Name: fastly-stats
Rating: 75.2 (1 reviews)
Author: fastly

fastly-stats

Fastly traffic numbers: cache hit ratio, bandwidth, request counts, status-code and error rates, edge vs origin traffic, real-time requests-per-second, origin latency, per-domain traffic, account usage and billing totals. Owns the `fastly stats` CLI commands and the Historical Stats, Real-Time and Origin/Domain Inspector HTTP APIs. Use for any question that needs a number about how a Fastly service is performing or how much it is being used.

Quality

93%

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

93%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 dense, well-structured body: token-efficient, fully executable, with one-level-deep references to real bundle files. The only gap is the absence of a single explicit end-to-end workflow with a retry feedback loop, which keeps workflow clarity just below maximal.

Suggestions

Add one short end-to-end worked example that chains: pick window → query → assert meta filters → recompute gauges from counters → report window beside rate, to give an explicit validate-and-fix feedback loop.

Consider a one-line "How to pick the right subcommand" decision hint above the command table so the workflow entry point is unambiguous for ambiguous requests.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence — no preamble on what Fastly is; every line is a specific gotcha, rule, or executable snippet (e.g. "Bytes to GB is decimal SI: `bytes / 1e9`. Never `2^30`"). Each token earns its place, matching the score-5 anchor.	5 / 5
Actionability	Fully executable, copy-paste-ready commands and jq pipelines cover the common cases (hit ratio from counters, 5xx share, bandwidth ranking, usage totals, live RPS with a bounded kill), matching the score-5 anchor.	5 / 5
Workflow Clarity	Worked answers are sequenced with explicit validation checkpoints ("Read back `meta.from` / `meta.to`", "assert `meta` carries the filter you sent", "Do not read the newest bucket"), but there is no single canonical end-to-end workflow with a feedback loop, leaving it just below the score-5 anchor.	4 / 5
Progressive Disclosure	Body is an overview of rules/commands/worked examples, with bulk detail split one level deep into real, clearly signaled bundle files ([references/api.md], [references/fields.md], [references/debugging.md]) at the end of the Raw API section — easy navigation matching the score-5 anchor.	5 / 5
	Total	19 / 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 high-quality description: specific, third-person, and complete with explicit trigger guidance. It enumerates concrete capabilities and clear use-conditions, with only minor room to broaden natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists many concrete metrics ("cache hit ratio, bandwidth, request counts, status-code and error rates, edge vs origin traffic, real-time requests-per-second, origin latency, per-domain traffic, account usage and billing totals") and names the exact CLI commands and HTTP APIs owned — comprehensive coverage matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what (the enumerated metrics plus the owned `fastly stats` CLI and three HTTP APIs) and when ("Use for any question that needs a number about how a Fastly service is performing or how much it is being used") with concrete trigger phrasing, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Strong natural triggers ("any question that needs a number about how a Fastly service is performing or how much it is being used", "Fastly traffic numbers") with good metric-term coverage, but a few common synonyms (e.g. "metrics", "analytics", "dashboard") are absent, so it sits just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to Fastly statistics with a distinct niche ("Owns the `fastly stats` CLI commands and the Historical Stats, Real-Time and Origin/Domain Inspector HTTP APIs"), minimal overlap risk with adjacent Fastly skills.	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/fastly-stats/SKILL.md
Commit: 42a6070

Reviewed: 1 day 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.