cli-design
Design and build agent-first CLIs with HATEOAS JSON responses, context-protecting output, and self-documenting command trees. Use when creating new CLI tools, adding commands to existing CLIs (joelclaw, slog), or reviewing CLI design for agent-friendliness. Triggers on 'build a CLI', 'add a command', 'CLI design', 'agent-friendly output', or any task involving command-line tool creation.
90
88%
Does it follow best practices?
Impact
94%
1.64xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a specific niche (agent-first CLI design), lists concrete capabilities, and provides explicit trigger guidance with both 'Use when' and 'Triggers on' clauses. The description is concise yet comprehensive, uses third-person voice correctly, and includes enough domain-specific terminology to be highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Design and build agent-first CLIs', 'HATEOAS JSON responses', 'context-protecting output', 'self-documenting command trees'. These are concrete, specific capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (design/build agent-first CLIs with HATEOAS JSON, context-protecting output, self-documenting command trees) and 'when' (explicit 'Use when...' clause with specific trigger scenarios and a 'Triggers on...' list). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'build a CLI', 'add a command', 'CLI design', 'agent-friendly output', 'command-line tool creation'. Also mentions specific CLI names (joelclaw, slog) for disambiguation. Good coverage of natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: agent-first CLI design with HATEOAS JSON is very specific and unlikely to conflict with general coding skills or other tool-building skills. The mention of specific CLI names (joelclaw, slog) and domain-specific terms like 'context-protecting output' further distinguish it. | 3 / 3 |
Total | 12 / 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 high-quality, highly actionable skill with excellent concrete examples, clear JSON schemas, and a thorough checklist. Its main weakness is length — the streaming protocol, type definitions, and Redis patterns could be extracted into referenced files to keep the SKILL.md as a concise overview. The content is well-structured with clear sections but would benefit from progressive disclosure to separate the core principles from the advanced streaming protocol.
Suggestions
Extract the Streaming Protocol (NDJSON/ADR-0058) section into a separate STREAMING.md file and reference it from the main skill with a one-line summary
Move the TypeScript type definitions and Redis subscription patterns into a separate REFERENCE.md to reduce the main document's token footprint
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly well-targeted, but it's quite long (~350+ lines). Some sections like the streaming protocol and Redis subscription patterns are very detailed and could be split into separate reference files. The anti-patterns table partially duplicates principles already stated. However, it generally avoids explaining things Claude already knows. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete JSON envelope schemas, executable TypeScript code examples, specific bash commands for building/installing, complete type definitions, and a detailed checklist for new commands. Every principle is backed by copy-paste-ready examples. | 3 / 3 |
Workflow Clarity | The 'Adding a new command' section provides a clear 7-step sequence. The checklist at the end serves as a validation checkpoint. Error handling is explicitly covered with the error envelope pattern including fix fields. The streaming section has clear cleanup requirements (SIGINT handling, timeouts). | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document that could benefit from splitting. The streaming protocol (ADR-0058), TypeScript types, and Redis subscription patterns could be separate reference files. Reference implementations are mentioned but the bulk of content is inline. The TODO section at the end is appropriate but the overall document is heavy for a SKILL.md overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
ce9ca8e
- 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.