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, and backend fetch semantics. Use when working with Compute runtime internals or host calls, understanding how edge data stores behave at runtime, exploring the WASM Component Model adaptation layer, 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.
71
86%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities, includes rich domain-specific trigger terms, explicitly states both what the skill does and when to use it, and even disambiguates itself from a related skill (Viceroy). The description is detailed yet focused, making it highly effective for skill selection among many options.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: running WASM binaries locally, host ABI, caching/purging APIs, KV/config/secret store interfaces, rate limiting with counters and penalty boxes, ACL lookups, request lifecycle, and backend fetch semantics. | 3 / 3 |
Completeness | Clearly answers both 'what' (runs Fastly Compute WASM binaries locally, covers host ABI, caching, KV stores, etc.) and 'when' with an explicit 'Use when...' clause listing four specific trigger scenarios, plus a comparative guidance note about preferring this over Viceroy for non-Rust work. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Fastly Compute', 'WASM binaries', 'host ABI', 'caching', 'purging', 'KV store', 'config store', 'secret store', 'rate limiting', 'ACL', 'backend fetch', 'WASM Component Model', 'Viceroy', 'edge data stores'. Good coverage of domain-specific terms a developer would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Fastly Compute platform internals and the fastlike tool specifically. The explicit comparison to Viceroy further disambiguates it from a closely related skill, reducing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that serves as both a practical CLI reference and a guide to using fastlike's source code as Compute documentation. Its main strengths are strong actionability with executable examples and excellent progressive disclosure with clearly organized references. The main weaknesses are some verbosity in the trigger/scope section and comparison table, and a lack of validation/error-handling guidance in the workflows.
Suggestions
Add a brief validation step after build (e.g., `bin/fastlike -version` or checking exit code) and a troubleshooting note for common startup failures to improve workflow clarity.
Trim the trigger/scope section — Claude can infer most of the 'Do NOT use for' items from context, and the trigger list could be shortened to key terms.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary content like the Fastlike vs Viceroy comparison table and explanatory text that could be trimmed. The trigger/scope section is quite long. However, the tables and CLI examples are well-structured and mostly earn their tokens. | 2 / 3 |
Actionability | Provides fully executable CLI commands for installation, quick start, and all configuration scenarios. The flag reference tables are complete and specific. Code examples are copy-paste ready with real flags and values. | 3 / 3 |
Workflow Clarity | The install-and-run workflow is clear, and the source-code-as-reference table provides good guidance for navigating the codebase. However, there are no validation checkpoints — e.g., no step to verify the build succeeded, no guidance on what to do if the WASM binary fails to load, and no feedback loops for debugging common issues. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in the main file and well-signaled one-level-deep references to specific topics (backends, config, build, test, ABI, understanding-compute-from-source). The references table at the bottom provides clear navigation with 'Use when...' context for each linked file. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- fastly/fastly-agent-toolkit
- Commit
e0f4205
- 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.