setup-codemap-cli
Guide for setup Codemap CLI for intelligent codebase visualization and navigation
54
43%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/mcp/skills/setup-codemap-cli/SKILL.mdQuality
Discovery
22%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 is too vague and lacks the structural elements needed for effective skill selection. It names a specific tool (Codemap CLI) which helps with distinctiveness, but fails to list concrete actions and entirely omits a 'Use when...' clause. The abstract terms 'visualization' and 'navigation' don't give Claude enough information to confidently select this skill over alternatives.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to set up Codemap, visualize code dependencies, map project structure, or install codemap CLI.'
List specific concrete actions the skill covers, e.g., 'Guides installation and configuration of Codemap CLI, generates dependency graphs, creates visual maps of project architecture, and navigates codebase relationships.'
Include natural trigger terms users might say, such as 'code map', 'dependency graph', 'project structure', 'code architecture', 'install codemap', '.codemap'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'setup Codemap CLI for intelligent codebase visualization and navigation' which names a tool and vague capabilities ('visualization and navigation') but does not list concrete actions like 'generate dependency graphs', 'map file relationships', or 'create visual diagrams'. The terms 'visualization' and 'navigation' are abstract. | 1 / 3 |
Completeness | The description partially addresses 'what' (setup Codemap CLI) but is vague about specific capabilities, and completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'Codemap CLI', 'codebase', 'visualization', and 'navigation' that a user might mention. However, it misses common variations and natural phrases users would say, such as 'code map', 'dependency graph', 'project structure', 'code architecture', or 'install codemap'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Codemap CLI' as a specific tool provides some distinctiveness, but 'codebase visualization and navigation' is broad enough to overlap with other code analysis, documentation, or architecture skills. The 'setup' framing helps narrow it somewhat. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
64%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 setup guide with strong actionability—every step has concrete, executable commands and exact file contents. Its main weaknesses are verbosity (the full hooks JSON example and inline CLAUDE.md content bloat the skill) and missing validation/error-recovery steps for file modification operations. The workflow is clear in sequence but could benefit from explicit checkpoints after writing configuration files.
Suggestions
Add validation steps after modifying CLAUDE.md, settings.json, and .gitignore (e.g., 'Verify the file was written correctly by reading it back' or 'Confirm the JSON is valid').
Move the full hooks JSON example to a separate reference file and link to it, keeping only the minimal session-start hook inline.
Remove the full options table from the CLAUDE.md insert content—Claude can regenerate this from the README loaded in step 3, or reference it externally.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy. The full hooks JSON example is quite verbose and could be trimmed. The CLAUDE.md content to be inserted is lengthy with a full options table that Claude could generate from the README. However, most content serves a purpose in the setup workflow. | 2 / 3 |
Actionability | The skill provides fully executable commands for every step—installation via brew/scoop, verification commands, exact JSON configurations for hooks, and exact markdown content to insert into CLAUDE.md. Everything is copy-paste ready with concrete paths and commands. | 3 / 3 |
Workflow Clarity | The 9-step sequence is clearly numbered and logically ordered, with a verification step after installation (step 5) and a test step (step 8). However, there are no explicit validation/error recovery steps—e.g., what to do if `codemap -help` fails for reasons other than not being installed, or if `brew install` fails. The workflow involves file modifications (.gitignore, CLAUDE.md, settings.json) without validation checkpoints after those writes. | 2 / 3 |
Progressive Disclosure | The skill references an external README for documentation (step 3), which is good. However, the skill itself is quite long (~180 lines) with the full hooks JSON example and the full CLAUDE.md content inline. The hooks configuration example and the options table could be split into separate reference files to keep the main skill leaner. | 2 / 3 |
Total | 9 / 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
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.