Tessl • The management layer for AI agent skills

The body is a model of token-efficient instruction writing: a clear safety-first quick reference, a well-sequenced workflow with explicit error handling and fallbacks, and precise output-format requirements, all in about 30 lines with zero padding. The only meaningful gap is the lack of a worked example showing placeholder substitution or a sample final response, which would make the substitution and labeling steps fully copy-paste unambiguous.

Suggestions

Add a short before/after example of placeholder substitution in step 4, e.g. a remediation snippet with <resource-group> and the same snippet with the substituted value from an actual resourceId.

Include a one-line sample of the final response format showing the required "Guidance source:" label followed by a learn.microsoft.com citation, so the output contract is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean and imperative, with every line carrying operational specifics ("Call `advisor_remediation_get` once with only `recommendationTypeId`, never `resourceId`") and no padding or explanation of concepts Claude already knows. Every token earns its place, matching anchor 5.	5 / 5
Actionability	Guidance is concrete: exact tool names (`advisor_remediation_get`, `advisor_recommendation_list`), parameters, the `RemediationNotFound` error branch, placeholder-substitution rules, and exact output label strings. Per the instruction-only scoring note the absence of code is not penalized, but there is no worked example of placeholder substitution or a sample final response, leaving minor gaps versus anchor 5.	4 / 5
Workflow Clarity	A clear five-step sequence with explicit error-recovery branches (RemediationNotFound -> Learn-docs fallback, "Ask which resource if ambiguous", "ask for missing values, never guess") and a safety checkpoint ("never execute without explicit confirmation"). This matches anchor 5's clear sequence with feedback loops for error recovery; no destructive/batch validation cap applies since the skill presents rather than executes remediation.	5 / 5
Progressive Disclosure	The skill is under 50 lines, self-contained with no external reference files (no references/, scripts/, or assets/ directories exist), and organized into well-signaled sections (Quick reference, Workflow, Final response). This meets the simple-skill exception where progressive disclosure scores 5 with just well-organized sections.	5 / 5
	Total	19 / 20 Passed

Description

66%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 concise, grammatical, uses third-person/declarative voice, and explicitly covers both what the skill does and when to use it, with a clear niche that poses minimal conflict risk. Its main weakness is thin trigger-term coverage — a single quoted trigger phrase with no synonyms or recommendation-category terms — and only a single named action.

Suggestions

Expand the WHEN clause with additional natural trigger phrases, e.g. WHEN: "fix Advisor recommendation", "resolve an Advisor recommendation", or when the user mentions Azure Advisor cost/security/performance recommendations.

Name one or two more concrete actions in the what portion, e.g. "Retrieves remediation steps, substitutes the affected resource's values, and cites the guidance source" to lift specificity from one named action to several.

Mention the recommendation categories (cost, security, reliability, performance, operational excellence) so users describing a category-level problem can still match this skill.

Dimension	Reasoning	Score
Specificity	"Remediate Azure Advisor recommendations" names the domain and one concrete action, but does not enumerate the underlying capabilities (retrieve remediation guidance, substitute resource values, label the guidance source). This matches anchor 3 ('names domain and 1-2 concrete actions'), not 4, which expects several listed specific actions.	3 / 5
Completeness	Both what ("Remediate Azure Advisor recommendations") and when (WHEN: "fix Advisor recommendation") are explicitly present, so the missing-trigger cap at 3 does not apply. However the when clause is a single terse quoted phrase rather than multiple concrete trigger phrases, matching anchor 4 ('both what and when; when could be more explicit') rather than 5.	4 / 5
Trigger Term Quality	Natural terms like "Azure Advisor", "recommendation", and the quoted phrase "fix Advisor recommendation" are present and would be said by a user needing this skill, but coverage is thin: common variations and synonyms ("resolve", "address", cost/security/performance recommendation categories) are missing. Fits anchor 3 ('some relevant keywords but missing common variations') better than 4.	3 / 5
Distinctiveness Conflict Risk	"Azure Advisor" is a specific named Azure service with distinct product-specific triggers; the description is unlikely to fire for any unrelated skill. Clear niche with minimal conflict risk, matching anchor 5.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/azure-skills
Path: .github/plugins/azure-advisor/skills/azure-advisor-actionability/SKILL.md
Revision: 9bbcb2e

Reviewed: 8 days ago

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.

azure-advisor-actionability

Table of Contents

Is this your skill?