CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-code-hooks

Claude Code hook system for pre/post tool execution. Triggers on: hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging.

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xdarkmatter/claude-mods/claude-code-hooks/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

A concise, actionable quick-reference with good structure, undermined by broken bundle references and the absence of an explicit implementation workflow with validation feedback loops. Fixing the missing reference files and adding a sequenced hook-development checklist would raise the weaker dimensions.

Suggestions

Create the referenced bundle files (references/hook-events.md, configuration.md, security-patterns.md) or remove the dead links so progressive disclosure is functional.

Add a numbered implementation workflow (write script → register in settings.json → test with the echo piped command → verify block/allow behavior) with an explicit validate→fix→retry loop.

Expand the hook script example into a complete, runnable validation script rather than a skeleton that only parses the tool name.

DimensionReasoningScore

Conciseness

Lean reference composed of dense tables, copy-paste snippets, and a checklist with no conceptual padding; every section assumes Claude's competence and earns its tokens.

5 / 5

Actionability

Provides executable JSON config, matcher tables, and troubleshooting commands, but the hook script example is a partial skeleton (parses tool_name, lists exit codes) rather than a complete, runnable validation script.

4 / 5

Workflow Clarity

Material is organized by topic, but there is no sequenced implementation workflow with validation checkpoints; because hooks can block tool execution (destructive/batch context), the missing validate→fix→retry feedback loop caps this at anchor 3.

3 / 5

Progressive Disclosure

Structure and sectioning are good and references are clearly signaled, but the referenced bundle files (./references/hook-events.md, configuration.md, security-patterns.md) do not exist, so the one-level-deep navigation is broken and non-functional.

3 / 5

Total

15

/

20

Passed

Description

78%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.

A solid, specific description that names concrete capabilities and explicit trigger terms within a well-defined niche. It would reach the top level with scenario-based 'Use when...' guidance and broader synonym/extension coverage.

Suggestions

Add an explicit 'Use when ...' clause describing the scenarios that call for this skill (e.g., 'Use when you need to validate, audit, or block Claude Code tool calls').

Include natural synonyms and concrete artifacts users may mention, such as 'settings.json', 'hook scripts', or 'tool interceptors'.

DimensionReasoningScore

Specificity

Names the domain ('Claude Code hook system') and several concrete actions (pre/post tool execution, tool validation, audit logging), with only minor coverage gaps; falls short of anchor 5's comprehensive action list.

4 / 5

Completeness

States the 'what' (hook system for pre/post tool execution) and provides explicit trigger guidance via 'Triggers on: ...', but the 'when' is a keyword list rather than concrete usage scenarios, keeping it below anchor 5.

4 / 5

Trigger Term Quality

Good keyword coverage listing 'hooks, PreToolUse, PostToolUse, hook script, tool validation, audit logging' — terms a Claude Code user would naturally say — but lacks synonyms or file extensions needed for anchor 5.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Claude Code hooks) with distinct, specific triggers (PreToolUse, PostToolUse, hook script) that minimize overlap with other skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
NeverSight/skills_feed
Reviewed

Table of Contents

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.