kit-cli-navigator
Run focused `kit` CLI commands (file-tree, symbols, search, semantic discovery, dependency analysis, and exports) to build high-signal repository context fast. Use when you need to understand an unfamiliar codebase, prep context for Claude, plan refactors, audit dependencies, or answer “where is X implemented?” without manually grepping.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 identifies the tool (kit CLI), enumerates specific capabilities, and provides explicit trigger scenarios via a 'Use when' clause. The natural language trigger terms cover a good range of user intents, and the description is distinctive enough to avoid conflicts with other skills. Minor note: it uses second person 'you' in the 'Use when' clause, but this is directed at Claude's decision-making rather than the user, so the impact is minimal.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: file-tree, symbols, search, semantic discovery, dependency analysis, and exports. These are clearly defined capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both what ('Run focused kit CLI commands for file-tree, symbols, search, semantic discovery, dependency analysis, and exports') and when ('Use when you need to understand an unfamiliar codebase, prep context for Claude, plan refactors, audit dependencies, or answer where is X implemented'). Explicit 'Use when' clause is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'understand an unfamiliar codebase', 'plan refactors', 'audit dependencies', 'where is X implemented', 'grepping', 'repository context', 'search', 'symbols'. Good coverage of how users naturally phrase these needs. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to the 'kit' CLI tool for repository exploration and code understanding. The specific tool name and enumerated capabilities (file-tree, symbols, semantic discovery, dependency analysis, exports) create a distinct niche unlikely to conflict with general coding or search skills. | 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 well-structured, highly actionable skill that provides concrete CLI commands and realistic worked examples for repository exploration with kit. Its main weakness is moderate verbosity—the repeated subagent delegation instructions and some explanatory text could be trimmed. The progressive disclosure structure is reasonable but the referenced reference.md is not provided in the bundle, making it hard to fully validate.
Suggestions
Trim the repeated 'Subagent:' prefixes and consolidate the subagent delegation pattern into a single note at the top of the workflow section rather than repeating it in every step.
Provide the referenced reference.md file in the bundle, or remove references to it if it doesn't exist, to ensure progressive disclosure actually works.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elaboration. The repeated 'Subagent:' prefixes and the tight coupling with 'subagent-orchestration' adds bulk. Some sections like 'When to activate' explain things Claude could infer. The best practices and pitfalls sections, while useful, could be tightened. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready CLI commands throughout with specific flags, output formats, and file paths. The three worked examples show realistic end-to-end workflows with exact commands. Every step includes an executable command rather than vague direction. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced in 7 numbered steps with logical progression from scoping → baseline → APIs → search → relationships → export → caching. Each step has explicit commands and expected outputs. The 'Common pitfalls & recoveries' section provides error recovery guidance, and the workflow includes validation-like checkpoints (confirm scope, check cache status, verify exit status). | 3 / 3 |
Progressive Disclosure | The skill references 'reference.md' for flag-level detail and links to external docs, which is good progressive disclosure. However, the bundle has no actual reference.md file provided, making it impossible to verify the reference exists. The main file itself is quite long (~150 lines of content) and some of the detailed command examples could potentially be split into the reference file to keep the overview leaner. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- cased/claude-code-plugins
- Commit
a026516
- 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.