CtrlK
BlogDocsLog inGet started
Tessl Logo

asim-parser-github-pr-packager

Packages the created and validated ASIM schema parser into a GitHub PR for the Azure-Sentinel repository. Use this skill when asked to package a parser into a GitHub PR.

60

Quality

70%

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 ./.github/skills/asim-parser-github-pr-packager/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is highly actionable with concrete paths, templates, and commands, but workflow clarity is undermined by missing validation feedback loops and broken step numbering, and progressive disclosure is limited by inline content with no reference files.

Suggestions

Fix the step numbering: the body skips Step 5 and has two 'Step 11' headers (Generate ARM templates and Commit) — renumber to a single continuous sequence.

Add explicit validation checkpoints for the risky/batch steps, e.g. verify the ARM script produced the expected templates without deleting files (validate -> fix -> re-run), and confirm the commit/PR creation succeeded before declaring done.

Extract the repeated YAML parser templates and changelog templates into reference files under references/ and link to them from a concise overview to improve progressive disclosure and remove redundancy.

DimensionReasoningScore

Conciseness

The body is largely lean and assumes Claude's competence, but it carries minor redundancy (two near-identical changelog templates and repeated YAML structure, duplicate 'Step 11' headers) that keeps it just short of 'every token earns its place.'

2 / 3

Actionability

It provides specific, copy-paste-ready guidance throughout — exact paths, a branch naming convention, full YAML templates with named fields, and a concrete ARM command — with placeholders only where input is genuinely runtime-supplied.

3 / 3

Workflow Clarity

Steps are clearly sequenced but validation checkpoints are missing/implicit for batch and repo-mutating operations, and step numbering is broken (Step 5 is missing; two 'Step 11' headers), which caps clarity at 2 per the destructive/batch guideline.

2 / 3

Progressive Disclosure

It has clear section organization but no bundle/reference files exist and substantial inline templates (two YAML parser templates, two changelog templates) that could be split remain inline, so it does not reach a clean overview-with-references structure.

2 / 3

Total

9

/

12

Passed

Description

75%

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 concrete and distinctive with an explicit 'Use when' trigger, scoring well on completeness and conflict risk. It is held back only by listing a single action and narrow trigger-term coverage.

DimensionReasoningScore

Specificity

It names a concrete action and target ('Packages the created and validated ASIM schema parser into a GitHub PR for the Azure-Sentinel repository') but lists only one primary action rather than multiple distinct concrete actions, matching the score-2 anchor.

2 / 3

Completeness

It explicitly states both what it does and when to use it via the explicit trigger clause 'Use this skill when asked to package a parser into a GitHub PR,' satisfying the score-3 anchor.

3 / 3

Trigger Term Quality

Relevant keywords ('GitHub PR', 'package a parser', 'Azure-Sentinel') are present but coverage is narrow and repeats one phrasing rather than offering common variations a user would naturally say, matching 'some relevant keywords but missing common variations.'

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific (packaging an ASIM parser into an Azure-Sentinel PR) with distinct triggers unlikely to match generic skills, satisfying the score-3 anchor.

3 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Azure/Azure-Sentinel
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.