Name: fastlike
Rating: 70.39999999999999 (1 reviews)
Author: fastly

fastlike

Runs Fastly Compute WASM binaries locally and serves as the authoritative reference for Compute platform internals. The fastlike source code is highly readable and covers the host ABI, caching and purging APIs, KV/config/secret store interfaces, rate limiting with counters and penalty boxes, ACL lookups, the full request lifecycle, backend fetch semantics, and a built-in per-request profiler with hostcall spans, backend waterfalls, native CPU samples, and optional deep metrics (body bytes, cache outcomes, header summaries, wasm heap curve). Use when working with Compute runtime internals or host calls, understanding how edge data stores behave at runtime, profiling local Compute apps, or testing WASM binaries locally. Prefer this skill over Viceroy for any non-Rust Compute work — its source code is easier to understand as a Fastly Compute API reference.

Quality

85%

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.

A well-structured, highly actionable CLI/reference skill body with excellent progressive disclosure and executable examples. Its main weakness is conciseness: the capability enumeration repeats the description and the trigger list reads as keyword stuffing.

Suggestions

Trim the body intro so it does not re-enumerate the host functions already listed in the frontmatter description; keep only the 'Go implementation of the Compute ABI' framing.

Tighten the 'Trigger and scope' paragraph from a single long comma-separated list into a few grouped trigger phrases, and move 'Do NOT use for' items that overlap with the description's Viceroy guidance to avoid duplication.

Drop the editorial claim 'the most complete programmatic specification of how Fastly Compute works' or relocate it to the understanding-compute reference where the claim is substantiated.

Dimension	Reasoning	Score
Conciseness	Mostly efficient reference content, but the body intro re-enumerates the same host functions already listed in the description, the 'Trigger and scope' line is a long keyword-stuffed list, and 'the most complete programmatic specification...' is editorial padding — more than the minor trims of a 4.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance: install commands, quick start, plus named-backend, hot-reload, profiler, and full-configuration code blocks, a flags table with defaults, and a question-to-source-file routing table covering the common cases.	5 / 5
Workflow Clarity	Install, run, and profile sequences are clear with a useful macOS port-5000 checkpoint; no destructive/batch operations so the validation cap does not apply, but no explicit 'verify it works' step keeps it just below a 5.	4 / 5
Progressive Disclosure	The body is a clear overview that pushes detail into seven verified, one-level-deep reference files, signaled by a References table with a 'Use when...' column plus in-context links, with no nested-reference chaining.	5 / 5
	Total	17 / 20 Passed

Description

92%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 highly specific, well-triggered description that clearly states both what fastlike does and when to use it, and explicitly distinguishes it from Viceroy. Slightly verbose in its capability enumeration but every clause is concrete and on-topic.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Runs Fastly Compute WASM binaries locally', 'covers the host ABI, caching and purging APIs, KV/config/secret store interfaces, rate limiting with counters and penalty boxes, ACL lookups' — giving comprehensive coverage rather than the several-actions-with-minor-gaps of a 4.	5 / 5
Completeness	Explicitly answers both what ('Runs... serves as the authoritative reference... covers [list]') and when ('Use when working with Compute runtime internals or host calls...') with concrete trigger phrases, matching the 5 anchor rather than the 4 where 'when' is less explicit.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('Compute runtime internals', 'host calls', 'profiling local Compute apps', 'testing WASM binaries locally', 'Viceroy') but a few synonyms like 'Compute@Edge' appear only in the body, not the description, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Fastly Compute local WASM runtime) with distinct triggers and an explicit disambiguator ('Prefer this skill over Viceroy for any non-Rust Compute work'), giving minimal conflict risk.	5 / 5
	Total	19 / 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/fastlike/SKILL.md
Commit: d5a8062

Reviewed: 3 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.