ghost-repo-context
Scans directory structure, detects projects, maps dependencies, and documents code organization into a repo.md file. Use when the user needs a codebase overview, project structure map, or repository context before security analysis.
99
100%
Does it follow best practices?
Impact
100%
3.57xAverage 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 well-crafted skill description that excels across all dimensions. It provides specific concrete actions, includes natural trigger terms users would actually say, explicitly addresses both what and when, and carves out a distinct niche around repository structure analysis. The description follows best practices with third-person voice and appropriate length.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Scans directory structure', 'detects projects', 'maps dependencies', and 'documents code organization into a repo.md file'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (scans, detects, maps, documents) AND when with explicit 'Use when...' clause specifying triggers: 'codebase overview', 'project structure map', 'repository context before security analysis'. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'codebase overview', 'project structure map', 'repository context', 'directory structure', 'dependencies'. These cover common variations of how users might request this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Has a clear niche with distinct triggers around repository scanning and structure documentation. The specific output artifact (repo.md file) and security analysis context make it unlikely to conflict with general code or documentation skills. | 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 a well-crafted skill that demonstrates excellent token efficiency, concrete actionability, and clear workflow structure. It appropriately delegates detailed instructions to separate files while maintaining a clear overview, includes validation checkpoints with retry logic, and handles edge cases (cache exists, no projects found, summarization failures).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, assuming Claude's competence. No unnecessary explanations of concepts Claude already knows, and every section serves a clear purpose. | 3 / 3 |
Actionability | Provides executable bash commands, specific file paths to reference, and concrete steps. The workflow is copy-paste ready with clear variable handling and tool restrictions. | 3 / 3 |
Workflow Clarity | Clear 5-step sequence with explicit validation in step 4 (read back and verify), error handling (retry once), and conditional logic (cache check, no-projects fallback, summarization failure handling). | 3 / 3 |
Progressive Disclosure | Excellent structure with SKILL.md as overview pointing to one-level-deep references (detector.md, summarizer.md, template-repo.md). Clear navigation with well-signaled file references. | 3 / 3 |
Total | 12 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- ghostsecurity/skills
- Commit
3c1875a
- 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.