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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

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

The body is highly actionable with a solid, validation-checkpointed workflow, but it suffers from verbosity and progressive-disclosure problems: a monolithic inline structure and several broken references to files (examples/*.sh, scripts/validate.sh) that do not exist in the bundle.

Suggestions

Create the referenced `examples/` directory with load-context.sh, validate-write.sh, and validate-bash.sh (or fix the references to point at existing files), since broken paths hurt both navigation and copy-paste readiness.

Move the matchers, security best-practices, performance, lifecycle, and debugging sections into the existing references/*.md files so SKILL.md reads as an overview rather than a 700-line monolith.

Trim redundant restatement — the "Benefits"/"Key points" callouts, DO/DON'T list, and the Quick Reference summary table largely duplicate the preceding sections and inflate token cost.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is mostly substantive API detail (JSON schemas, $CLAUDE_ENV_FILE, permissionDecision) that earns its place, but it is padded with redundant "Benefits"/"Key points" lists, a DO/DON'T section, and summary tables that restate earlier content and could be tightened.	2 / 3
Actionability	Abundant executable, copy-paste-ready guidance: complete hooks.json blocks, bash scripts with `set -euo pipefail` and jq parsing, and test commands like `echo '{...}' \| bash .../validate.sh`.	3 / 3
Workflow Clarity	The "Implementation Workflow" is a clearly sequenced 9-step process with explicit validation checkpoints (validate-hook-schema.sh, test-hook.sh, `claude --debug`) and a debugging section providing feedback loops for error recovery.	3 / 3
Progressive Disclosure	Three reference files and utility scripts are correctly signaled in "Additional Resources", but the body itself is a monolithic 700 lines that should be split, and it references a non-existent `examples/` directory (load-context.sh, validate-write.sh, validate-bash.sh) plus `scripts/validate.sh` which is also missing.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is well-crafted for activation: it pairs an explicit "used when" trigger list with a clear statement of capability and a distinctive niche. Its only weakness is mild verbosity and the soft over-claim "comprehensive guidance", which the description rubric does not directly penalize.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "block dangerous commands" — rather than vague language; the only soft over-claim is "comprehensive guidance", but the enumerated actions are concrete.	3 / 3
Completeness	Explicitly answers both: what ("Provides ... guidance for creating and implementing Claude Code plugin hooks") and when ("This skill should be used when the user asks to ..."), satisfying the explicit-trigger requirement that would otherwise cap this at 2.	3 / 3
Trigger Term Quality	Good coverage of natural terms users would say ("create a hook", "add a ... hook", "block dangerous commands") plus the full hook-event vocabulary; some entries like "use ${CLAUDE_PLUGIN_ROOT}" are more technical jargon, but overall coverage is strong.	3 / 3
Distinctiveness Conflict Risk	A clear niche — Claude Code plugin hooks — anchored by distinctive triggers (specific event names, ${CLAUDE_PLUGIN_ROOT}) that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 2f7766f

Reviewed: about 14 hours 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.