create-hook
Create and configure git hooks with intelligent project analysis, suggestions, and automated testing
47
36%
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/customaize-agent/skills/create-hook/SKILL.mdQuality
Discovery
32%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 identifies a clear domain (git hooks) and lists some relevant actions, but suffers from the absence of explicit trigger guidance ('Use when...') and somewhat vague capability language like 'intelligent project analysis' and 'suggestions.' Adding concrete trigger terms and specific hook types would significantly improve skill selection accuracy.
Suggestions
Add a 'Use when...' clause with trigger terms like 'git hook', 'pre-commit', 'post-commit', 'pre-push', 'commit hook', 'husky'.
Replace vague phrases like 'intelligent project analysis' and 'suggestions' with concrete actions such as 'generate pre-commit linting hooks, set up pre-push test runners, configure commit-msg format validation'.
Include common file/tool references users might mention, such as '.git/hooks', 'husky', 'lint-staged', or 'githooks'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (git hooks) and some actions (create, configure, project analysis, suggestions, automated testing), but the actions like 'intelligent project analysis' and 'suggestions' are somewhat vague rather than concrete. | 2 / 3 |
Completeness | Describes what the skill does but 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 since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes 'git hooks' which is a strong natural keyword, but misses common variations like 'pre-commit', 'post-commit', 'pre-push', '.git/hooks', 'husky', or 'lint-staged' that users might naturally mention. | 2 / 3 |
Distinctiveness Conflict Risk | 'Git hooks' is a fairly specific niche that distinguishes it from general git or code quality skills, but the mention of 'automated testing' and 'project analysis' could cause overlap with testing or CI/CD skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-designed workflow with clear steps, good decision trees for project analysis, and proper testing guidance. However, it is severely undermined by inlining the complete hooks guide and hooks reference documentation, which inflates the file to an enormous size and wastes context window tokens. The hook templates use pseudocode rather than executable examples, reducing actionability.
Suggestions
Remove the inlined 'Automate workflows with hooks' and 'Hooks reference' documentation sections entirely — they are already linked via URLs and massively bloat the skill
Replace the pseudocode hook templates (Type Checking, Auto-formatting, Security Scanning) with complete, executable scripts that can be copied directly
Consider splitting the detailed configuration questions (Section 2) into a separate reference file if the skill needs to stay concise
Add a concrete end-to-end example showing the full flow: detected tooling → suggested hook → generated script → test commands → expected output
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, containing the entire hooks documentation (~1500+ lines) appended after the skill-specific content. This massively bloats the token budget with reference documentation that should be linked, not inlined. The skill-specific content itself also includes unnecessary explanations (e.g., explaining what each hook type does when Claude already knows this from the appended docs). | 1 / 3 |
Actionability | The skill provides a clear workflow and decision tree for hook creation, but the hook templates are pseudocode comments rather than executable code. The configuration questions and testing steps are concrete, but the actual hook script examples are skeletal outlines rather than copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | The 4-step workflow (Analyze → Configure → Create → Test) is clearly sequenced with explicit validation checkpoints. Testing includes both happy and sad path verification, with clear debugging steps if issues occur. The decision tree for suggestions is well-structured. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text. The entire hooks guide and hooks reference documentation (~1000+ lines) is inlined directly into the skill file rather than being referenced via links. The skill already includes links to the official docs, making the inline duplication entirely redundant and counterproductive. | 1 / 3 |
Total | 7 / 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 (2317 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 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.