CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 provides highly actionable, concrete guidance for running Fastly Compute WASM binaries locally with fastlike. Its greatest strengths are the executable CLI examples, comprehensive flag documentation, and excellent progressive disclosure to reference files. The main weaknesses are minor verbosity in places and the lack of explicit validation/error-recovery steps in the workflow.

Suggestions

Add a brief validation step after installation (e.g., `bin/fastlike -version` or a smoke test command) and mention common startup errors (e.g., port already in use, invalid WASM binary) with recovery guidance.

Trim the introductory paragraph that restates what the source code reference table already conveys to reduce redundancy.

DimensionReasoningScore

Conciseness

The skill is mostly efficient and avoids explaining basic concepts, but includes some redundancy — the Fastlike vs Viceroy comparison table partially repeats trigger/scope guidance, and the full configuration example could be trimmed since individual flags are already documented in the table. The source code reference table is valuable but the introductory paragraph restates what the table already shows.

2 / 3

Actionability

Provides fully executable commands for installation, quick start, and multiple configuration scenarios. The CLI flags are documented with defaults and descriptions, and concrete bash examples are copy-paste ready with real flag combinations.

3 / 3

Workflow Clarity

The install-build-run sequence is clear, and the profiling workflow has a logical progression. However, there are no explicit validation checkpoints — no guidance on verifying the WASM binary is valid before running, no error recovery steps if fastlike fails to start, and no verification that backends are reachable. For a tool that runs arbitrary WASM binaries, some validation guidance would be expected.

2 / 3

Progressive Disclosure

Excellent structure with a clear overview in the main file and well-signaled one-level-deep references to specific topics (profiling.md, backends.md, config.md, abi.md, etc.). The references table at the bottom provides clear navigation with 'Use when...' context for each linked file. The source code reference table also serves as effective progressive disclosure into the codebase.

3 / 3

Total

10

/

12

Passed

Description

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 abundant natural trigger terms, explicitly states both what the skill does and when to use it, and clearly distinguishes itself from related skills like Viceroy. The description is detailed without being padded, and uses proper third-person voice throughout. The only minor concern is that the description is quite long, but the density of useful information justifies the length.

DimensionReasoningScore

Specificity

The description lists numerous 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, backend fetch semantics, per-request profiler with hostcall spans, backend waterfalls, CPU samples, and deep metrics.

3 / 3

Completeness

Clearly answers both 'what' (runs Fastly Compute WASM binaries locally, serves as reference for platform internals, with detailed capability list) and 'when' (explicit 'Use when' clause covering runtime internals, host calls, edge data stores, profiling, and testing WASM binaries locally, plus guidance on when to prefer over Viceroy).

3 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'Fastly Compute', 'WASM binaries', 'host calls', 'KV store', 'config store', 'secret store', 'rate limiting', 'ACL', 'profiler', 'backend fetch', 'edge data stores', 'Viceroy'. These cover a wide range of terms a developer working with Fastly Compute would naturally use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche around Fastly Compute/fastlike specifically. The description even explicitly differentiates from a competing skill (Viceroy), reducing conflict risk. The domain-specific terminology (Fastly Compute, WASM, host ABI, penalty boxes) makes accidental triggering very unlikely.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
fastly/fastly-agent-toolkit
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.