writing-hookify-rules
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
65
47%
Does it follow best practices?
Impact
100%
2.38xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/hookify/skills/writing-rules/SKILL.mdQuality
Discovery
44%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 description is heavily skewed toward trigger terms and 'when to use' guidance but completely neglects explaining what the skill actually does. It reads more like a list of activation phrases than a skill description. A user or Claude selecting from many skills would know when to pick it but not what it delivers.
Suggestions
Add a clear 'what' clause explaining what hookify rules are and what the skill produces (e.g., 'Creates and configures hookify rules that [specific purpose]. Provides guidance on rule syntax, patterns, and best practices.').
Describe concrete actions the skill performs, such as generating rule files, validating syntax, or explaining configuration options.
Restructure to lead with capabilities first, then follow with the 'Use when...' trigger clause, following the pattern: '[What it does]. Use when [triggers].'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description does not describe any concrete actions or capabilities. It only mentions trigger phrases like 'create a hookify rule' and 'configure hookify' but never explains what hookify rules are, what they do, or what specific actions the skill performs. | 1 / 3 |
Completeness | While the 'when' is explicitly covered with trigger phrases, the 'what does this do' is essentially missing. The description never explains what hookify is, what rules do, or what the skill actually produces. The 'what' is very weak, which caps this at 1. | 1 / 3 |
Trigger Term Quality | The description includes multiple natural trigger phrases users would say: 'create a hookify rule', 'write a hook rule', 'configure hookify', 'add a hookify rule', and 'hookify rule syntax and patterns'. These are specific and varied enough to cover common user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | The term 'hookify' is highly specific and distinctive. It is unlikely to conflict with other skills since it targets a very specific tool/domain with unique terminology. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent concrete examples and complete rule templates that Claude can directly use. However, it is significantly over-verbose, spending many tokens on regex basics and writing advice that Claude already knows. The content would benefit from aggressive trimming and splitting reference material into separate files.
Suggestions
Remove the 'Regex Basics' and 'Pattern Writing Tips' sections entirely or reduce to a 3-line cheat sheet — Claude already knows regex syntax.
Remove the 'Good messages' advice section (explain what was detected, explain why, suggest alternatives) — this is generic writing guidance Claude doesn't need.
Add a validation step to the workflow: after creating a rule, describe how to test it triggers correctly (e.g., run a matching command and verify the warning appears).
Move the detailed event-type examples and common patterns into a separate REFERENCE.md file, keeping only the quick reference and one complete example in the main skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose at 200+ lines. The regex basics section explains concepts Claude already knows (what \s, \d, +, * mean). The 'good messages' section explains basic writing advice. The 'common pitfalls' section with too-broad/too-specific examples and the pattern writing tips could be drastically condensed. Much of this is reference material Claude doesn't need spelled out. | 1 / 3 |
Actionability | The skill provides fully copy-paste ready markdown rule templates with complete YAML frontmatter and message bodies. Every example is a concrete, complete rule file that can be directly written to disk. The conditions syntax, field options, and operators are all precisely specified. | 3 / 3 |
Workflow Clarity | The 'Creating a Rule' and 'Refining a Rule' workflows are listed as clear steps, but there's no validation checkpoint — no way to verify a rule actually triggers correctly before relying on it. For a system that intercepts potentially dangerous operations, a test/verify step is important but missing. | 2 / 3 |
Progressive Disclosure | The content has good section structure and references examples in `${CLAUDE_PLUGIN_ROOT}/examples/`, but the bulk of the content is monolithic — the regex basics, pattern tips, and extensive event-type guides are all inline when they could be in separate reference files. The quick reference at the end partially redeems this but also means information is duplicated. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- anthropics/claude-plugins-official
- Commit
fcdcd07
- 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.