hook-rules

Scaffold and validate hookify rule files (.claude/hookify.NAME.local.md) that turn a prose guideline into a pattern-matched hook message, via scripts/scaffold_rule.py and scripts/validate_rule.py. Use when the user asks to create, write or validate a hookify rule, or to turn a rule of thumb into an enforced hook. [EXPLICIT]

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-native-toolkit/skills/hook-rules/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The SKILL.md body is a well-structured router that keeps the stage contract lean and delegates depth to real reference files. Its weaknesses are inline actionability and an implicit validation loop, both consequences of pushing all executable detail into references.

Suggestions

Add a one-line per-reference hint in the resource map (e.g. which playbook covers scaffolding vs. patterns/events) so Claude knows which file to open without scanning both.

Inline one minimal scaffold+validate command pair (e.g. `python scripts/scaffold_rule.py ...` then `python scripts/validate_rule.py <file>`) so the body is executable without opening a reference.

Make the Procedure's validation step a feedback loop: 'validate; if errors, fix and re-validate before proceeding.'

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the multilingual Contract section and the verbose Spanish wire-packet block add tokens that could be trimmed.	4 / 5
Actionability	The Procedure gives high-level steps ('open the matching references/ playbook', 'Apply its decision tables') and points to scripts, but the body itself lacks copy-paste-ready commands or code; executable detail is deferred to references.	3 / 5
Workflow Clarity	Three sequenced steps are listed including a validation step, but checkpoints are implicit and there is no validate->fix->retry feedback loop for a tool that writes rule files.	3 / 5
Progressive Disclosure	Content is split into a lean overview with one-level-deep references (references/full-playbook.md, references/patterns-and-events.md, both real files), but the resource map does not signal which reference to open for which sub-task.	4 / 5
	Total	14 / 20 Passed

Description

87%Weight 40%Scale 1-5

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 is strong: it states concrete actions with named scripts, gives explicit 'Use when' triggers, and clearly distinguishes the skill from adjacent raw-hook tooling. Minor gaps in synonym coverage keep trigger quality and specificity just short of perfect.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('Scaffold and validate hookify rule files', 'turn a prose guideline into a pattern-matched hook message') with specific tooling paths, listing several specific actions with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ('Scaffold and validate hookify rule files... via scripts/...') and when ('Use when the user asks to create, write or validate a hookify rule, or to turn a rule of thumb into an enforced hook') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases ('create, write or validate a hookify rule', 'turn a rule of thumb into an enforced hook') with good coverage, though 'hookify rule' is somewhat jargon-laden and a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche tied to a specific file path (.claude/hookify.NAME.local.md) and explicit routing away from adjacent domains ('for raw hooks blocks, use hook-creator'), giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

68%

Warnings & errors only

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 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	11 / 16 Passed

Repository: JaviMontano/claude-plugins
Path: plugins/claude-native-toolkit/skills/hook-rules/SKILL.md
Commit: e8f986b

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.