code-search-assistant
Finds code by meaning, structure, or text across large codebases — picks the right search strategy (grep, AST query, call graph walk, semantic search) for the question being asked. Use when the user asks where something is implemented, when navigating unfamiliar code, or when a simple grep isn't enough.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill code-search-assistant100
Quality
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
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 an excellent skill description that clearly articulates what the skill does (multi-strategy code search) and when to use it (implementation questions, unfamiliar codebases, complex searches). It uses third person voice correctly, includes natural trigger terms, and is distinctive enough to avoid conflicts with simpler search tools.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Finds code by meaning, structure, or text' and explicitly names four search strategies (grep, AST query, call graph walk, semantic search). This provides clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (finds code using multiple search strategies) AND when with explicit 'Use when' clause covering three distinct trigger scenarios: implementation location questions, unfamiliar code navigation, and complex search needs. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'where something is implemented', 'navigating unfamiliar code', 'grep isn't enough', plus technical terms like 'AST query', 'call graph', 'semantic search' that power users would recognize. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around advanced code search strategies. The specific mention of AST queries, call graph walks, and semantic search distinguishes it from basic file search or grep-only tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently maps question types to search strategies with concrete, executable examples. The decision table at the top provides immediate value, the worked example demonstrates real-world application, and the 'Do not' section prevents common mistakes. Token-efficient throughout with no wasted explanation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanation of what grep is or how code search works conceptually—jumps straight to decision tables and actionable patterns. The worked example is dense with signal, not padding. | 3 / 3 |
Actionability | Provides executable commands throughout (rg flags, semgrep patterns, specific regex patterns). The worked example shows exact command sequences with expected results. Copy-paste ready. | 3 / 3 |
Workflow Clarity | The worked example demonstrates a clear multi-step sequence with explicit reasoning at each step. The 'Do not' section provides validation checkpoints by warning against common mistakes. The output format template ensures structured results. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (decision table → tool-specific guidance → worked example → anti-patterns → output format). Self-contained at ~150 lines with no need for external references. Tables and headers enable quick scanning. | 3 / 3 |
Total | 12 / 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.
- 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.