claude-code-hook-development

This skill should be used when the user asks to "create a hook", "add a hook", "write a hook", or mentions Claude Code hooks. Also suggest this skill when the user asks to "automatically do X" or "run X before/after Y" as these are good candidates for hooks.

1.14x

Quality

—

Does it follow best practices?

Impact

93%

1.14x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

85%

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 executable examples and well-sequenced verification workflows, and it uses progressive disclosure effectively with real reference files; its main weakness is mild redundancy between the inline summary tables and the referenced detail files.

Suggestions

Trim the 'Hook Events Summary' and 'Common Matchers' tables to the essentials or defer fully to hook-events.md to avoid duplicating referenced detail inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, built from tables and executable code, but the 'Hook Events Summary' and 'Common Matchers' sections partially duplicate content that the skill itself directs to the reference files, and a few explanatory asides could be trimmed.	2 / 3
Actionability	Provides copy-paste-ready artifacts: a complete settings.json hook block, an executable bash template with jq input parsing, concrete commands like '/hooks', 'claude --debug', and 'cat .claude/settings.json \| jq .', plus specific matcher examples.	3 / 3
Workflow Clarity	Sequences are explicit with validation checkpoints — the restart-or-/hooks activation step, the 'Verifying Hooks Are Loaded' checklist, and the four-step 'Testing Hooks Safely' (test on safe branch, verify the block, update config, restart and verify) form a clear feedback loop for a risky operation.	3 / 3
Progressive Disclosure	SKILL.md acts as a concise overview with clearly signaled, one-level-deep references (hook-events.md and three example files), all of which exist as real bundle files, and detail is appropriately split into those references.	3 / 3
	Total	11 / 12 Passed

Description

72%

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 has strong, natural trigger coverage and a clear niche, but it leans on triggers at the expense of explicitly stating the skill's concrete capabilities, leaving the 'what does this do' half implied.

Suggestions

Lead with a concrete capability statement (e.g., 'Create Claude Code hooks that run shell commands on events to enforce guardrails and automations') before the trigger clause.

Replace the repetitive 'create/add/write a hook' synonyms with distinct capabilities the skill supports (e.g., blocking commands, running checks after edits, auto-running tests).

Dimension	Reasoning	Score
Specificity	Phrases like 'create a hook', 'add a hook', 'write a hook' name concrete actions, but they are near-synonyms for the same action rather than a comprehensive set of distinct capabilities, and the description never states what producing a hook actually entails.	2 / 3
Completeness	The 'when' is explicit and strong ('should be used when...', 'Also suggest this skill when...'), but the 'what' is only implied through trigger verbs and relies on the user already knowing what hooks are, so it does not clearly answer both halves.	2 / 3
Trigger Term Quality	Covers natural user phrasings well — 'create a hook', 'add a hook', 'write a hook', 'Claude Code hooks', plus the indirect triggers 'automatically do X' and 'run X before/after Y' that a user would genuinely say.	3 / 3
Distinctiveness Conflict Risk	The 'Claude Code hooks' niche and its specific trigger phrasings are clearly distinguishable and unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
relative_links	Relative link issues: 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: dwmkerr/claude-toolkit
Commit: 5432a9f

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.