain, but could overlap with general code scaffolding or CLI development skills. The mention of specific binary types (agent, cluster-agent) helps but isn't enough for a clear niche. | 2 / 3 |
Total | 7 / 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 for adding CLI subcommands to Datadog Agent binaries. Its main strength is the clear workflow with decision points and verification steps. The primary weakness is that it depends heavily on reading reference files at runtime rather than providing inline code templates, which reduces immediate actionability—if those reference files change or are unavailable, the skill becomes less useful.
Suggestions
Add a minimal inline code template showing the skeleton of a `Commands()` function and cobra.Command setup for the simple pattern, so Claude doesn't fully depend on reading external reference files.
Include a brief example of what the registration import and slice entry look like in `subcommands.go` to make Step 4 fully copy-paste ready.
| 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 verification steps (build, test help output, lint). The information-gathering step is well-structured with conditional logic (skip questions if arguments provided), and the shared-vs-local decision point is clearly articulated. | 3 / 3 |
Progressive Disclosure | The skill references external files in the repo (reference commands, registration files) which is appropriate, but there are no bundle files to support it. The content is well-organized with tables and numbered steps, but the reference pattern files are critical dependencies that exist only in the repo, not in the skill bundle. | 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
0f36ad4
- 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.