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

78%

Does it follow best practices?

Impact

93%

1.14x

Average score across 3 eval scenarios

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./plugins/toolkit/skills/claude-code-hook-development/SKILL.md

Quality

Content

92%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 strong, action-oriented skill document: executable templates, table-driven quick reference, and explicit activation/verification/testing workflows with validation feedback loops. Only minor conciseness trimming would improve it further.

Dimension	Reasoning	Score
Conciseness	The body is efficient, using tables for exit codes, events, and matchers instead of prose, with a one-line intro and no padding about what hooks are; a couple of mildly explanatory asides (the security-feature note, wildcard rationale) keep it just below fully lean.	4 / 5
Actionability	Fully executable guidance: a concrete JSON settings structure, a complete copy-paste bash template with jq stdin parsing, specific commands (`claude --debug`, `/hooks`, `jq .`), and real matcher/wildcard examples covering the common cases.	5 / 5
Workflow Clarity	Multi-step processes are clearly sequenced with explicit validation checkpoints and feedback loops: the restart/`/hooks` activation flow, a loaded-hook verification checklist, and a 4-step safe-testing sequence for destructive blocking hooks.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references (hook-events.md plus three example files, all confirmed to exist), with detailed schemas and full examples appropriately split into separate files for easy navigation.	5 / 5
	Total	19 / 20 Passed

Description

63%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 excels at trigger-term quality and distinctiveness, giving Claude clear, natural guidance on when to surface it. Its main weakness is that it never states what the skill actually does, which caps completeness and specificity.

Suggestions

Lead with a concrete 'what' clause stating the skill's actions, e.g. 'Creates Claude Code hooks that run shell commands on specific events to add guardrails, automations, and policy enforcement.'

Keep the strong trigger phrasing but restructure as 'WHAT. Use when...' so both what and when are explicit, raising completeness.

Tighten 'automatically do X' to hook-specific framing to further reduce overlap risk with general automation skills.

Dimension	Reasoning	Score
Specificity	The description names the domain (Claude Code hooks) but never states concrete actions the skill performs; it only describes the trigger surface ("create a hook", "add a hook"), matching the anchor for naming a domain with minimal/generic actions.	2 / 5
Completeness	It provides a strong, explicit 'when' with concrete trigger phrases but never answers 'what' the skill does; the missing 'what' caps it below 4, while the unusually strong 'when' lifts it above a pure when-only anchor of 2.	3 / 5
Trigger Term Quality	Comprehensive natural-language triggers are given — "create a hook", "add a hook", "write a hook", "mentions Claude Code hooks", plus the behavioral synonyms "automatically do X" and "run X before/after Y" — covering the phrases users would actually say.	5 / 5
Distinctiveness Conflict Risk	"Claude Code hooks" with its specific behavioral triggers is a clear niche with minimal conflict risk; not 5 because "automatically do X" is somewhat broad and could overlap with general automation/scripting skills.	4 / 5
	Total	14 / 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
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
Path: plugins/toolkit/skills/claude-code-hook-development/SKILL.md
Commit: 4316684

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.