Build and merge repository .gitignore files or global gitignore files using github/gitignore templates with smart target separation. Use when the user asks to "create gitignore", "build .gitignore", "add gitignore templates", "set up gitignore", "update gitignore", "create global gitignore", or requests "/gitignore". Also trigger when observing projects without .gitignore, seeing untracked files like node_modules/, .env, __pycache__/, or *.log in git status, or after git init in a new repo. Boundary: not for .dockerignore or other non-git ignore files.
68
81%
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 an excellent skill description that hits all the marks. It provides specific actions, comprehensive trigger terms covering both explicit user requests and contextual situations, clear 'what' and 'when' guidance, and an explicit boundary to prevent conflicts with similar skills. The description is well-structured and uses third person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build and merge repository .gitignore files', 'global gitignore files', 'using github/gitignore templates', 'smart target separation'. Also specifies boundary conditions. | 3 / 3 |
Completeness | Clearly answers both 'what' (build and merge .gitignore files using github/gitignore templates) and 'when' (explicit 'Use when...' clause with multiple trigger phrases, contextual triggers, and boundary exclusions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create gitignore', 'build .gitignore', 'add gitignore templates', 'set up gitignore', 'update gitignore', 'create global gitignore', '/gitignore'. Also includes contextual triggers like 'node_modules/', '.env', '__pycache__/', 'git init'. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on .gitignore files with an explicit boundary statement excluding .dockerignore and other non-git ignore files, making it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides an exceptionally thorough and well-structured workflow for building gitignore files with clear decision tables, validation checkpoints, and concrete commands. However, it is significantly over-verbose—repeating formatted output examples multiple times, explaining gitignore syntax Claude already knows, and including content inline that should be in reference files. The actionability and workflow design are strong, but the token cost is unnecessarily high.
Suggestions
Remove the 'Gitignore Syntax Reminders' section entirely—Claude already knows gitignore syntax, and this wastes ~10 lines of context.
Consolidate the three near-identical template structure examples (Steps 6, Source Attribution, Preserve User Content) into a single reference in a separate file, with just one brief inline example.
Remove or drastically shorten the 'When to Use' section since it duplicates the skill description/trigger metadata.
Move the detailed detection tables and script reference to a separate reference file, keeping only a summary in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It explains gitignore syntax basics Claude already knows, includes extensive ASCII art box-drawing for markers, repeats the same template structure multiple times (Steps 6, Important Notes, and Preserve User Content all show nearly identical formatted output), and has redundant tables. The 'When to Use' section duplicates the description. Much of this could be cut by 50%+ without losing actionable information. | 1 / 3 |
Actionability | The skill provides concrete, executable commands (scripts/merge-gitignore.sh with specific flags), clear detection tables mapping indicator files to templates, specific exit codes, and copy-paste ready examples. The workflow steps give precise instructions for each scenario. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints: user confirmation at Step 3 (recommendations), EOL conflict resolution at Step 5, diff preview with confirmation at Step 6, and final write confirmation at Step 7. Error recovery is addressed via exit codes and the edit option. The feedback loop of detect → present → confirm → preview → write is well-defined. | 3 / 3 |
Progressive Disclosure | The skill references examples.md and a merge-gitignore.sh script, which is good structure. However, no bundle files are provided to verify these exist, and the main SKILL.md itself contains too much inline content that could be split out (e.g., the detailed template structure examples, gitignore syntax reminders, and the full script reference could live in separate files). The inline content is heavy for an overview document. | 2 / 3 |
Total | 9 / 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.
2a29a4a
Table of Contents
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.