Name: fastly-reference-architectures
Rating: 67.2 (1 reviews)
Author: fastly

fastly-reference-architectures

Curated GitHub repositories demonstrating working reference architectures on the Fastly platform, from single Compute applications to systems combining multiple Fastly products. Use when designing a new solution on Fastly and a worked example of the target pattern would help, or when implementing and a concrete assembled reference would clarify the shape of the code. Not for documentation of how a specific Fastly tool or API works on its own — see the tool-specific skills for that.

Quality

80%

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

Quality

Content

78%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.

An appropriately minimal, well-structured body that uses progressive disclosure correctly — overview in SKILL.md, catalog in references/examples.md. It is maximally concise; its weakest area is actionability, since the body delegates essentially all guidance to the referenced file without any in-body usage hint.

Suggestions

Add one sentence in the body describing how to use the catalog, e.g. 'Scan the Platform column in examples.md to find a project whose stack matches the user's target pattern, then study its repo for the assembled shape.'

Consider noting how to combine patterns (single-product vs multi-product examples) so Claude knows when to consult more than one reference.

Dimension	Reasoning	Score
Conciseness	The body is a heading plus a single one-line pointer to references/examples.md; every token earns its place and it assumes Claude's competence with no padding, matching the 'lean and efficient' anchor.	5 / 5
Actionability	The body gives a concrete pointer to a real file containing the actionable catalog (repo links with descriptions), but all of the actionable detail lives in the reference rather than in the body itself, leaving the body's own guidance incomplete.	3 / 5
Workflow Clarity	As a single-purpose catalog skill the single action (consult examples.md) is unambiguous and no validation is needed, but the body offers no guidance on how to select or match a project within the catalog, a minor gap below the top anchor.	4 / 5
Progressive Disclosure	SKILL.md is a clean overview pointing one level deep to references/examples.md via a clearly signaled markdown link, with the catalog content appropriately split into the reference file (a well-organized Project/Description/Platform table), matching the top anchor.	5 / 5
	Total	17 / 20 Passed

Description

82%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 strong, well-structured description that clearly states what the skill provides, when to use it, and where its boundary with tool-specific skills lies. Its only soft spot is specificity, since as a catalog skill it describes one curated capability rather than enumerating several concrete actions.

Dimension	Reasoning	Score
Specificity	It names the domain (Fastly reference architectures) and one concrete capability (curated GitHub repos demonstrating working architectures) with scope detail ('from single Compute applications to systems combining multiple Fastly products'), but does not list several distinct actions, so it sits at the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	It explicitly answers both what ('Curated GitHub repositories demonstrating working reference architectures on the Fastly platform...') and when ('Use when designing a new solution on Fastly... or when implementing...'), with concrete trigger phrases and an explicit negative boundary, matching the top anchor.	5 / 5
Trigger Term Quality	Natural trigger phrasing is good — 'designing a new solution on Fastly', 'a worked example of the target pattern would help', 'implementing', 'reference architectures' — covering the main ways a user would phrase this need, though a few natural synonyms (e.g. 'sample app', 'Fastly starter', 'example project') are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (worked reference architectures) and explicitly distinguishes itself from related skills ('Not for documentation of how a specific Fastly tool or API works on its own — see the tool-specific skills'), giving minimal conflict risk.	5 / 5
	Total	17 / 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: fastly/fastly-agent-toolkit
Path: skills/fastly-reference-architectures/SKILL.md
Commit: 42a6070

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.