create-hook

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

Quality

55%

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

57%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 is well-structured and lean with useful concrete guidance on the discovery process, but it delegates the central hook template to a hooks.md file that is missing from the bundle, and its workflow lacks an explicit validation checkpoint for a consequential policy-enforcement task.

Suggestions

Ship the referenced hooks.md in references/ (with the hook JSON template and principles) or inline a minimal template/example directly in SKILL.md so the core artifact is reachable.

Add an explicit validation step to Iterate, e.g. 'Save the hook, then trigger the event and confirm it blocks/warns/injects as intended; fix and re-test before finalizing.'

Tighten Path Conventions by dropping the deliberative phrasing (e.g. 'Absolute paths only when intentional') to remove minor verbosity.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no padding about what hooks are), but the Path Conventions section has a few wordy clauses like 'Absolute paths are fine when intentional — just be deliberate about which you use' that could be trimmed.	4 / 5
Actionability	It gives concrete process guidance (extraction checklist, clarify-questions, event types like PreToolUse/SessionStart/Stop, path rules) but the core executable artifact — a hook JSON template/example — is delegated entirely to hooks.md, which is not present in the bundle, leaving key details missing.	3 / 5
Workflow Clarity	The Extract → Clarify → Path Conventions → Iterate sequence is clear, but validation is only mentioned as a final suggestion ('suggest ways to test it') rather than an explicit validate-then-proceed checkpoint with a fix/retry loop, which the rubric caps at 3 for consequential policy-enforcement workflows.	3 / 5
Progressive Disclosure	Sections are well-organized and the hooks.md reference is clearly signaled, but hooks.md does not exist in the references/ bundle, so the key template/principles the body depends on are unreachable — a navigation failure beyond a minor organization gap.	3 / 5
	Total	13 / 20 Passed

Description

53%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 clearly states what the skill does and carves out a distinct niche, but it lacks any 'Use when...' trigger guidance and its action verbs are high-level rather than concrete. It sits at a mid-pack level: clear domain, missing trigger completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user wants to block or gate agent actions, inject context at lifecycle events, or automate session-start/tool-use behavior.'

Replace abstract verbs with concrete actions, e.g. 'Create a hook (.json) to block specific tool calls, warn before risky commands, or inject context on PreToolUse/SessionStart/Stop.'

Include a few natural synonyms users would actually say (e.g. 'gate', 'block', 'lifecycle', 'session start') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Create a hook (.json) to enforce policy or automate agent lifecycle events' names the domain and a couple of high-level actions, but 'enforce policy' and 'automate...events' are abstract rather than a list of specific concrete actions as the score-4 anchor requires.	3 / 5
Completeness	There is a clear 'what' ('Create a hook...to enforce policy or automate agent lifecycle events') but no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'hook', 'policy', 'agent lifecycle events', 'enforce', and 'automate' are relevant, but common natural variations a user might say (e.g. 'block a command', 'gate tool use', 'run something on session start') and file-extension synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The hook-creation niche is distinct and the explicit 'Related skill: agent-customization' note scopes it, though the absence of explicit triggers leaves minor overlap risk with that closely related skill rather than the minimal conflict risk of a 5.	4 / 5
	Total	13 / 20 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: 9bb0f27

Reviewed: about 22 hours 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.