create-hook

Create a hook (.json) to enforce policy or automate agent lifecycle events.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./extensions/copilot/assets/prompts/skills/create-hook/SKILL.md

Quality

Content

65%

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

The skill body is concise and well-sequenced for a guided creation workflow, but it leans on a hooks.md reference that is not bundled and lacks a built-in validation step. Fixing the broken reference and inlining a minimal template would lift its weakest dimensions.

Suggestions

Inline a minimal executable hook JSON template/example instead of deferring entirely to hooks.md, which is absent from the bundle — the core deliverable is currently unreachable.

Add an explicit validation/test checkpoint in the Iterate loop (e.g., validate the hook JSON against the schema, then run a dry test) rather than only suggesting the user test it.

Either bundle hooks.md under references/ or inline its template and principles so the 'Load and follow hooks.md' reference is not a navigation dead end.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what hooks are and keeps each section to a few focused lines, so every token earns its place.	3 / 3
Actionability	It gives a concrete path (.github/hooks/), specific event types (PreToolUse, SessionStart, Stop), and clear steps, but the core deliverable — a hook JSON template — is deferred to hooks.md, which is not present in the bundle, leaving key details missing.	2 / 3
Workflow Clarity	A clear Extract → Clarify → Iterate sequence exists with a clarify-the-ambiguous-parts loop, but verification is only suggested to the user ('suggest ways to test it') rather than an explicit validation checkpoint built into the workflow.	2 / 3
Progressive Disclosure	The body is well organized into short sections, but its single external reference (hooks.md) does not resolve — there is no references/ bundle — so navigation is a dead end rather than a one-level-deep pointer.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 identifies a clear deliverable and niche but stays abstract and lacks any explicit "when to use" trigger guidance. It is competent but capped at the midpoint across all dimensions.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when the user wants to enforce agent behavior rules or automate session/tool lifecycle events') to raise completeness.

Replace the abstract 'enforce policy' with concrete capabilities (e.g., block commands, gate tool use, inject context at SessionStart/PreToolUse) to improve specificity.

Include natural trigger variations users would actually say (e.g., 'prevent Claude from running X', 'always check before doing Y') for better trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names a concrete deliverable ("Create a hook (.json)") and two purposes ("enforce policy", "automate agent lifecycle events"), but those purposes are abstract rather than a comprehensive list of specific actions, matching the score-2 anchor.	2 / 3
Completeness	It answers "what" (create a hook to enforce/automate) but has no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"hook", "policy", and "agent lifecycle events" are reasonably natural terms, but coverage of common user phrasings (e.g. "prevent Claude from running X", "always check before Y") is missing, so it sits at the some-relevant-keywords level.	2 / 3
Distinctiveness Conflict Risk	Hooks are a distinct niche, but "enforce policy" is generic and the skill explicitly overlaps with the related `agent-customization` skill, so it could still trigger for similar skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: posit-dev/positron
Path: extensions/copilot/assets/prompts/skills/create-hook/SKILL.md
Commit: b87c504

Reviewed: 2 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.