hook-development

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Quality

81%

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

Quality

Content

63%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 body is a thorough, actionable reference with real bundle files and a validated workflow, but it repeats several config examples and contains dangling references to a non-existent examples/ directory, which slightly weakens conciseness and navigation.

Suggestions

Add the missing examples/ directory with validate-write.sh, validate-bash.sh, and load-context.sh, or remove the dangling 'See examples/...' references to fix broken navigation.

De-duplicate the hooks.json wrapper and PreToolUse/Stop/SessionStart examples shown in 'Hook Configuration Formats', the per-event sections, and 'Plugin Hook Configuration' — keep one canonical version and cross-reference it.

Move the Security, Matchers, and Performance sections into the existing reference files (e.g. references/patterns.md) to reduce SKILL.md length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concepts Claude already knows, but the plugin hooks.json wrapper and PreToolUse/Stop/SessionStart config examples are shown three or more times across 'Hook Configuration Formats', the per-event sections, and 'Plugin Hook Configuration', which could be tightened.	3 / 5
Actionability	Provides many copy-paste-ready JSON configs and complete bash snippets (shebang, set -euo pipefail, jq parsing) plus specific commands like 'claude --debug' and the utility scripts; the gap is references to non-existent examples/*.sh files.	4 / 5
Workflow Clarity	The 9-step Implementation Workflow includes explicit validation checkpoints (validate-hook-schema.sh, test-hook.sh, claude --debug) and a Debugging section provides feedback loops, though error-recovery is documented separately from the main workflow rather than inline.	4 / 5
Progressive Disclosure	Real reference files (patterns.md, migration.md, advanced.md) and scripts are clearly signaled one level deep in Additional Resources, but large sections (security, matchers, performance) are inlined in SKILL.md and the body points to a missing examples/ directory and examples/*.sh files.	3 / 5
	Total	14 / 20 Passed

Description

100%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 excellent: third-person voice, explicit trigger guidance, concrete actions, and a distinct niche. It clearly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('create a hook', 'validate tool use', 'implement prompt-based hooks', 'block dangerous commands') plus the full event-name surface, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers 'what' ('creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API') and 'when' via an explicit 'should be used when the user asks...' trigger clause.	5 / 5
Trigger Term Quality	Includes extensive natural trigger phrases users would actually say ('create a hook', 'add a PreToolUse/PostToolUse/Stop hook', 'block dangerous commands') alongside event-name synonyms, with no common variations missing.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Claude Code plugin hooks) with highly specific triggers like '${CLAUDE_PLUGIN_ROOT}' and named hook events, making overlap with other skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (713 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/hook-development/SKILL.md
Commit: 6ed46da

Reviewed: 8 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.