codebase-search
Search and navigate large codebases efficiently. Use when finding specific code patterns, tracing function calls, understanding code structure, or locating bugs. Handles semantic search, grep patterns, AST analysis.
66
63%
Does it follow best practices?
Impact
56%
0.98xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/codebase-search/SKILL.mdQuality
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 well-crafted skill description that excels across all dimensions. It provides specific capabilities, includes natural trigger terms developers would use, explicitly states both what it does and when to use it, and carves out a distinct niche for code search and navigation tasks.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'finding specific code patterns', 'tracing function calls', 'understanding code structure', 'locating bugs', and mentions specific techniques like 'semantic search, grep patterns, AST analysis'. | 3 / 3 |
Completeness | Clearly answers both what ('Search and navigate large codebases efficiently', 'semantic search, grep patterns, AST analysis') AND when ('Use when finding specific code patterns, tracing function calls, understanding code structure, or locating bugs'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'codebases', 'code patterns', 'function calls', 'code structure', 'bugs', 'grep', 'search'. These are terms developers naturally use when needing code navigation help. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on code search/navigation with distinct triggers like 'codebase', 'grep', 'AST analysis', 'tracing function calls'. Unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered and verbose, explaining concepts Claude already knows (regex syntax, git blame, what grep does). The content would be more effective at 1/4 the length, focusing on project-specific search patterns and tool configurations rather than generic tutorials. The empty example sections and lack of progressive disclosure further weaken its utility.
Suggestions
Remove all explanatory content about basic tools (grep, regex, git) that Claude already knows - focus only on project-specific patterns or non-obvious techniques
Extract the regex reference, git integration, and common patterns into separate reference files (e.g., PATTERNS.md, GIT_SEARCH.md) and link to them
Complete the empty example sections with actual executable examples showing input queries and expected outputs
Add validation checkpoints to workflows (e.g., 'If grep returns >50 results, narrow with directory targeting before proceeding')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations Claude already knows (what grep is, regex basics, git blame). Many sections are padded with obvious information like 'Benefits: Fast and precise' for grep. The skill is over 400 lines when it could be under 100. | 1 / 3 |
Actionability | Provides concrete grep patterns and examples, but many are pseudocode-like workflows rather than executable commands. The 'Examples' section at the end is empty placeholder content ('<!-- Add example content here -->'). | 2 / 3 |
Workflow Clarity | Multi-step workflows are present (e.g., 'Start broad, then narrow') but lack validation checkpoints. No feedback loops for when searches fail or return wrong results beyond generic troubleshooting tips at the end. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including detailed regex tutorials, git commands, and IDE tips that should be separate reference documents. Poor organization with redundant sections. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (535 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- supercent-io/skills-template
- Commit
c033769
- 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.