fastly-cli
Executes Fastly CLI commands for managing CDN services, Compute deploys, and edge infrastructure. Use when running `fastly` CLI commands, creating or managing Fastly services from the terminal, deploying Fastly Compute applications, managing backends/domains/VCL snippets via command line, purging cache, configuring log streaming, setting up TLS certificates, managing KV/config/secret stores, checking service stats, authenticating with Fastly SSO, or working with fastly.toml. Also applies when working with Fastly service IDs in CLI context, or with `fastly service`, `fastly compute`, `fastly auth`, or any Fastly CLI subcommand. Covers service CRUD, version management, autocloning, and troubleshooting common CLI errors.
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, provides extensive and natural trigger terms, explicitly addresses both what the skill does and when to use it, and is clearly distinguishable from other skills. The description is comprehensive without being padded with fluff, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: managing CDN services, Compute deploys, deploying applications, managing backends/domains/VCL snippets, purging cache, configuring log streaming, setting up TLS certificates, managing KV/config/secret stores, checking service stats, authenticating with SSO, service CRUD, version management, autocloning, and troubleshooting CLI errors. | 3 / 3 |
Completeness | Clearly answers both 'what' (executes Fastly CLI commands for managing CDN services, Compute deploys, edge infrastructure) and 'when' with an explicit and extensive 'Use when...' clause covering numerous specific trigger scenarios including CLI commands, file references, and subcommands. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'fastly', 'fastly CLI', 'fastly compute', 'fastly service', 'fastly auth', 'fastly.toml', 'purging cache', 'CDN', 'edge infrastructure', 'backends', 'domains', 'VCL snippets', 'TLS certificates', 'KV store', 'secret store', 'Fastly SSO'. Includes both CLI subcommand names and conceptual terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around the Fastly CLI specifically. The triggers are tightly scoped to Fastly-specific terms (fastly.toml, Fastly service IDs, Fastly CLI subcommands) making it very unlikely to conflict with other skills like generic CDN or deployment tools. | 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 strong, well-structured skill that excels at actionability and progressive disclosure. It provides concrete, executable commands with explicit correct/incorrect patterns for common pitfalls, and cleanly delegates detailed topics to reference files. The main weaknesses are moderate verbosity in some sections and the lack of an explicit end-to-end workflow with validation checkpoints for multi-step operations like setting up a new service.
Suggestions
Add a concise end-to-end 'New Service Setup' workflow section with numbered steps and explicit validation checkpoints (e.g., verify domain resolves, verify backend responds, check activation status) to improve workflow clarity.
Tighten the KV Store Gotchas and Propagation Delays sections — consider moving detailed gotchas to the stores.md and troubleshooting.md references respectively, keeping only the most critical one-liners inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but some sections are slightly verbose — e.g., the propagation delays section, KV Store gotchas, and the repeated emphasis on --autoclone could be tightened. The 'CORRECT/WRONG' examples are useful but add length. Overall it respects Claude's intelligence but could trim ~20% without losing information. | 2 / 3 |
Actionability | Excellent actionability throughout — concrete, copy-paste-ready bash commands with correct flags, explicit correct/incorrect patterns for common pitfalls (boolean flags, domain creation, autoclone), and specific flag values. The host header override pattern and stats examples are fully executable. | 3 / 3 |
Workflow Clarity | Individual commands are clear, but there's no explicit end-to-end workflow with validation checkpoints (e.g., 'create service → add domain → add backend → validate → activate → verify'). The new service activation sequence mentions waiting but doesn't provide a structured retry/validation loop. For a tool that involves destructive/stateful operations like version activation and cache purging, explicit feedback loops would strengthen this. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference table linking to 8 topic-specific files (auth, compute, services, logging, NGWAF, stats, stores, TLS) plus a troubleshooting reference. The main SKILL.md serves as a well-organized overview with the most critical patterns inline, while directing to deeper content via one-level-deep references. | 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.