create-hook

Create and configure git hooks with intelligent project analysis, suggestions, and automated testing

Quality

43%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/create-hook/SKILL.md

Quality

Content

37%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's own ~220 lines are reasonably structured and actionable, but they are buried under ~2000 lines of pasted official documentation that Claude already knows, wrecking token efficiency and progressive disclosure. The code templates are also pseudocode rather than executable.

Suggestions

Delete the inlined official documentation (lines ~229–2317) and replace it with a one-line pointer to https://docs.claude.com/en/docs/claude-code/hooks; keep only the skill-specific guidance in SKILL.md.

Replace the comment-only hook templates with minimal executable scripts (or move full templates into a references/ file) so the guidance is copy-paste ready.

Move the per-tooling suggestion table and the 8 configuration questions into a references/ file referenced from a concise overview, keeping SKILL.md under ~50 lines.

Dimension	Reasoning	Score
Conciseness	The body inlines ~2000 lines of verbatim official hooks documentation (the full 'Automate workflows with hooks' guide and 'Hooks reference' from line 229 onward) explaining concepts Claude already knows (what hooks are, the lifecycle table, every event schema), which is the textbook score-1 anti-pattern of severely verbose, heavily padded content.	1 / 5
Actionability	The skill's own portion gives concrete process guidance (per-tooling hook suggestions, an 8-point configuration question list, implementation standards) but its code templates are comment-only pseudocode (e.g. '// Read stdin JSON ... // Run: npx tsc --noEmit') rather than executable code, matching the 3-anchor (some concrete guidance, pseudocode instead of executable code).	3 / 5
Workflow Clarity	There is a clear four-step sequence (Environment Analysis → Hook Configuration → Hook Creation → Testing & Validation) with a dedicated validation section covering happy/sad paths and an 'If Issues Occur' debug feedback loop, fitting the 4-anchor (clear sequence with most checkpoints present); minor gaps are the awkward inline numbering in the testing section and that validation is offered rather than enforced.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the entire official hooks guide and reference — content that clearly belongs in separate files or external links — is inlined as a monolithic block, matching the 2-anchor (minimal effective structure; content that belongs in separate files is inlined).	2 / 5
	Total	10 / 20 Passed

Description

50%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 adequate — it names the domain and a few actions in third person — but lacks any explicit trigger guidance and leans on the buzzword "intelligent". The "git hooks" wording also mismatches the skill's actual Claude Code hooks focus, raising conflict risk.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to add Claude Code automation hooks (type-check, format, lint, security) to a project.'

Replace the fluffy 'intelligent project analysis, suggestions' with concrete capabilities like 'detects project tooling and suggests type-check, format, lint, and security hooks'.

Clarify these are Claude Code hooks (not git hooks) to avoid triggering for users wanting husky/pre-commit git hooks.

Dimension	Reasoning	Score
Specificity	The description names the domain ("git hooks") and a few concrete actions ("Create and configure", "automated testing"), but pads them with the vague buzzword "intelligent project analysis" and the generic "suggestions", so it sits at the 3-anchor (domain + 1-2 concrete actions) rather than the more comprehensive 4-anchor.	3 / 5
Completeness	It clearly states what the skill does ("Create and configure git hooks with ... analysis, suggestions, and automated testing") but has no "Use when..." clause or equivalent trigger guidance, so per the rubric cap completeness sits at 3 (clear what, missing when).	3 / 5
Trigger Term Quality	"git hooks" is a natural term a user would say, but coverage stops there; common variations/synonyms like "pre-commit", "hook scripts", "automation", or "Claude Code hooks" are missing, matching the 3-anchor (some relevant keywords but missing common variations).	3 / 5
Distinctiveness Conflict Risk	The phrase "git hooks" suggests a fairly distinct niche, but the body is actually about Claude Code hooks (PreToolUse/PostToolUse/settings.json), so the description could trigger for users wanting real git hooks (husky/pre-commit), placing it at the 3-anchor (somewhat specific but could overlap with related skills).	3 / 5
	Total	12 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (2317 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 40 suspicious	Warning

	Total	13 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/create-hook/SKILL.md
Commit: 8539779

Reviewed: 4 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.